Methods › General › Stochastic Optimization › SGD › Papers, page 5

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 5 of 21: papers 401 to 500 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.

• A Quadratic Synchronization Rule for Distributed Deep Learning
  22 Oct 2023 · 1 repository · arXiv:2310.14423
  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) · 1 unverified (of 6 harvested samples)
• Towards Hyperparameter-Agnostic DNN Training via Dynamical System Insights
  21 Oct 2023 · 0 repositories · arXiv:2310.13901
• Demystifying the Myths and Legends of Nonconvex Convergence of SGD
  19 Oct 2023 · 0 repositories · arXiv:2310.12969
• LASER: Linear Compression in Wireless Distributed Optimization
  19 Oct 2023 · 0 repositories · arXiv:2310.13033
• Jorge: Approximate Preconditioning for GPU-efficient Second-order Optimization
  18 Oct 2023 · 0 repositories · arXiv:2310.12298
• Learning to Generate Parameters of ConvNets for Unseen Image Data
  18 Oct 2023 · 1 repository · arXiv:2310.11862
• An Automatic Learning Rate Schedule Algorithm for Achieving Faster Convergence and Steeper Descent
  17 Oct 2023 · 0 repositories · arXiv:2310.11291
• Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
  17 Oct 2023 · 0 repositories · arXiv:2310.11428
• Resampling Stochastic Gradient Descent Cheaply for Efficient Uncertainty Quantification
  17 Oct 2023 · 0 repositories · arXiv:2310.11065
• Contextual Data Augmentation for Task-Oriented Dialog Systems
  16 Oct 2023 · 0 repositories · arXiv:2310.10380
• Adam-family Methods with Decoupled Weight Decay in Deep Learning
  13 Oct 2023 · 0 repositories · arXiv:2310.08858
• Asynchronous Federated Learning with Incentive Mechanism Based on Contract Theory
  10 Oct 2023 · 0 repositories · arXiv:2310.06448
• Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition
  10 Oct 2023 · 0 repositories · arXiv:2310.06301
• Augmenting Vision-Based Human Pose Estimation with Rotation Matrix
  9 Oct 2023 · 0 repositories · arXiv:2310.06068
• Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL
  6 Oct 2023 · 2 repositories · arXiv:2310.04411
  Syntology 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:2310.04415
  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) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
• Spectral alignment of stochastic gradient descent for high-dimensional classification tasks
  4 Oct 2023 · 0 repositories · arXiv:2310.03010
• Hoeffding's Inequality for Markov Chains under Generalized Concentrability Condition
  4 Oct 2023 · 0 repositories · arXiv:2310.02941
• A simple connection from loss flatness to compressed neural representations
  3 Oct 2023 · 0 repositories · arXiv:2310.01770
• Chunking: Continual Learning is not just about Distribution Shift
  3 Oct 2023 · 1 repository · arXiv:2310.02206
  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) · 0 unverified (of 5 harvested samples) · 5 pointer-only (licence)
• On the Parallel Complexity of Multilevel Monte Carlo in Stochastic Gradient Descent
  3 Oct 2023 · 0 repositories · arXiv:2310.02402
• Symmetric Single Index Learning
  3 Oct 2023 · 0 repositories · arXiv:2310.02117
• Batch-less stochastic gradient descent for compressive learning of deep regularization for image denoising
  2 Oct 2023 · 0 repositories · arXiv:2310.03085
• Improving Dialogue Management: Quality Datasets vs Models
  2 Oct 2023 · 1 repository · arXiv:2310.01339
• Stability and Generalization for Minibatch SGD and Local SGD
  2 Oct 2023 · 0 repositories · arXiv:2310.01139
• A Theoretical Analysis of Noise Geometry in Stochastic Gradient Descent
  1 Oct 2023 · 0 repositories · arXiv:2310.00692
• On Memorization and Privacy Risks of Sharpness Aware Minimization
  30 Sep 2023 · 0 repositories · arXiv:2310.00488
  Syntology 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)
• Robust Stochastic Optimization via Gradient Quantile Clipping
  29 Sep 2023 · 0 repositories · arXiv:2309.17316
• AutoEncoding Tree for City Generation and Applications
  27 Sep 2023 · 0 repositories · arXiv:2309.15941
• Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs
  26 Sep 2023 · 0 repositories · arXiv:2309.15096
• SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
  26 Sep 2023 · 0 repositories · arXiv:2309.15111
• Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns
  23 Sep 2023 · 0 repositories · arXiv:2309.13448
• A Guide Through the Zoo of Biased SGD
  21 Sep 2023 · 0 repositories
• Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent
  21 Sep 2023 · 1 repository
• Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection
  21 Sep 2023 · 0 repositories
• Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger
  21 Sep 2023 · 1 repository
• BayesTune: Bayesian Sparse Deep Model Fine-tuning
  21 Sep 2023 · 1 repository
• Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence
  21 Sep 2023 · 1 repository
• Differentially Private Image Classification by Learning Priors from Random Processes
  21 Sep 2023 · 1 repository
• Easy Bayesian Transfer Learning with Informative Priors
  21 Sep 2023 · 0 repositories
• Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds
  21 Sep 2023 · 1 repository
• Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization
  21 Sep 2023 · 0 repositories
• Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network
  21 Sep 2023 · 0 repositories
• KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training
  21 Sep 2023 · 1 repository
• Mean-field Langevin dynamics: Time-space discretization, stochastic gradient, and variance reduction
  21 Sep 2023 · 0 repositories
• (S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability
  21 Sep 2023 · 0 repositories
• Preconditioned Federated Learning
  20 Sep 2023 · 0 repositories · arXiv:2309.11378
• On the different regimes of Stochastic Gradient Descent
  19 Sep 2023 · 1 repository · arXiv:2309.10688
  Syntology 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)
• Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets
  17 Sep 2023 · 0 repositories · arXiv:2309.09258
• Stochastic Gradient Descent-like relaxation is equivalent to Metropolis dynamics in discrete optimization and inference problems
  11 Sep 2023 · 1 repository · arXiv:2309.05337
• Stochastic Gradient Descent outperforms Gradient Descent in recovering a high-dimensional signal in a glassy energy landscape
  9 Sep 2023 · 0 repositories · arXiv:2309.04788
• Convergence Analysis of Decentralized ASGD
  7 Sep 2023 · 0 repositories · arXiv:2309.03754
• AdaPlus: Integrating Nesterov Momentum and Precise Stepsize Adjustment on AdamW Basis
  5 Sep 2023 · 1 repository · arXiv:2309.01966
• Asymmetric Momentum: A Rethinking of Gradient Descent
  5 Sep 2023 · 1 repository · arXiv:2309.02130
• Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD
  4 Sep 2023 · 0 repositories · arXiv:2309.01640
• ABS-SGD: A Delayed Synchronous Stochastic Gradient Descent Algorithm with Adaptive Batch Size for Heterogeneous GPU Clusters
  29 Aug 2023 · 0 repositories · arXiv:2308.15164
• Bias-Aware Minimisation: Understanding and Mitigating Estimator Bias in Private SGD
  23 Aug 2023 · 0 repositories · arXiv:2308.12018
• Extended Linear Regression: A Kalman Filter Approach for Minimizing Loss via Area Under the Curve
  23 Aug 2023 · 0 repositories · arXiv:2308.12280
• When MiniBatch SGD Meets SplitFed Learning:Convergence Analysis and Performance Evaluation
  23 Aug 2023 · 0 repositories · arXiv:2308.11953
• Towards Understanding the Generalizability of Delayed Stochastic Gradient Descent
  18 Aug 2023 · 0 repositories · arXiv:2308.09430
• Hitting the High-Dimensional Notes: An ODE for SGD learning dynamics on GLMs and multi-index models
  17 Aug 2023 · 0 repositories · arXiv:2308.08977
• Max-affine regression via first-order methods
  15 Aug 2023 · 0 repositories · arXiv:2308.08070
• Law of Balance and Stationary Distribution of Stochastic Gradient Descent
  13 Aug 2023 · 0 repositories · arXiv:2308.06671
• Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods
  13 Aug 2023 · 1 repository · arXiv:2308.06703
  Syntology 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)
• Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction
  11 Aug 2023 · 0 repositories · arXiv:2308.06058
• Real-Time Progressive Learning: Accumulate Knowledge from Control with Neural-Network-Based Selective Memory
  8 Aug 2023 · 0 repositories · arXiv:2308.04223
• The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning
  6 Aug 2023 · 0 repositories · arXiv:2308.03215
• Eva: A General Vectorized Approximation Framework for Second-order Optimization
  4 Aug 2023 · 0 repositories · arXiv:2308.02123
• Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation
  3 Aug 2023 · 1 repository · arXiv:2308.01547
• Online covariance estimation for stochastic gradient descent under Markovian sampling
  3 Aug 2023 · 0 repositories · arXiv:2308.01481
• Toward Quantum Machine Translation of Syntactically Distinct Languages
  31 Jul 2023 · 0 repositories · arXiv:2307.16576
• The Marginal Value of Momentum for Small Learning Rate SGD
  27 Jul 2023 · 0 repositories · arXiv:2307.15196
• Function Value Learning: Adaptive Learning Rates Based on the Polyak Stepsize and Function Splitting in ERM
  26 Jul 2023 · 0 repositories · arXiv:2307.14528
• Relationship between Batch Size and Number of Steps Needed for Nonconvex Optimization of Stochastic Gradient Descent using Armijo Line Search
  25 Jul 2023 · 0 repositories · arXiv:2307.13831
• Convergence of SGD for Training Neural Networks with Sliced Wasserstein Losses
  21 Jul 2023 · 0 repositories · arXiv:2307.11714
• Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization
  19 Jul 2023 · 0 repositories · arXiv:2307.10053
• Weighted Averaged Stochastic Gradient Descent: Asymptotic Normality and Optimality
  13 Jul 2023 · 0 repositories · arXiv:2307.06915
• Mini-Batch Optimization of Contrastive Loss
  12 Jul 2023 · 1 repository · arXiv:2307.05906
• FedYolo: Augmenting Federated Learning with Pretrained Transformers
  10 Jul 2023 · 0 repositories · arXiv:2307.04905
• Bidirectional Looking with A Novel Double Exponential Moving Average to Adaptive and Non-adaptive Momentum Optimizers
  2 Jul 2023 · 1 repository · arXiv:2307.00631
  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) · 1 unverified (of 6 harvested samples)
• Federated Ensemble YOLOv5 -- A Better Generalized Object Detection Algorithm
  30 Jun 2023 · 0 repositories · arXiv:2306.17829
• Nonconvex Stochastic Bregman Proximal Gradient Method with Application to Deep Learning
  26 Jun 2023 · 0 repositories · arXiv:2306.14522
• Empirical Risk Minimization with Shuffled SGD: A Primal-Dual Perspective and Improved Bounds
  21 Jun 2023 · 0 repositories · arXiv:2306.12498
• InRank: Incremental Low-Rank Learning
  20 Jun 2023 · 1 repository · arXiv:2306.11250
• Adaptive Federated Learning with Auto-Tuned Clients
  19 Jun 2023 · 1 repository · arXiv:2306.11201
• Adaptive Strategies in Non-convex Optimization
  17 Jun 2023 · 0 repositories · arXiv:2306.10278
• Gradient is All You Need?
  16 Jun 2023 · 2 repositories · arXiv:2306.09778
• Evaluation and Optimization of Gradient Compression for Distributed Deep Learning
  15 Jun 2023 · 1 repository · arXiv:2306.08881
• Span-Selective Linear Attention Transformers for Effective and Robust Schema-Guided Dialogue State Tracking
  15 Jun 2023 · 0 repositories · arXiv:2306.09340
• Stochastic Re-weighted Gradient Descent via Distributionally Robust Optimization
  15 Jun 2023 · 0 repositories · arXiv:2306.09222
• When and Why Momentum Accelerates SGD:An Empirical Study
  15 Jun 2023 · 0 repositories · arXiv:2306.09000
• Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
  14 Jun 2023 · 0 repositories · arXiv:2306.08590
• Kalman Filter for Online Classification of Non-Stationary Data
  14 Jun 2023 · 0 repositories · arXiv:2306.08448
• Noise Stability Optimization for Finding Flat Minima: A Hessian-based Regularization Approach
  14 Jun 2023 · 1 repository · arXiv:2306.08553
  Syntology 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)
• Exact Mean Square Linear Stability Analysis for SGD
  13 Jun 2023 · 0 repositories · arXiv:2306.07850
• Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD
  13 Jun 2023 · 1 repository · arXiv:2306.08125
• Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction
  12 Jun 2023 · 0 repositories · arXiv:2306.07221
• Fast Diffusion Model
  12 Jun 2023 · 1 repository · arXiv:2306.06991
  Syntology 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)
• Gaussian Membership Inference Privacy
  12 Jun 2023 · 1 repository · arXiv:2306.07273
• Correlated Noise in Epoch-Based Stochastic Gradient Descent: Implications for Weight Variances
  8 Jun 2023 · 0 repositories · arXiv:2306.05300