Scaling Limits of Constant-Stepsize SGD at Flat Minima
Jingyi Zhang, Cheng Mao, Debankur Mukherjee
cs.LG, math.OC, math.PR, stat.ML
Submitted: 2026-07-17
Comments: 52 pages, 3 figures, 1 table
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
- Constant-Stepsize Stochastic Approximation: Finite-Time Convergence, Gaussian Approximation, and Tail Bounds
- A Piecewise Lyapunov Analysis of Sub-quadratic SGD: Applications to Robust and Quantile Regression
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks