← Keywords

stochastic gradient descent

1088 papers

Explore in graph

Also known as

SGD ASGD SAGA SGM SGDA PSGD SKGD

Co-occurring keywords

non-convex optimization (546) distributed learning (563) neural network optimization (1293) convergence rate (606) convex optimization (1320) neural network (6616) variance reduction (520) stochastic optimization (1060) convergence analysis (394) differential privacy (1010)

Papers

Tighter Analysis for ProxSkip ICML 2023
A Bayesian Approach To Analysing Training Data Attribution In Deep Learning NIPS 2023
Beyond Uniform Lipschitz Condition in Differentially Private Optimization ICML 2023
KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training NIPS 2023
Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods AISTATS 2023
Dropout Reduces Underfitting ICML 2023
Toward Large Kernel Models ICML 2023
Implicit Jacobian regularization weighted with impurity of probability output ICML 2023
A Continuous-time Stochastic Gradient Descent Method for Continuous Data JMLR 2023
Beyond Lipschitz Smoothness: A Tighter Analysis for Nonconvex Optimization ICML 2023
Learning Compact Features via In-Training Representation Alignment AAAI 2023
spred: Solving L1 Penalty with SGD ICML 2023
SGD with Large Step Sizes Learns Sparse Features ICML 2023
Alternating Projected SGD for Equality-constrained Bilevel Optimization AISTATS 2023
Decentralized Riemannian Algorithm for Nonconvex Minimax Problems AAAI 2023
Tighter Lower Bounds for Shuffling SGD: Random Permutations and Beyond ICML 2023
ASkewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks AISTATS 2023
High Probability Convergence of Stochastic Gradient Methods ICML 2023
Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions ICML 2023
A Theoretical Analysis of the Learning Dynamics under Class Imbalance ICML 2023
DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule ICML 2023
Convergence of First-Order Methods for Constrained Nonconvex Optimization with Dependent Data ICML 2023
SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance ICML 2023
Learning-Rate-Free Learning by D-Adaptation ICML 2023
Backward Feature Correction: How Deep Learning Performs Deep (Hierarchical) Learning COLT 2023