Methods › General › Stochastic Optimization › SGD › Papers where code ran, page 1
Stochastic Gradient Descent
SGD
Papers archive 2025-07-28
archive papers tagged: 2,021 · with a code link: 591 · where Syntology ran a sample: 192 (161 with a run with no instrument failure, 31 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (192 of 2,021 tagged: 161 with a run with no instrument failure, 31 where every run was a failure of Syntology's instrument)
Syntology We ran code from the paper's repository; we did not isolate this method inside it.
Page 1 of 2: papers 1 to 100 of the 192 tagged papers where Syntology ran at least one harvested sample (161 with a run with no instrument failure, 31 where every run was a failure of Syntology's instrument), newest first by the archive's date (ties by arXiv id). This is a filter on Syntology's record ordered by date only, not a ranking; a run is not a correctness claim. A paper missing from this list is not a recorded non-run: it may have no arXiv id, no harvested code, or only samples that have not run yet.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Sharpness-Aware Machine Unlearning 16 Jun 2025 · 0 repositories · arXiv:2506.13715Syntology 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
AdamS: Momentum Itself Can Be A Normalizer for LLM Pretraining and Post-training 22 May 2025 · 1 repository · arXiv:2505.16363Syntology official: no sample here; runs from other or unrecorded repositories · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
SASSHA: Sharpness-aware Adaptive Second-order Optimization with Stable Hessian Approximation 25 Feb 2025 · 1 repository · arXiv:2502.18153Syntology official (archive's flag): 3 ran · 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
A Stronger Mixture of Low-Rank Experts for Fine-Tuning Foundation Models 20 Feb 2025 · 1 repository · arXiv:2502.15828Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
FRUGAL: Memory-Efficient Optimization by Reducing State Overhead for Scalable Training 12 Nov 2024 · 1 repository · arXiv:2411.07837Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples) · 2 pointer-only (licence)
-
Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs 17 Oct 2024 · 1 repository · arXiv:2410.13835Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 6 harvested samples) · 6 pointer-only (licence)
-
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training 14 Oct 2024 · 0 repositories · arXiv:2410.10373Syntology 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
SAMPa: Sharpness-aware Minimization Parallelized 14 Oct 2024 · 1 repository · arXiv:2410.10683Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 15 harvested samples) · 15 pointer-only (licence)
-
Zeroth-Order Fine-Tuning of LLMs in Random Subspaces 11 Oct 2024 · 1 repository · arXiv:2410.08989Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified (of 15 harvested samples) · 15 pointer-only (licence)
-
Adam Exploits ℓ_∞-geometry of Loss Landscape via Coordinate-wise Adaptivity 10 Oct 2024 · 1 repository · arXiv:2410.08198Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples)
-
PFDiff: Training-free Acceleration of Diffusion Models through the Gradient Guidance of Past and Future 16 Aug 2024 · 1 repository · arXiv:2408.08822Syntology official (archive's flag): 7 ran · 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 1 unverified (of 9 harvested samples) · 4 pointer-only (licence)
-
Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation 31 Jul 2024 · 1 repository · arXiv:2407.21633Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
Gradient descent with generalized Newton's method 3 Jul 2024 · 1 repository · arXiv:2407.02772Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements 13 Jun 2024 · 0 repositories · arXiv:2406.09405Syntology 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples)
-
Stochastic Polyak Step-sizes and Momentum: Convergence Guarantees and Practical Performance 6 Jun 2024 · 1 repository · arXiv:2406.04142Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample)
-
AdaFisher: Adaptive Second Order Optimization via Fisher Information 26 May 2024 · 1 repository · arXiv:2405.16397Syntology official (archive's flag): 7 ran · 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
Does SGD really happen in tiny subspaces? 25 May 2024 · 0 repositories · arXiv:2405.16002Syntology 14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 15 harvested samples) · 15 pointer-only (licence)
-
The Privacy Power of Correlated Noise in Decentralized Learning 2 May 2024 · 1 repository · arXiv:2405.01031Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Make Continual Learning Stronger via C-Flat 1 Apr 2024 · 1 repository · arXiv:2404.00986Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples) · 12 pointer-only (licence)
-
Differentially Private Next-Token Prediction of Large Language Models 22 Mar 2024 · 1 repository · arXiv:2403.15638Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
Do Deep Neural Network Solutions Form a Star Domain? 12 Mar 2024 · 1 repository · arXiv:2403.07968Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
Why Transformers Need Adam: A Hessian Perspective 26 Feb 2024 · 2 repositories · arXiv:2402.16788Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations 18 Feb 2024 · 1 repository · arXiv:2402.11427Syntology official (archive's flag): 7 ran · 7 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples) · 7 pointer-only (licence)
-
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark 18 Feb 2024 · 1 repository · arXiv:2402.11592Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
Can We Remove the Square-Root in Adaptive Gradient Methods? A Second-Order Perspective 5 Feb 2024 · 2 repositories · arXiv:2402.03496Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 2 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples) · 9 pointer-only (licence)
-
Vanishing Feature: Diagnosing Model Merging and Beyond 5 Feb 2024 · 2 repositories · arXiv:2402.05966Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models 4 Feb 2024 · 1 repository · arXiv:2402.02347Syntology official (archive's flag): 12 ran · 15 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified (of 21 harvested samples) · 3 pointer-only (licence)
-
HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy 26 Jan 2024 · 1 repository · arXiv:2401.15207Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
Momentum-SAM: Sharpness Aware Minimization without Computational Overhead 22 Jan 2024 · 1 repository · arXiv:2401.12033Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization 23 Dec 2023 · 1 repository · arXiv:2312.15184Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
TOD-Flow: Modeling the Structure of Task-Oriented Dialogues 7 Dec 2023 · 1 repository · arXiv:2312.04668Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples) · 10 pointer-only (licence)
-
AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix 4 Dec 2023 · 2 repositories · arXiv:2312.01658Syntology official (archive's flag): 1 ran · 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)
-
Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training 1 Dec 2023 · 1 repository · arXiv:2312.00359Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Critical Influence of Overparameterization on Sharpness-aware Minimization 29 Nov 2023 · 1 repository · arXiv:2311.17539Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 9 pointer-only (licence)
-
MAST: Model-Agnostic Sparsified Training 27 Nov 2023 · 1 repository · arXiv:2311.16086Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)
-
Learning From Free-Text Human Feedback -- Collect New Datasets Or Extend Existing Ones? 24 Oct 2023 · 1 repository · arXiv:2310.15758Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
Studying K-FAC Heuristics by Viewing Adam through a Second-Order Lens 23 Oct 2023 · 1 repository · arXiv:2310.14963Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified (of 16 harvested samples) · 16 pointer-only (licence)
-
A Quadratic Synchronization Rule for Distributed Deep Learning 22 Oct 2023 · 1 repository · arXiv:2310.14423Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)
-
Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL 6 Oct 2023 · 2 repositories · arXiv:2310.04411Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
Why Do We Need Weight Decay in Modern Deep Learning? 6 Oct 2023 · 1 repository · arXiv:2310.04415Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Chunking: Continual Learning is not just about Distribution Shift 3 Oct 2023 · 1 repository · arXiv:2310.02206Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)
-
On Memorization and Privacy Risks of Sharpness Aware Minimization 30 Sep 2023 · 0 repositories · arXiv:2310.00488Syntology 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples) · 1 pointer-only (licence)
-
On the different regimes of Stochastic Gradient Descent 19 Sep 2023 · 1 repository · arXiv:2309.10688Syntology official (archive's flag): 9 ran · 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified (of 17 harvested samples)
-
Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods 13 Aug 2023 · 1 repository · arXiv:2308.06703Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 13 harvested samples) · 13 pointer-only (licence)
-
Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers 2 Jul 2023 · 1 repository · arXiv:2307.00631Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)
-
Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach 14 Jun 2023 · 1 repository · arXiv:2306.08553Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 15 harvested samples)
-
Fast Diffusion Model 12 Jun 2023 · 1 repository · arXiv:2306.06991Syntology official (archive's flag): 14 ran · 14 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 3 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified (of 17 harvested samples) · 9 pointer-only (licence)
-
Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks 7 Jun 2023 · 1 repository · arXiv:2306.04251Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)
-
Decentralized SGD and Average-direction SAM are Asymptotically Equivalent 5 Jun 2023 · 1 repository · arXiv:2306.02913Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples) · 2 pointer-only (licence)
-
Towards Sustainable Learning: Coresets for Data-efficient Deep Learning 2 Jun 2023 · 1 repository · arXiv:2306.01244Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
The Impact of Positional Encoding on Length Generalization in Transformers 31 May 2023 · 2 repositories · arXiv:2305.19466Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples)
-
A Bayesian Approach To Analysing Training Data Attribution In Deep Learning 31 May 2023 · 1 repository · arXiv:2305.19765Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples)
-
A Rainbow in Deep Network Black Boxes 29 May 2023 · 1 repository · arXiv:2305.18512Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 14 harvested samples) · 1 pointer-only (licence)
-
Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms 28 May 2023 · 1 repository · arXiv:2305.18409Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 1 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples)
-
Rotational Equilibrium: How Weight Decay Balances Learning Across Neural Networks 26 May 2023 · 2 repositories · arXiv:2305.17212Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)
-
Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks 25 May 2023 · 1 repository · arXiv:2305.15912Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples)
-
Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks 25 May 2023 · 1 repository · arXiv:2305.16044Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
MoMo: Momentum Models for Adaptive Learning Rates 12 May 2023 · 1 repository · arXiv:2305.07583Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond 13 Mar 2023 · 1 repository · arXiv:2303.07160Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
Variance-reduced Clipping for Non-convex Optimization 2 Mar 2023 · 1 repository · arXiv:2303.00883Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)
-
Why (and When) does Local SGD Generalize Better than SGD? 2 Mar 2023 · 1 repository · arXiv:2303.01215Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)
-
Dropout Reduces Underfitting 2 Mar 2023 · 1 repository · arXiv:2303.01500Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
A Unified Framework for Soft Threshold Pruning 25 Feb 2023 · 1 repository · arXiv:2302.13019Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule 8 Feb 2023 · 1 repository · arXiv:2302.12022Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)
-
Coordinating Distributed Example Orders for Provably Accelerated Training 2 Feb 2023 · 1 repository · arXiv:2302.00845Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Learning-Rate-Free Learning by D-Adaptation 18 Jan 2023 · 1 repository · arXiv:2301.07733Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
ModelDiff: A Framework for Comparing Learning Algorithms 22 Nov 2022 · 1 repository · arXiv:2211.12491Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples)
-
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization 15 Nov 2022 · 1 repository · arXiv:2211.08583Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified (of 11 harvested samples) · 1 pointer-only (licence)
-
A Kernel-Based View of Language Model Fine-Tuning 11 Oct 2022 · 1 repository · arXiv:2210.05643Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer 29 Sep 2022 · 2 repositories · arXiv:2209.14937Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 4 harvested samples)
-
Optimization without Backpropagation 13 Sep 2022 · 1 repository · arXiv:2209.06302Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples)
-
CrAM: A Compression-Aware Minimizer 28 Jul 2022 · 1 repository · arXiv:2207.14200Syntology official (archive's flag): 1 ran · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified; the one sample that ran constructed an object rather than computing a result (of 2 harvested samples)
-
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels 13 Jul 2022 · 1 repository · arXiv:2207.06343Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta 22 Jun 2022 · 1 repository · arXiv:2206.11124Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
Low-Precision Stochastic Gradient Langevin Dynamics 20 Jun 2022 · 1 repository · arXiv:2206.09909Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Bayesian Estimation of Differential Privacy 10 Jun 2022 · 1 repository · arXiv:2206.05199Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
Integrating Random Effects in Deep Neural Networks 7 Jun 2022 · 1 repository · arXiv:2206.03314Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
A Theoretical Framework for Inference Learning 1 Jun 2022 · 1 repository · arXiv:2206.00164Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Re-parameterizing Your Optimizers rather than Architectures 30 May 2022 · 1 repository · arXiv:2205.15242Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples)
-
Trainable Weight Averaging: A General Approach for Subspace Training 26 May 2022 · 1 repository · arXiv:2205.13104Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 5 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 8 harvested samples)
-
FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction 26 May 2022 · 1 repository · arXiv:2205.13462Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 4 where Syntology's instrument failed) · 5 unverified (of 15 harvested samples) · 2 pointer-only (licence)
-
GraB: Finding Provably Better Data Permutations than Random Reshuffling 22 May 2022 · 3 repositories · arXiv:2205.10733Syntology official (archive's flag): 1 ran · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples) · 4 pointer-only (licence)
-
A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks 10 May 2022 · 1 repository · arXiv:2205.05040Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
What You See is What You Get: Principled Deep Learning via Distributional Generalization 7 Apr 2022 · 1 repository · arXiv:2204.03230Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples) · 1 pointer-only (licence)
-
Towards Efficient and Scalable Sharpness-Aware Minimization 5 Mar 2022 · 4 repositories · arXiv:2203.02714Syntology 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)
-
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions 2 Feb 2022 · 2 repositories · arXiv:2202.01331Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 7 harvested samples)
-
Training Structured Neural Networks Through Manifold Identification and Variance Reduction 5 Dec 2021 · 2 repositories · arXiv:2112.02612Syntology official (archive's flag): 4 ran · 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
Simple Stochastic and Online Gradient DescentAlgorithms for Pairwise Learning 23 Nov 2021 · 1 repository · arXiv:2111.12050Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Exponential Graph is Provably Efficient for Decentralized Deep Training 26 Oct 2021 · 2 repositories · arXiv:2110.13363Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)
-
Training Deep Neural Networks with Adaptive Momentum Inspired by the Quadratic Optimization 18 Oct 2021 · 1 repository · arXiv:2110.09057Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 3 violated, 3 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified (of 17 harvested samples) · 5 pointer-only (licence)
-
IGLU: Efficient GCN Training via Lazy Updates 28 Sep 2021 · 1 repository · arXiv:2109.13995Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 4 harvested samples)
-
Unrolling SGD: Understanding Factors Influencing Machine Unlearning 27 Sep 2021 · 1 repository · arXiv:2109.13398Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 10 harvested samples)
-
EDEN: Communication-Efficient and Robust Distributed Mean Estimation for Federated Learning 19 Aug 2021 · 1 repository · arXiv:2108.08842Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
M-FAC: Efficient Matrix-Free Approximations of Second-Order Information 7 Jul 2021 · 2 repositories · arXiv:2107.03356Syntology official (archive's flag): 4 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 4 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified (of 14 harvested samples)
-
Open-set Label Noise Can Improve Robustness Against Inherent Label Noise 21 Jun 2021 · 4 repositories · arXiv:2106.10891Syntology official (archive's flag): 9 ran · 17 ran (of which 5 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 1 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 12 unverified (of 29 harvested samples) · 29 pointer-only (licence)
-
Multirate Training of Neural Networks 20 Jun 2021 · 4 repositories · arXiv:2106.10771Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Large Scale Private Learning via Low-rank Reparametrization 17 Jun 2021 · 1 repository · arXiv:2106.09352Syntology official (archive's flag): 4 ran · 4 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 8 harvested samples) · 8 pointer-only (licence)
-
Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses 17 Jun 2021 · 2 repositories · arXiv:2106.09779Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
Robust Training in High Dimensions via Block Coordinate Geometric Median Descent 16 Jun 2021 · 2 repositories · arXiv:2106.08882Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 3 harvested samples)
-
Debiasing a First-order Heuristic for Approximate Bi-level Optimization 4 Jun 2021 · 1 repository · arXiv:2106.02487Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)