method · first seen 4 Oct 2026
stochastic gradient descent
Also: SGD
An optimization method that updates parameters using gradients estimated from small random batches of data.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Gaussian Limits for SGD Without Stationary MomentsPapers · 4 Oct 2026 · Xiaoli Li, Wei Biao Wu
- Rare Gate Disagreements Can Limit Plasticity: When Gradient Flow Mispredicts Finite-Batch SGDPapers · 8 Oct 2026 · Ruoyu Zhao, Mingxuan Zhang, Jianbo Dai, Jiaqi Wu, Chenyu Zhu, Tong Che
- Strong Gaussian Approximation of Constant Learning Rate SGD: Bias and Trajectory InferencePapers · 10 Oct 2026 · Joseph Keslin, Wei Biao Wu
- Asymptotic Risk of Learning-Rate Schedules for Least-Squares Regression with Discretely Distributed FeaturesPapers · 12 Oct 2026 · Noé Colomban, Francis Bach, Fabian Schaipp
- Feature Normalization under Finite Training BudgetsPapers · 12 Oct 2026 · Johan Larsson
- A Rate Transfer Method: Convergence Rates in Stochastic Gradient Descent via Stochastic CalculusPapers · 13 Oct 2026 · Neil Walton
Latest sources
- Improved last-iterate bounds for SGD with and without replacementPapers · 10 Nov 2026 · Yimin Zhong, Jiaxin Zhou
- Settling the Burn-in Gap: Sharp Risk Bounds for Tail-Averaged SGD in Linear RegressionPapers · 10 Nov 2026 · Qingyue Zhao, Xuheng Li, Quanquan Gu
- Learning Rate Decay Can Exponentially Accelerate SGD for Global Optimization of Nonconvex FunctionsPapers · 9 Nov 2026 · Guneykan Ozgul, Dylan Herman, Junhyung Lyle Kim, Shree Hari Sureshbabu, Shouvani…
- Last-Iterate Convergence of Stochastic Gradient Methods for Unbounded ProblemsPapers · 5 Nov 2026 · Kevin Kurian Thomas Vaidyan, Ahmet Alacaoglu, Michael P. Friedlander
- Stepsize modulation for cross entropy from local quadratic optimizationPapers · 3 Nov 2026 · Bruno Bauwens, Viacheslav Krivodub, Bingyu Zhang
- Lower Bounds on Inference Complexity for Polyak-Ruppert Averaged Stochastic Gradient DescentPapers · 31 Oct 2026 · Denis Belomestny, Alexey Naumov, Sergey Samsonov
- Self-Normalized Inference from Riemannian Stochastic Gradient PathsPapers · 31 Oct 2026 · Xiaotian Chang, Qirui Hu, Yi Liu
- Stochastic learning flow: moment equations for stochastic gradient descent at finite step sizePapers · 30 Oct 2026 · Christian Schmid, James M Murray
- Exact Theory and Optimal Stepsizes for Stochastic Gradient Descent in Smooth Convex MinimizationPapers · 30 Oct 2026 · Benjamin Grimmer, Qining Shen
- Stochastic and Noisy Oracles in Smooth Continuous OptimizationPapers · 29 Oct 2026 · Albert S. Berahas, Liyuan Cao, Katya Scheinberg
- Finite-step statistical mechanics of scale-invariant learning: spectral equations of state and curvature transportPapers · 27 Oct 2026 · Alexander Itin
- On the stability of learningPapers · 26 Oct 2026 · John J. Vastola