Methods › General › Stochastic Optimization › SGD › Papers, page 16

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 16 of 21: papers 1,501 to 1,600 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.

• Communication trade-offs for Local-SGD with large step size
  1 Dec 2019 · 1 repository
• Control Batch Size and Learning Rate to Generalize Well: Theoretical and Empirical Evidence
  1 Dec 2019 · 0 repositories
• Efficient Meta Learning via Minibatch Proximal Update
  1 Dec 2019 · 0 repositories
• Fast and Accurate Stochastic Gradient Estimation
  1 Dec 2019 · 1 repository
• Optimal Sparsity-Sensitive Bounds for Distributed Mean Estimation
  1 Dec 2019 · 1 repository
• Qsparse-local-SGD: Distributed SGD with Quantization, Sparsification and Local Computations
  1 Dec 2019 · 1 repository
• A Hybrid Approach Towards Two Stage Bengali Question Classification Utilizing Smart Data Balancing Technique
  30 Nov 2019 · 0 repositories · arXiv:1912.00127
• On the Heavy-Tailed Theory of Stochastic Gradient Descent for Deep Neural Networks
  29 Nov 2019 · 0 repositories · arXiv:1912.00018
• Non-parametric Uni-modality Constraints for Deep Ordinal Classification
  25 Nov 2019 · 1 repository · arXiv:1911.10720
• Neural Networks Learning and Memorization with (almost) no Over-Parameterization
  22 Nov 2019 · 0 repositories · arXiv:1911.09873
• Parameter-Free Locally Differentially Private Stochastic Subgradient Descent
  21 Nov 2019 · 0 repositories · arXiv:1911.09564
• Bayesian interpretation of SGD as Ito process
  20 Nov 2019 · 0 repositories · arXiv:1911.09011
• Local AdaAlter: Communication-Efficient Stochastic Gradient Descent with Adaptive Learning Rates
  20 Nov 2019 · 1 repository · arXiv:1911.09030
• Optimal Mini-Batch Size Selection for Fast Gradient Descent
  15 Nov 2019 · 0 repositories · arXiv:1911.06459
• Throughput Prediction of Asynchronous SGD in TensorFlow
  12 Nov 2019 · 0 repositories · arXiv:1911.04650
• MindTheStep-AsyncPSGD: Adaptive Asynchronous Parallel Stochastic Gradient Descent
  8 Nov 2019 · 0 repositories · arXiv:1911.03444
• A Rule for Gradient Estimator Selection, with an Application to Variational Inference
  5 Nov 2019 · 0 repositories · arXiv:1911.01894
• Reinforced Product Metadata Selection for Helpfulness Assessment of Customer Reviews
  1 Nov 2019 · 0 repositories
• Mixing of Stochastic Accelerated Gradient Descent
  31 Oct 2019 · 0 repositories · arXiv:1910.14616
• On the Convergence of Local Descent Methods in Federated Learning
  31 Oct 2019 · 0 repositories · arXiv:1910.14425
• Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization
  30 Oct 2019 · 2 repositories · arXiv:1910.13598
  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)
• Lsh-sampling Breaks the Computation Chicken-and-egg Loop in Adaptive Stochastic Gradient Estimation
  30 Oct 2019 · 0 repositories · arXiv:1910.14162
• Online Stochastic Gradient Descent with Arbitrary Initialization Solves Non-smooth, Non-convex Phase Retrieval
  28 Oct 2019 · 0 repositories · arXiv:1910.12837
• A geometric interpretation of stochastic gradient descent using diffusion metrics
  27 Oct 2019 · 0 repositories · arXiv:1910.12194
• Asynchronous Decentralized SGD with Quantized and Local Updates
  27 Oct 2019 · 0 repositories · arXiv:1910.12308
• Sound Event Recognition in a Smart City Surveillance Context
  27 Oct 2019 · 0 repositories · arXiv:1910.12369
• Bias-Variance Tradeoff in a Sliding Window Implementation of the Stochastic Gradient Algorithm
  25 Oct 2019 · 0 repositories · arXiv:1910.11868
• The Practicality of Stochastic Optimization in Imaging Inverse Problems
  22 Oct 2019 · 0 repositories · arXiv:1910.10100
• Communication-Efficient Local Decentralized SGD Methods
  21 Oct 2019 · 0 repositories · arXiv:1910.09126
• Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD
  21 Oct 2019 · 0 repositories · arXiv:1910.09466
• Error Lower Bounds of Constant Step-size Stochastic Gradient Descent
  18 Oct 2019 · 0 repositories · arXiv:1910.08212
• Improving the convergence of SGD through adaptive batch sizes
  18 Oct 2019 · 0 repositories · arXiv:1910.08222
• Interpreting Basis Path Set in Neural Networks
  18 Oct 2019 · 0 repositories · arXiv:1910.09402
• Robust Learning Rate Selection for Stochastic Optimization via Splitting Diagnostic
  18 Oct 2019 · 0 repositories · arXiv:1910.08597
• Why bigger is not always better: on finite and infinite neural networks
  17 Oct 2019 · 0 repositories · arXiv:1910.08013
• Derivative-Free Optimization of Neural Networks using Local Search
  15 Oct 2019 · 1 repository
• DP-MAC: The Differentially Private Method of Auxiliary Coordinates for Deep Learning
  15 Oct 2019 · 1 repository · arXiv:1910.06924
• Demon: Improved Neural Network Training with Momentum Decay
  11 Oct 2019 · 2 repositories · arXiv:1910.04952
• Distributed Learning of Deep Neural Networks using Independent Subnet Training
  4 Oct 2019 · 2 repositories · arXiv:1910.02120
• The Complexity of Finding Stationary Points with Stochastic Gradient Descent
  4 Oct 2019 · 0 repositories · arXiv:1910.01845
• Accelerating Deep Learning by Focusing on the Biggest Losers
  2 Oct 2019 · 2 repositories · arXiv:1910.00762
• Adaptive Activation Thresholding: Dynamic Routing Type Behavior for Interpretability in Convolutional Neural Networks
  1 Oct 2019 · 0 repositories
• How noise affects the Hessian spectrum in overparameterized neural networks
  1 Oct 2019 · 0 repositories · arXiv:1910.00195
• SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum
  1 Oct 2019 · 2 repositories · arXiv:1910.00643
  Syntology official: harvested for another paper · 0 ran · 3 unverified (of 3 harvested samples) · 1 pointer-only (licence)
• Small Steps and Giant Leaps: Minimal Newton Solvers for Deep Learning
  1 Oct 2019 · 1 repository
• Distributed SGD Generalizes Well Under Asynchrony
  29 Sep 2019 · 0 repositories · arXiv:1909.13391
• A Mean-Field Theory for Kernel Alignment with Random Features in Generative and Discriminative Models
  25 Sep 2019 · 0 repositories · arXiv:1909.11820
• Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
  25 Sep 2019 · 2 repositories · arXiv:1909.11378
• Gap Aware Mitigation of Gradient Staleness
  24 Sep 2019 · 0 repositories · arXiv:1909.10802
• Algorithm for Training Neural Networks on Resistive Device Arrays
  17 Sep 2019 · 0 repositories · arXiv:1909.07908
• Finite Depth and Width Corrections to the Neural Tangent Kernel
  13 Sep 2019 · 0 repositories · arXiv:1909.05989
• diffGrad: An Optimization Method for Convolutional Neural Networks
  12 Sep 2019 · 1 repository · arXiv:1909.11015
• The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication
  11 Sep 2019 · 0 repositories · arXiv:1909.05350
• Tighter Theory for Local SGD on Identical and Heterogeneous Data
  10 Sep 2019 · 0 repositories · arXiv:1909.04746
• Byzantine-Resilient Stochastic Gradient Descent for Distributed Learning: A Lipschitz-Inspired Coordinate-wise Median Approach
  10 Sep 2019 · 0 repositories · arXiv:1909.04532
• A Stochastic Quasi-Newton Method with Nesterov's Accelerated Gradient
  9 Sep 2019 · 0 repositories · arXiv:1909.03621
• Communication-Censored Distributed Stochastic Gradient Descent
  9 Sep 2019 · 1 repository · arXiv:1909.03631
• Distributed Training of Embeddings using Graph Analytics
  8 Sep 2019 · 0 repositories · arXiv:1909.03359
• Decentralized Stochastic Gradient Tracking for Non-convex Empirical Risk Minimization
  6 Sep 2019 · 0 repositories · arXiv:1909.02712
• FreeAnchor: Learning to Match Anchors for Visual Object Detection
  5 Sep 2019 · 4 repositories · arXiv:1909.02466
  Syntology 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) · 0 unverified (of 3 harvested samples)
• Quasi-Newton Optimization Methods For Deep Learning Applications
  4 Sep 2019 · 0 repositories · arXiv:1909.01994
• A Concert-planning Tool for Independent Musicians by Machine Learning Models
  29 Aug 2019 · 0 repositories · arXiv:1908.11200
• Automatic and Simultaneous Adjustment of Learning Rate and Momentum for Stochastic Gradient Descent
  20 Aug 2019 · 1 repository · arXiv:1908.07607
• AdaCliP: Adaptive Clipping for Private SGD
  20 Aug 2019 · 1 repository · arXiv:1908.07643
• Multi Target Tracking by Learning from Generalized Graph Differences
  19 Aug 2019 · 1 repository · arXiv:1908.06646
• Towards Better Generalization: BP-SVRG in Training Deep Neural Networks
  18 Aug 2019 · 0 repositories · arXiv:1908.06395
• NUQSGD: Improved Communication Efficiency for Data-parallel SGD via Nonuniform Quantization
  16 Aug 2019 · 1 repository · arXiv:1908.06077
  Syntology 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) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
• On the Convergence of AdaBound and its Connection to SGD
  13 Aug 2019 · 2 repositories · arXiv:1908.04457
• Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations
  12 Aug 2019 · 0 repositories · arXiv:1908.04207
• The HSIC Bottleneck: Deep Learning without Back-Propagation
  5 Aug 2019 · 3 repositories · arXiv:1908.01580
  Syntology official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified (of 16 harvested samples) · 1 pointer-only (licence)
• How Good is SGD with Random Shuffling?
  31 Jul 2019 · 0 repositories · arXiv:1908.00045
• Deep Gradient Boosting -- Layer-wise Input Normalization of Neural Networks
  29 Jul 2019 · 0 repositories · arXiv:1907.12608
• DEAM: Adaptive Momentum with Discriminative Weight for Stochastic Optimization
  25 Jul 2019 · 0 repositories · arXiv:1907.11307
• Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization
  24 Jul 2019 · 0 repositories · arXiv:1907.10732
• Mix and Match: An Optimistic Tree-Search Approach for Learning Models from Mixture Distributions
  23 Jul 2019 · 1 repository · arXiv:1907.10154
• Practical Newton-Type Distributed Learning using Gradient Based Approximations
  22 Jul 2019 · 0 repositories · arXiv:1907.09562
• Speeding Up Iterative Closest Point Using Stochastic Gradient Descent
  22 Jul 2019 · 1 repository · arXiv:1907.09133
• Post-synaptic potential regularization has potential
  19 Jul 2019 · 1 repository · arXiv:1907.08544
• SGD momentum optimizer with step estimation by online parabola model
  16 Jul 2019 · 1 repository · arXiv:1907.07063
• Amplifying Rényi Differential Privacy via Shuffling
  11 Jul 2019 · 0 repositories · arXiv:1907.05156
• A Highly Efficient Distributed Deep Learning System For Automatic Speech Recognition
  10 Jul 2019 · 0 repositories · arXiv:1907.05701
• Ordered SGD: A New Stochastic Optimization Framework for Empirical Risk Minimization
  9 Jul 2019 · 2 repositories · arXiv:1907.04371
  Syntology 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) · 2 pointer-only (licence)
• Unified Optimal Analysis of the (Stochastic) Gradient Method
  9 Jul 2019 · 0 repositories · arXiv:1907.04232
• Stochastic Gradient and Langevin Processes
  7 Jul 2019 · 0 repositories · arXiv:1907.03215
• Next Generation Radiogenomics Sequencing for Prediction of EGFR and KRAS Mutation Status in NSCLC Patients Using Multimodal Imaging and Machine Learning Approaches
  3 Jul 2019 · 0 repositories · arXiv:1907.02121
• On Symmetry and Initialization for Neural Networks
  1 Jul 2019 · 0 repositories · arXiv:1907.00560
• Approximate matrix completion based on cavity method
  29 Jun 2019 · 0 repositories · arXiv:1907.00138
• DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM
  28 Jun 2019 · 1 repository · arXiv:1906.12056
• Faster Distributed Deep Net Training: Computation and Communication Decoupled Stochastic Gradient Descent
  28 Jun 2019 · 0 repositories · arXiv:1906.12043
• Gradient Noise Convolution (GNC): Smoothing Loss Function for Distributed Large-Batch SGD
  26 Jun 2019 · 0 repositories · arXiv:1906.10822
• Learning Data Augmentation Strategies for Object Detection
  26 Jun 2019 · 6 repositories · arXiv:1906.11172
  Syntology community repositories only · 3 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; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)
• First Exit Time Analysis of Stochastic Gradient Descent Under Heavy-Tailed Gradient Noise
  21 Jun 2019 · 1 repository · arXiv:1906.09069
• Data Cleansing for Models Trained with SGD
  20 Jun 2019 · 1 repository · arXiv:1906.08473
  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) · 0 unverified (of 1 harvested sample)
• Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
  18 Jun 2019 · 3 repositories · arXiv:1906.08632
  Syntology community repositories only · 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)
• On the Noisy Gradient Descent that Generalizes as SGD
  18 Jun 2019 · 1 repository · arXiv:1906.07405
• REMAP: Multi-layer entropy-guided pooling of dense CNN features for image retrieval
  15 Jun 2019 · 0 repositories · arXiv:1906.06626
• Stochastic Proximal AUC Maximization
  14 Jun 2019 · 0 repositories · arXiv:1906.06053
• Layered SGD: A Decentralized and Synchronous SGD Algorithm for Scalable Deep Neural Network Training
  13 Jun 2019 · 0 repositories · arXiv:1906.05936
• Training Neural Networks for and by Interpolation
  13 Jun 2019 · 1 repository · arXiv:1906.05661
  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) · 1 unverified (of 4 harvested samples)
• ADASS: Adaptive Sample Selection for Training Acceleration
  11 Jun 2019 · 0 repositories · arXiv:1906.04819