Methods › General › Stochastic Optimization › SGD › Papers, page 18

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 18 of 21: papers 1,701 to 1,800 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.

• FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters
  4 Jan 2019 · 0 repositories · arXiv:1901.01007
• SGD Converges to Global Minimum in Deep Learning via Star-convex Path
  2 Jan 2019 · 0 repositories · arXiv:1901.00451
• A continuous-time analysis of distributed stochastic gradient
  28 Dec 2018 · 0 repositories · arXiv:1812.10995
• Overparameterized Nonlinear Learning: Gradient Descent Takes the Shortest Path?
  25 Dec 2018 · 0 repositories · arXiv:1812.10004
• Stochastic Doubly Robust Gradient
  21 Dec 2018 · 0 repositories · arXiv:1812.08997
• Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL
  18 Dec 2018 · 0 repositories · arXiv:1812.07671
• Provable limitations of deep learning
  16 Dec 2018 · 0 repositories · arXiv:1812.06369
• Stagewise Training Accelerates Convergence of Testing Error Over SGD
  10 Dec 2018 · 0 repositories · arXiv:1812.03934
• What is the Effect of Importance Weighting in Deep Learning?
  8 Dec 2018 · 1 repository · arXiv:1812.03372
• Elastic Gossip: Distributing Neural Network Training Using Gossip-like Protocols
  6 Dec 2018 · 1 repository · arXiv:1812.02407
• Towards Theoretical Understanding of Large Batch Training in Stochastic Gradient Descent
  3 Dec 2018 · 0 repositories · arXiv:1812.00542
• A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication
  1 Dec 2018 · 0 repositories
• Exact natural gradient in deep linear networks and its application to the nonlinear case
  1 Dec 2018 · 0 repositories
• How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective
  1 Dec 2018 · 1 repository
• On the Local Hessian in Back-propagation
  1 Dec 2018 · 0 repositories
• Stochastic Composite Mirror Descent: Optimal Bounds with High Probabilities
  1 Dec 2018 · 0 repositories
• Stochastic Primal-Dual Method for Empirical Risk Minimization with O(1) Per-Iteration Complexity
  1 Dec 2018 · 0 repositories
• Training Deep Models Faster with Robust, Approximate Importance Sampling
  1 Dec 2018 · 0 repositories
• Variance-Reduced Stochastic Gradient Descent on Streaming Data
  1 Dec 2018 · 0 repositories
• ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
  28 Nov 2018 · 10 repositories · arXiv:1811.11431
  Syntology community repositories only · 4 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; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
• Stochastic Gradient Push for Distributed Deep Learning
  27 Nov 2018 · 3 repositories · arXiv:1811.10792
  Syntology 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 15 harvested samples) · 2 pointer-only (licence)
• The promises and pitfalls of Stochastic Gradient Langevin Dynamics
  25 Nov 2018 · 0 repositories · arXiv:1811.10072
• Hydra: A Peer to Peer Distributed Training & Data Collection Framework
  24 Nov 2018 · 1 repository · arXiv:1811.09878
• HyperAdam: A Learnable Task-Adaptive Adam for Network Training
  22 Nov 2018 · 2 repositories · arXiv:1811.08996
• Deep Frank-Wolfe For Neural Network Optimization
  19 Nov 2018 · 1 repository · arXiv:1811.07591
  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)
• Minimum weight norm models do not always generalize well for over-parameterized problems
  16 Nov 2018 · 0 repositories · arXiv:1811.07055
• Learning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
  12 Nov 2018 · 0 repositories · arXiv:1811.04918
• New Convergence Aspects of Stochastic Gradient Algorithms
  10 Nov 2018 · 0 repositories · arXiv:1811.12403
• A Convergence Theory for Deep Learning via Over-Parameterization
  9 Nov 2018 · 0 repositories · arXiv:1811.03962
• On exponential convergence of SGD in non-convex over-parametrized learning
  6 Nov 2018 · 0 repositories · arXiv:1811.02564
• Deep Reinforcement Learning via L-BFGS Optimization
  6 Nov 2018 · 0 repositories · arXiv:1811.02693
• Stochastic Modified Equations and Dynamics of Stochastic Gradient Algorithms I: Mathematical Foundations
  5 Nov 2018 · 0 repositories · arXiv:1811.01558
• Stochastic Primal-Dual Method for Empirical Risk Minimization with 𝒪(1) Per-Iteration Complexity
  3 Nov 2018 · 0 repositories · arXiv:1811.01182
• Implicit Regularization of Stochastic Gradient Descent in Natural Language Processing: Observations and Implications
  1 Nov 2018 · 0 repositories · arXiv:1811.00659
• Accelerating SGD with momentum for over-parameterized learning
  31 Oct 2018 · 1 repository · arXiv:1810.13395
• Kalman Gradient Descent: Adaptive Variance Reduction in Stochastic Optimization
  29 Oct 2018 · 1 repository · arXiv:1810.12273
• On the Convergence Rate of Training Recurrent Neural Networks
  29 Oct 2018 · 0 repositories · arXiv:1810.12065
• Finding Mixed Nash Equilibria of Generative Adversarial Networks
  23 Oct 2018 · 0 repositories · arXiv:1811.02002
• ensmallen: a flexible C++ library for efficient function optimization
  22 Oct 2018 · 1 repository · arXiv:1810.09361
• Optimality of the final model found via Stochastic Gradient Descent
  22 Oct 2018 · 0 repositories · arXiv:1810.09418
• Adaptive Communication Strategies to Achieve the Best Error-Runtime Trade-off in Local-Update SGD
  19 Oct 2018 · 0 repositories · arXiv:1810.08313
• Exchangeability and Kernel Invariance in Trained MLPs
  19 Oct 2018 · 0 repositories · arXiv:1810.08351
• Small ReLU networks are powerful memorizers: a tight analysis of memorization capacity
  17 Oct 2018 · 0 repositories · arXiv:1810.07770
• Evolutionary Stochastic Gradient Descent for Optimization of Deep Neural Networks
  16 Oct 2018 · 1 repository · arXiv:1810.06773
• Fast and Faster Convergence of SGD for Over-Parameterized Models and an Accelerated Perceptron
  16 Oct 2018 · 0 repositories · arXiv:1810.07288
• Quasi-hyperbolic momentum and Adam for deep learning
  16 Oct 2018 · 2 repositories · arXiv:1810.06801
  Syntology 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) · 7 pointer-only (licence)
• Training Deep Neural Network in Limited Precision
  12 Oct 2018 · 0 repositories · arXiv:1810.05486
• Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes
  11 Oct 2018 · 0 repositories · arXiv:1810.05148
• signSGD with Majority Vote is Communication Efficient And Fault Tolerant
  11 Oct 2018 · 4 repositories · arXiv:1810.05291
  Syntology 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)
• Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD
  10 Oct 2018 · 0 repositories · arXiv:1810.04723
• Anytime Stochastic Gradient Descent: A Time to Hear from all the Workers
  6 Oct 2018 · 0 repositories · arXiv:1810.02976
• Continuous-time Models for Stochastic Optimization Algorithms
  5 Oct 2018 · 1 repository · arXiv:1810.02565
• Large batch size training of neural networks with adversarial training and second-order information
  2 Oct 2018 · 1 repository · arXiv:1810.01021
• Directional Analysis of Stochastic Gradient Descent via von Mises-Fisher Distributions in Deep learning
  29 Sep 2018 · 0 repositories · arXiv:1810.00150
• The Convergence of Sparsified Gradient Methods
  27 Sep 2018 · 0 repositories · arXiv:1809.10505
• Preconditioner on Matrix Lie Group for SGD
  26 Sep 2018 · 2 repositories · arXiv:1809.10232
  Syntology official (archive's flag): 5 ran · 5 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; 4 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 6 pointer-only (licence)
• Sparsified SGD with Memory
  20 Sep 2018 · 1 repository · arXiv:1809.07599
  Syntology 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) · 0 unverified (of 3 harvested samples)
• Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent
  18 Sep 2018 · 0 repositories · arXiv:1809.06958
• Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference
  11 Sep 2018 · 0 repositories · arXiv:1809.04191
• Learning Rate Adaptation for Federated and Differentially Private Learning
  11 Sep 2018 · 1 repository · arXiv:1809.03832
  Syntology 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)
• Privacy-Preserving Deep Learning via Weight Transmission
  10 Sep 2018 · 0 repositories · arXiv:1809.03272
• Stochastic Gradient Descent Learns State Equations with Nonlinear Activations
  9 Sep 2018 · 0 repositories · arXiv:1809.03019
• Decentralized Differentially Private Without-Replacement Stochastic Gradient Descent
  8 Sep 2018 · 0 repositories · arXiv:1809.02727
• Online ICA: Understanding Global Dynamics of Nonconvex Optimization via Diffusion Processes
  29 Aug 2018 · 0 repositories · arXiv:1808.09642
• Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms
  22 Aug 2018 · 0 repositories · arXiv:1808.07576
• Don't Use Large Mini-Batches, Use Local SGD
  22 Aug 2018 · 2 repositories · arXiv:1808.07217
• Universal Stagewise Learning for Non-Convex Problems with Convergence on Averaged Solutions
  20 Aug 2018 · 0 repositories · arXiv:1808.06296
• Ensemble Kalman Inversion: A Derivative-Free Technique For Machine Learning Tasks
  10 Aug 2018 · 0 repositories · arXiv:1808.03620
• A Unified Analysis of AdaGrad with Weighted Aggregation and Momentum Acceleration
  10 Aug 2018 · 0 repositories · arXiv:1808.03408
• Learning Overparameterized Neural Networks via Stochastic Gradient Descent on Structured Data
  3 Aug 2018 · 0 repositories · arXiv:1808.01204
• Stochastic Gradient Descent with Biased but Consistent Gradient Estimators
  31 Jul 2018 · 1 repository · arXiv:1807.11880
• A Surprising Linear Relationship Predicts Test Performance in Deep Networks
  25 Jul 2018 · 3 repositories · arXiv:1807.09659
• signProx: One-Bit Proximal Algorithm for Nonconvex Stochastic Optimization
  20 Jul 2018 · 0 repositories · arXiv:1807.08023
• Bayesian filtering unifies adaptive and non-adaptive neural network optimization methods
  19 Jul 2018 · 1 repository · arXiv:1807.07540
• Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning
  17 Jul 2018 · 0 repositories · arXiv:1807.06629
• Evolving Differentiable Gene Regulatory Networks
  16 Jul 2018 · 0 repositories · arXiv:1807.05948
• On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
  13 Jul 2018 · 1 repository · arXiv:1807.05031
• Maximizing Invariant Data Perturbation with Stochastic Optimization
  12 Jul 2018 · 1 repository · arXiv:1807.05077
• Metalearning with Hebbian Fast Weights
  12 Jul 2018 · 0 repositories · arXiv:1807.05076
• Quasi-Monte Carlo Variational Inference
  4 Jul 2018 · 0 repositories · arXiv:1807.01604
• Batch IS NOT Heavy: Learning Word Representations From All Samples
  1 Jul 2018 · 0 repositories
• Random Shuffling Beats SGD after Finite Epochs
  26 Jun 2018 · 0 repositories · arXiv:1806.10077
• Faster SGD training by minibatch persistency
  19 Jun 2018 · 0 repositories · arXiv:1806.07353
• Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
  18 Jun 2018 · 2 repositories · arXiv:1806.06763
• Using Mode Connectivity for Loss Landscape Analysis
  18 Jun 2018 · 0 repositories · arXiv:1806.06977
• There Are Many Consistent Explanations of Unlabeled Data: Why You Should Average
  14 Jun 2018 · 2 repositories · arXiv:1806.05594
• Boosted Training of Convolutional Neural Networks for Multi-Class Segmentation
  13 Jun 2018 · 0 repositories · arXiv:1806.05974
• When Will Gradient Methods Converge to Max-margin Classifier under ReLU Models?
  12 Jun 2018 · 1 repository · arXiv:1806.04339
• Full deep neural network training on a pruned weight budget
  11 Jun 2018 · 1 repository · arXiv:1806.06949
• The Effect of Network Width on the Performance of Large-batch Training
  11 Jun 2018 · 0 repositories · arXiv:1806.03791
• Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
  8 Jun 2018 · 0 repositories · arXiv:1806.02927
• Probabilistic Deep Learning using Random Sum-Product Networks
  5 Jun 2018 · 0 repositories · arXiv:1806.01910
• Stochastic Gradient Descent on Separable Data: Exact Convergence with a Fixed Learning Rate
  5 Jun 2018 · 0 repositories · arXiv:1806.01796
• Backdrop: Stochastic Backpropagation
  4 Jun 2018 · 1 repository · arXiv:1806.01337
• Geometry Aware Constrained Optimization Techniques for Deep Learning
  1 Jun 2018 · 0 repositories
• On Consensus-Optimality Trade-offs in Collaborative Deep Learning
  30 May 2018 · 0 repositories · arXiv:1805.12120
• How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery?
  25 May 2018 · 0 repositories · arXiv:1805.10251
• Statistical Optimality of Stochastic Gradient Descent on Hard Learning Problems through Multiple Passes
  25 May 2018 · 0 repositories · arXiv:1805.10074
• Zeno: Distributed Stochastic Gradient Descent with Suspicion-based Fault-tolerance
  25 May 2018 · 1 repository · arXiv:1805.10032
• Local SGD Converges Fast and Communicates Little
  24 May 2018 · 2 repositories · arXiv:1805.09767