Methods › General › Stochastic Optimization › SGD › Papers, page 20

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 20 of 21: papers 1,901 to 2,000 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.

• YellowFin and the Art of Momentum Tuning
  12 Jun 2017 · 2 repositories · arXiv:1706.03471
  Syntology 0 ran · 1 unverified (of 1 harvested sample)
• Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
  8 Jun 2017 · 73 repositories · arXiv:1706.02677
  Syntology 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) · 4 unverified (of 7 harvested samples) · 7 pointer-only (licence)
• CATERPILLAR: Coarse Grain Reconfigurable Architecture for Accelerating the Training of Deep Neural Networks
  1 Jun 2017 · 0 repositories · arXiv:1706.00517
• Reinforcement Learning for Learning Rate Control
  31 May 2017 · 0 repositories · arXiv:1705.11159
• Online to Offline Conversions, Universality and Adaptive Minibatch Sizes
  30 May 2017 · 0 repositories · arXiv:1705.10499
• Convergence Analysis of Two-layer Neural Networks with ReLU Activation
  28 May 2017 · 0 repositories · arXiv:1705.09886
• The Marginal Value of Adaptive Gradient Methods in Machine Learning
  23 May 2017 · 3 repositories · arXiv:1705.08292
• Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients
  22 May 2017 · 2 repositories · arXiv:1705.07774
• On the diffusion approximation of nonconvex stochastic gradient descent
  22 May 2017 · 0 repositories · arXiv:1705.07562
• Parallel Stochastic Gradient Descent with Sound Combiners
  22 May 2017 · 0 repositories · arXiv:1705.08030
• Statistical inference using SGD
  21 May 2017 · 0 repositories · arXiv:1705.07477
• Determinantal Point Processes for Mini-Batch Diversification
  1 May 2017 · 0 repositories · arXiv:1705.00607
• Parseval Networks: Improving Robustness to Adversarial Examples
  28 Apr 2017 · 1 repository · arXiv:1704.08847
• Linear Convergence of Accelerated Stochastic Gradient Descent for Nonconvex Nonsmooth Optimization
  26 Apr 2017 · 0 repositories · arXiv:1704.07953
• Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples
  24 Apr 2017 · 1 repository · arXiv:1704.07433
• Stochastic Gradient Descent as Approximate Bayesian Inference
  13 Apr 2017 · 1 repository · arXiv:1704.04289
• Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
  31 Mar 2017 · 3 repositories · arXiv:1703.11008
  Syntology 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) · 2 pointer-only (licence)
• Theory II: Landscape of the Empirical Risk in Deep Learning
  28 Mar 2017 · 0 repositories · arXiv:1703.09833
• Empirical Evaluation of Parallel Training Algorithms on Acoustic Modeling
  17 Mar 2017 · 0 repositories · arXiv:1703.05880
• Separation of time scales and direct computation of weights in deep neural networks
  14 Mar 2017 · 0 repositories · arXiv:1703.04757
• Data-Dependent Stability of Stochastic Gradient Descent
  5 Mar 2017 · 0 repositories · arXiv:1703.01678
• A Robust Adaptive Stochastic Gradient Method for Deep Learning
  2 Mar 2017 · 1 repository · arXiv:1703.00788
• SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient
  1 Mar 2017 · 0 repositories · arXiv:1703.00102
• Learning What Data to Learn
  28 Feb 2017 · 0 repositories · arXiv:1702.08635
• McKernel: A Library for Approximate Kernel Expansions in Log-linear Time
  27 Feb 2017 · 1 repository · arXiv:1702.08159
• SGD Learns the Conjugate Kernel Class of the Network
  27 Feb 2017 · 0 repositories · arXiv:1702.08503
• On SGD's Failure in Practice: Characterizing and Overcoming Stalling
  1 Feb 2017 · 0 repositories · arXiv:1702.00317
• Reinforced stochastic gradient descent for deep neural network learning
  27 Jan 2017 · 0 repositories · arXiv:1701.07974
• Optimization on Product Submanifolds of Convolution Kernels
  22 Jan 2017 · 0 repositories · arXiv:1701.06123
• Efficient Distributed Semi-Supervised Learning using Stochastic Regularization over Affinity Graphs
  15 Dec 2016 · 0 repositories · arXiv:1612.04898
• Tuning the Scheduling of Distributed Stochastic Gradient Descent with Bayesian Optimization
  1 Dec 2016 · 0 repositories · arXiv:1612.00383
• Spatial contrasting for deep unsupervised learning
  21 Nov 2016 · 0 repositories · arXiv:1611.06996
• How to scale distributed deep learning?
  14 Nov 2016 · 0 repositories · arXiv:1611.04581
• Entropy-SGD: Biasing Gradient Descent Into Wide Valleys
  6 Nov 2016 · 2 repositories · arXiv:1611.01838
• Quasi-Recurrent Neural Networks
  5 Nov 2016 · 7 repositories · arXiv:1611.01576
  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)
• Statistical Inference for Model Parameters in Stochastic Gradient Descent
  27 Oct 2016 · 0 repositories · arXiv:1610.08637
• Optimization on Submanifolds of Convolution Kernels in CNNs
  22 Oct 2016 · 0 repositories · arXiv:1610.07008
• An Efficient Minibatch Acceptance Test for Metropolis-Hastings
  19 Oct 2016 · 0 repositories · arXiv:1610.06848
• CuMF_SGD: Fast and Scalable Matrix Factorization
  19 Oct 2016 · 2 repositories · arXiv:1610.05838
• Big Batch SGD: Automated Inference using Adaptive Batch Sizes
  18 Oct 2016 · 0 repositories · arXiv:1610.05792
• Parallelizing Stochastic Gradient Descent for Least Squares Regression: mini-batching, averaging, and model misspecification
  12 Oct 2016 · 4 repositories · arXiv:1610.03774
• QSGD: Communication-Efficient SGD via Gradient Quantization and Encoding
  7 Oct 2016 · 2 repositories · arXiv:1610.02132
  Syntology 0 ran · 3 unverified (of 3 harvested samples) · 3 pointer-only (licence)
• Near-Data Processing for Differentiable Machine Learning Models
  6 Oct 2016 · 0 repositories · arXiv:1610.02273
• Stochastic Optimization with Variance Reduction for Infinite Datasets with Finite-Sum Structure
  4 Oct 2016 · 1 repository · arXiv:1610.00970
• Deep unsupervised learning through spatial contrasting
  2 Oct 2016 · 0 repositories · arXiv:1610.00243
• Asynchronous Stochastic Gradient Descent with Delay Compensation
  27 Sep 2016 · 0 repositories · arXiv:1609.08326
• Generalization Error Bounds for Optimization Algorithms via Stability
  27 Sep 2016 · 0 repositories · arXiv:1609.08397
• Data Dependent Convergence for Distributed Stochastic Optimization
  30 Aug 2016 · 0 repositories · arXiv:1608.08337
• Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures
  22 Aug 2016 · 9 repositories · arXiv:1608.06037
  Syntology community repositories only · 11 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; 3 where Syntology's instrument failed) · 0 unverified (of 11 harvested samples)
• Uniform Generalization, Concentration, and Adaptive Learning
  22 Aug 2016 · 0 repositories · arXiv:1608.06072
• Parallel SGD: When does averaging help?
  23 Jun 2016 · 0 repositories · arXiv:1606.07365
• Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics
  15 Jun 2016 · 1 repository · arXiv:1606.04722
• Distributed Hessian-Free Optimization for Deep Neural Network
  2 Jun 2016 · 0 repositories · arXiv:1606.00511
• Asynchrony begets Momentum, with an Application to Deep Learning
  31 May 2016 · 3 repositories · arXiv:1605.09774
• CYCLADES: Conflict-free Asynchronous Machine Learning
  31 May 2016 · 1 repository · arXiv:1605.09721
• Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent
  26 May 2016 · 0 repositories · arXiv:1605.08370
• Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations
  23 May 2016 · 0 repositories · arXiv:1605.07154
• Barzilai-Borwein Step Size for Stochastic Gradient Descent
  13 May 2016 · 1 repository · arXiv:1605.04131
  Syntology 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) · 2 unverified (of 7 harvested samples)
• Distributed stochastic optimization for deep learning (thesis)
  7 May 2016 · 0 repositories · arXiv:1605.02216
• On the Convergence of A Family of Robust Losses for Stochastic Gradient Descent
  5 May 2016 · 0 repositories · arXiv:1605.01623
• Greedy Criterion in Orthogonal Greedy Learning
  20 Apr 2016 · 0 repositories · arXiv:1604.05993
• Asynchronous Stochastic Gradient Descent with Variance Reduction for Non-Convex Optimization
  12 Apr 2016 · 0 repositories · arXiv:1604.03584
• Efficient Globally Convergent Stochastic Optimization for Canonical Correlation Analysis
  7 Apr 2016 · 0 repositories · arXiv:1604.01870
• Stochastic Variance Reduction for Nonconvex Optimization
  19 Mar 2016 · 0 repositories · arXiv:1603.06160
• Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent
  17 Mar 2016 · 0 repositories · arXiv:1603.05544
• Distributed Deep Learning Using Synchronous Stochastic Gradient Descent
  22 Feb 2016 · 0 repositories · arXiv:1602.06709
• A Variational Analysis of Stochastic Gradient Algorithms
  8 Feb 2016 · 0 repositories · arXiv:1602.02666
• Loss factorization, weakly supervised learning and label noise robustness
  8 Feb 2016 · 0 repositories · arXiv:1602.02450
• A Kronecker-factored approximate Fisher matrix for convolution layers
  3 Feb 2016 · 4 repositories · arXiv:1602.01407
  Syntology 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)
• Training Recurrent Neural Networks by Diffusion
  16 Jan 2016 · 0 repositories · arXiv:1601.04114
• A Light Touch for Heavily Constrained SGD
  15 Dec 2015 · 0 repositories · arXiv:1512.04960
• Preconditioned Stochastic Gradient Descent
  14 Dec 2015 · 2 repositories · arXiv:1512.04202
  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)
• Efficient Distributed SGD with Variance Reduction
  9 Dec 2015 · 0 repositories · arXiv:1512.02970
• Variance Reduction for Distributed Stochastic Gradient Descent
  5 Dec 2015 · 0 repositories · arXiv:1512.01708
• Kalman-based Stochastic Gradient Method with Stop Condition and Insensitivity to Conditioning
  3 Dec 2015 · 0 repositories · arXiv:1512.01139
• Finite-Time Analysis of Projected Langevin Monte Carlo
  1 Dec 2015 · 0 repositories
• Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms
  1 Dec 2015 · 0 repositories
• Distributed Deep Learning for Question Answering
  3 Nov 2015 · 0 repositories · arXiv:1511.01158
• How Important is Weight Symmetry in Backpropagation?
  17 Oct 2015 · 2 repositories · arXiv:1510.05067
• Uniform Learning in a Deep Neural Network via "Oddball" Stochastic Gradient Descent
  8 Oct 2015 · 0 repositories · arXiv:1510.02442
• Convergence of Stochastic Gradient Descent for PCA
  30 Sep 2015 · 0 repositories · arXiv:1509.09002
• Stochastic gradient descent methods for estimation with large data sets
  22 Sep 2015 · 1 repository · arXiv:1509.06459
• "Oddball SGD": Novelty Driven Stochastic Gradient Descent for Training Deep Neural Networks
  18 Sep 2015 · 0 repositories · arXiv:1509.05765
• Fast Asynchronous Parallel Stochastic Gradient Decent
  24 Aug 2015 · 0 repositories · arXiv:1508.05711
• On the Convergence of SGD Training of Neural Networks
  12 Aug 2015 · 0 repositories · arXiv:1508.02790
• Beyond Convexity: Stochastic Quasi-Convex Optimization
  8 Jul 2015 · 0 repositories · arXiv:1507.02030
• Online Learning to Sample
  30 Jun 2015 · 0 repositories · arXiv:1506.09016
• Stochastic Gradient Made Stable: A Manifold Propagation Approach for Large-Scale Optimization
  28 Jun 2015 · 0 repositories · arXiv:1506.08350
• On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants
  23 Jun 2015 · 0 repositories · arXiv:1506.06840
• Taming the Wild: A Unified Analysis of Hogwild!-Style Algorithms
  22 Jun 2015 · 0 repositories · arXiv:1506.06438
• Variance Reduced Stochastic Gradient Descent with Neighbors
  11 Jun 2015 · 0 repositories · arXiv:1506.03662
• Path-SGD: Path-Normalized Optimization in Deep Neural Networks
  8 Jun 2015 · 1 repository · arXiv:1506.02617
• Spatial Transformer Networks
  5 Jun 2015 · 45 repositories · arXiv:1506.02025
  Syntology 21 ran (of which 0 constructed an object rather than computing a result; 21 with no instrument failure: 1 honoured, 0 violated, 20 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified (of 31 harvested samples)
• Early Stopping is Nonparametric Variational Inference
  6 Apr 2015 · 1 repository · arXiv:1504.01344
• Learning Co-Sparse Analysis Operators with Separable Structures
  9 Mar 2015 · 0 repositories · arXiv:1503.02398
• ADASECANT: Robust Adaptive Secant Method for Stochastic Gradient
  23 Dec 2014 · 0 repositories · arXiv:1412.7419
• Learning from Data with Heterogeneous Noise using SGD
  17 Dec 2014 · 0 repositories · arXiv:1412.5617
• The Loss Surfaces of Multilayer Networks
  30 Nov 2014 · 1 repository · arXiv:1412.0233
• Global Convergence of Stochastic Gradient Descent for Some Non-convex Matrix Problems
  5 Nov 2014 · 0 repositories · arXiv:1411.1134
• Parallel training of DNNs with Natural Gradient and Parameter Averaging
  27 Oct 2014 · 1 repository · arXiv:1410.7455