conftrace_

step size schedule

11 papers

Explore in graph

Co-occurring keywords · papers mentioning both

stochastic gradient descent (6) convergence rate (5) convex optimization (4) step size (3) anytime convergence (2) gradient descent (2) non-convex optimization (2) parameter-free optimization (1) vision and language transfer (1) neural network (1)

Papers

A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak–Ruppert Averaging COLT 2026 Anytime Acceleration of Gradient Descent COLT 2025 Open Problem: Anytime Convergence Rate of Gradient Descent COLT 2024 DoG is SGD’s Best Friend: A Parameter-Free Dynamic Step Size Schedule ICML 2023 SGD with Large Step Sizes Learns Sparse Features ICML 2023 A Damped Newton Method Achieves Global $\mathcal O \left(\frac{1}{k^2}\right)$ and Local Quadratic Convergence Rate NeurIPS 2022 Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent ICML 2022 On the Convergence of Step Decay Step-Size for Stochastic Optimization NeurIPS 2021 Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise COLT 2020 On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems NeurIPS 2020 Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD ICML 2019