Methods › General › Stochastic Optimization › SGD › Papers, page 7

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)

Page 7 of 21: papers 601 to 700 of 2,021, newest first by the archive's date (ties by slug), in archive order.

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.

• The Monge Gap: A Regularizer to Learn All Transport Maps
  9 Feb 2023 · 0 repositories · arXiv:2302.04953
• DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
  8 Feb 2023 · 1 repository · arXiv:2302.12022
  Syntology 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)
• Easy Learning from Label Proportions
  6 Feb 2023 · 1 repository · arXiv:2302.03115
• On the Convergence of Federated Averaging with Cyclic Client Participation
  6 Feb 2023 · 0 repositories · arXiv:2302.03109
• Toward Large Kernel Models
  6 Feb 2023 · 1 repository · arXiv:2302.02605
• z-SignFedAvg: A Unified Stochastic Sign-based Compression for Federated Learning
  6 Feb 2023 · 0 repositories · arXiv:2302.02589
• Quantized Distributed Training of Large Models with Convergence Guarantees
  5 Feb 2023 · 0 repositories · arXiv:2302.02390
• Selecting the Best Optimizers for Deep Learning based Medical Image Segmentation
  5 Feb 2023 · 0 repositories · arXiv:2302.02289
• On Suppressing Range of Adaptive Stepsizes of Adam to Improve Generalisation Performance
  2 Feb 2023 · 0 repositories · arXiv:2302.01029
• Coordinating Distributed Example Orders for Provably Accelerated Training
  2 Feb 2023 · 1 repository · arXiv:2302.00845
  Syntology 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)
• STEP: Learning N:M Structured Sparsity Masks from Scratch with Precondition
  2 Feb 2023 · 1 repository · arXiv:2302.01172
• Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
  31 Jan 2023 · 0 repositories · arXiv:2301.13703
• Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation
  29 Jan 2023 · 1 repository · arXiv:2301.12568
• CyclicFL: A Cyclic Model Pre-Training Approach to Efficient Federated Learning
  28 Jan 2023 · 0 repositories · arXiv:2301.12193
• On the Lipschitz Constant of Deep Networks and Double Descent
  28 Jan 2023 · 1 repository · arXiv:2301.12309
• Algorithmic Stability of Heavy-Tailed SGD with General Loss Functions
  27 Jan 2023 · 0 repositories · arXiv:2301.11885
• Trainable Activations for Image Classification
  26 Jan 2023 · 1 repository
• Transfer Learning in Deep Learning Models for Building Load Forecasting: Case of Limited Data
  25 Jan 2023 · 2 repositories · arXiv:2301.10663
• Read the Signs: Towards Invariance to Gradient Descent's Hyperparameter Initialization
  24 Jan 2023 · 1 repository · arXiv:2301.10133
• Genetically Modified Wolf Optimization with Stochastic Gradient Descent for Optimising Deep Neural Networks
  21 Jan 2023 · 0 repositories · arXiv:2301.08950
• ScaDLES: Scalable Deep Learning over Streaming data at the Edge
  21 Jan 2023 · 1 repository · arXiv:2301.08897
• Learning-Rate-Free Learning by D-Adaptation
  18 Jan 2023 · 1 repository · arXiv:2301.07733
  Syntology 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)
• Convergence of First-Order Algorithms for Meta-Learning with Moreau Envelopes
  17 Jan 2023 · 0 repositories · arXiv:2301.06806
• Expected Gradients of Maxout Networks and Consequences to Parameter Initialization
  17 Jan 2023 · 1 repository · arXiv:2301.06956
• CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence
  14 Jan 2023 · 0 repositories · arXiv:2301.05872
• Toward Theoretical Guidance for Two Common Questions in Practical Cross-Validation based Hyperparameter Selection
  12 Jan 2023 · 0 repositories · arXiv:2301.05131
• Training trajectories, mini-batch losses and the curious role of the learning rate
  5 Jan 2023 · 0 repositories · arXiv:2301.02312
• On the Convergence of Stochastic Gradient Descent in Low-precision Number Formats
  4 Jan 2023 · 0 repositories · arXiv:2301.01651
• Temporal Difference Learning with Compressed Updates: Error-Feedback meets Reinforcement Learning
  3 Jan 2023 · 0 repositories · arXiv:2301.00944
• GPU accelerated matrix factorization of large scale data using block based approach
  2 Jan 2023 · 0 repositories · arXiv:2304.13724
• Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent
  30 Dec 2022 · 0 repositories · arXiv:2212.14883
• Visualizing Information Bottleneck through Variational Inference
  24 Dec 2022 · 0 repositories · arXiv:2212.12667
• When Do Curricula Work in Federated Learning?
  24 Dec 2022 · 1 repository · arXiv:2212.12712
• AnyTOD: A Programmable Task-Oriented Dialog System
  20 Dec 2022 · 0 repositories · arXiv:2212.09939
• Improving Levenberg-Marquardt Algorithm for Neural Networks
  17 Dec 2022 · 1 repository · arXiv:2212.08769
• Huber-energy measure quantization
  15 Dec 2022 · 0 repositories · arXiv:2212.08162
• Neuroevolution of Physics-Informed Neural Nets: Benchmark Problems and Comparative Results
  15 Dec 2022 · 0 repositories · arXiv:2212.07624
• Generalizing DP-SGD with Shuffling and Batch Clipping
  12 Dec 2022 · 0 repositories · arXiv:2212.05796
• Covariance Estimators for the ROOT-SGD Algorithm in Online Learning
  2 Dec 2022 · 0 repositories · arXiv:2212.01259
• Investigating certain choices of CNN configurations for brain lesion segmentation
  2 Dec 2022 · 0 repositories · arXiv:2212.01235
• Disentangling the Mechanisms Behind Implicit Regularization in SGD
  29 Nov 2022 · 1 repository · arXiv:2211.15853
• Stochastic Steffensen method
  28 Nov 2022 · 0 repositories · arXiv:2211.15310
• Learning Compact Features via In-Training Representation Alignment
  23 Nov 2022 · 0 repositories · arXiv:2211.13332
• Mutual Information Learned Regressor: an Information-theoretic Viewpoint of Training Regression Systems
  23 Nov 2022 · 0 repositories · arXiv:2211.12685
• ModelDiff: A Framework for Comparing Learning Algorithms
  22 Nov 2022 · 1 repository · arXiv:2211.12491
  Syntology 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)
• Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory
  19 Nov 2022 · 2 repositories · arXiv:2211.10586
  Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
• Two Facets of SDE Under an Information-Theoretic Lens: Generalization of SGD via Training Trajectories and via Terminal States
  19 Nov 2022 · 0 repositories · arXiv:2211.10691
• How to Fine-Tune Vision Models with SGD
  17 Nov 2022 · 0 repositories · arXiv:2211.09359
• SketchySGD: Reliable Stochastic Optimization via Randomized Curvature Estimates
  16 Nov 2022 · 1 repository · arXiv:2211.08597
• Empirical Study on Optimizer Selection for Out-of-Distribution Generalization
  15 Nov 2022 · 1 repository · arXiv:2211.08583
  Syntology 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)
• REPAIR: REnormalizing Permuted Activations for Interpolation Repair
  15 Nov 2022 · 1 repository · arXiv:2211.08403
• Selective Memory Recursive Least Squares: Recast Forgetting into Memory in RBF Neural Network Based Real-Time Learning
  15 Nov 2022 · 0 repositories · arXiv:2211.07909
• Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization
  14 Nov 2022 · 1 repository · arXiv:2211.07096
• Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning
  12 Nov 2022 · 1 repository · arXiv:2211.06530
• Variants of SGD for Lipschitz Continuous Loss Functions in Low-Precision Environments
  9 Nov 2022 · 0 repositories · arXiv:2211.04655
• AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks
  7 Nov 2022 · 0 repositories · arXiv:2211.03741
• Accelerating Parallel Stochastic Gradient Descent via Non-blocking Mini-batches
  2 Nov 2022 · 0 repositories · arXiv:2211.00889
• Large deviations rates for stochastic gradient descent with strongly convex functions
  2 Nov 2022 · 0 repositories · arXiv:2211.00969
• RCD-SGD: Resource-Constrained Distributed SGD in Heterogeneous Environment via Submodular Partitioning
  2 Nov 2022 · 0 repositories · arXiv:2211.00839
• Strong Lottery Ticket Hypothesis with ε--perturbation
  29 Oct 2022 · 0 repositories · arXiv:2210.16589
• Flatter, faster: scaling momentum for optimal speedup of SGD
  28 Oct 2022 · 0 repositories · arXiv:2210.16400
• Stochastic Mirror Descent in Average Ensemble Models
  27 Oct 2022 · 0 repositories · arXiv:2210.15323
• Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models
  25 Oct 2022 · 0 repositories · arXiv:2210.14199
• Adaptive Top-K in SGD for Communication-Efficient Distributed Learning
  24 Oct 2022 · 0 repositories · arXiv:2210.13532
• Decentralized Stochastic Bilevel Optimization with Improved per-Iteration Complexity
  23 Oct 2022 · 0 repositories · arXiv:2210.12839
• K-SAM: Sharpness-Aware Minimization at the Speed of SGD
  23 Oct 2022 · 0 repositories · arXiv:2210.12864
• When Expressivity Meets Trainability: Fewer than n Neurons Can Work
  21 Oct 2022 · 0 repositories · arXiv:2210.12001
• Global Convergence of SGD On Two Layer Neural Nets
  20 Oct 2022 · 0 repositories · arXiv:2210.11452
• Large-batch Optimization for Dense Visual Predictions
  20 Oct 2022 · 1 repository · arXiv:2210.11078
• Local SGD in Overparameterized Linear Regression
  20 Oct 2022 · 0 repositories · arXiv:2210.11562
• DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling
  18 Oct 2022 · 1 repository · arXiv:2210.09634
• Linear Scalarization for Byzantine-robust learning on non-IID data
  15 Oct 2022 · 0 repositories · arXiv:2210.08287
• Communication-Efficient Topologies for Decentralized Learning with O(1) Consensus Rate
  14 Oct 2022 · 1 repository · arXiv:2210.07881
• When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture
  14 Oct 2022 · 1 repository · arXiv:2210.07540
• From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent
  13 Oct 2022 · 0 repositories · arXiv:2210.06705
• Mean-field analysis for heavy ball methods: Dropout-stability, connectivity, and global convergence
  13 Oct 2022 · 0 repositories · arXiv:2210.06819
• Wasserstein Barycenter-based Model Fusion and Linear Mode Connectivity of Neural Networks
  13 Oct 2022 · 1 repository · arXiv:2210.06671
• AdaNorm: Adaptive Gradient Norm Correction based Optimizer for CNNs
  12 Oct 2022 · 1 repository · arXiv:2210.06364
• Improving information retention in large scale online continual learning
  12 Oct 2022 · 0 repositories · arXiv:2210.06401
• Rigorous dynamical mean field theory for stochastic gradient descent methods
  12 Oct 2022 · 1 repository · arXiv:2210.06591
• A Kernel-Based View of Language Model Fine-Tuning
  11 Oct 2022 · 1 repository · arXiv:2210.05643
  Syntology 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)
• SGD with Large Step Sizes Learns Sparse Features
  11 Oct 2022 · 1 repository · arXiv:2210.05337
• Fast Hierarchical Learning for Few-Shot Object Detection
  10 Oct 2022 · 0 repositories · arXiv:2210.05008
• Dissecting adaptive methods in GANs
  9 Oct 2022 · 0 repositories · arXiv:2210.04319
• STSyn: Speeding Up Local SGD with Straggler-Tolerant Synchronization
  6 Oct 2022 · 0 repositories · arXiv:2210.03521
• Scaling up Stochastic Gradient Descent for Non-convex Optimisation
  6 Oct 2022 · 0 repositories · arXiv:2210.02882
• Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
  6 Oct 2022 · 0 repositories · arXiv:2210.03044
• Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks
  4 Oct 2022 · 0 repositories · arXiv:2210.01360
• Distributed Non-Convex Optimization with One-Bit Compressors on Heterogeneous Data: Efficient and Resilient Algorithms
  3 Oct 2022 · 0 repositories · arXiv:2210.00665
• Downlink Compression Improves TopK Sparsification
  30 Sep 2022 · 0 repositories · arXiv:2209.15203
• Momentum Tracking: Momentum Acceleration for Decentralized Deep Learning on Heterogeneous Data
  30 Sep 2022 · 0 repositories · arXiv:2209.15505
• NAG-GS: Semi-Implicit, Accelerated and Robust Stochastic Optimizer
  29 Sep 2022 · 2 repositories · arXiv:2209.14937
  Syntology 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)
• Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
  29 Sep 2022 · 0 repositories · arXiv:2209.14863
• Statistical Learning and Inverse Problems: A Stochastic Gradient Approach
  29 Sep 2022 · 0 repositories · arXiv:2209.14967
• On the Stability Analysis of Open Federated Learning Systems
  25 Sep 2022 · 0 repositories · arXiv:2209.12307
• Error Mitigation-Aided Optimization of Parameterized Quantum Circuits: Convergence Analysis
  23 Sep 2022 · 0 repositories · arXiv:2209.11514
• Robust Collaborative Learning with Linear Gradient Overhead
  22 Sep 2022 · 1 repository · arXiv:2209.10931
  Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
• Generalization Bounds for Stochastic Gradient Descent via Localized ε-Covers
  19 Sep 2022 · 0 repositories · arXiv:2209.08951
• Stability and Generalization Analysis of Gradient Methods for Shallow Neural Networks
  19 Sep 2022 · 0 repositories · arXiv:2209.09298
• Empirical Analysis on Top-k Gradient Sparsification for Distributed Deep Learning in a Supercomputing Environment
  18 Sep 2022 · 0 repositories · arXiv:2209.08497