conftrace_

step size

26 papers

Explore in graph

Co-occurring keywords

stochastic gradient descent (1091) gradient descent (1144) convergence analysis (395) convex optimization (1321) convergence rate (607) adaptive step size (18) learning rate (192) step size schedule (4) neural network (6616) lower bound (173)

Papers

Suspicious Alignment of SGD:A Fine-Grained Step Size Condition Analysis ALT 2026
On the Convergence of Projected Policy Gradient for Any Constant Step Sizes JMLR 2025
Reducing Discretization Error in the Frank-Wolfe Method AISTATS 2023
SGD with Large Step Sizes Learns Sparse Features ICML 2023
BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization NIPS 2023
DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule ICML 2023
Gradient Descent: The Ultimate Optimizer NIPS 2022
Delay-Adaptive Step-sizes for Asynchronous Learning ICML 2022
Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent ICML 2022
Understanding the unstable convergence of gradient descent ICML 2022
Revisit last-iterate convergence of mSGD under milder requirement on step size NIPS 2022
ASAP.SGD: Instance-based Adaptiveness to Staleness in Asynchronous SGD ICML 2022
Acceleration via Fractal Learning Rate Schedules ICML 2021
Guarantees for Tuning the Step Size using a Learning-to-Learn Approach ICML 2021
Parabolic Approximation Line Search for DNNs NIPS 2020
Tight Dimension Independent Lower Bound on the Expected Convergence Rate for Diminishing Step Sizes in SGD NIPS 2019
Communication trade-offs for Local-SGD with large step size NIPS 2019
Optimal Mini-Batch and Step Sizes for SAGA ICML 2019
Adaptive Three Operator Splitting ICML 2018
Step Size Matters in Deep Learning NIPS 2018
Adaptive Batch Size for Safe Policy Gradients NIPS 2017
A Study on Trust Region Update Rules in Newton Methods for Large-scale Linear Classification ACML 2017
Barzilai-Borwein Step Size for Stochastic Gradient Descent NIPS 2016
Exploration of the (Non-)Asymptotic Bias and Variance of Stochastic Gradient Langevin Dynamics JMLR 2016
On the Iteration Complexity of Oblivious First-Order Optimization Algorithms ICML 2016