Research map / Optimization / Nonconvex and smooth optimization
SGD with AdaGrad Stepsizes: Full Adaptivity with High Probability to Unknown Parameters, Unbounded Gradients and Affine Variance
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use AdaGrad stepsizes without knowing the problem parameters | SGD with AdaGrad stepsizes · Smooth non-convex optimization | average squared gradient norm: \tfrac{1}{T} + \tfrac{\sigma(1+\sigma)}{\sqrt{T}} | Helped |
| Use the same AdaGrad stepsize schedule in the convex setting | SGD with AdaGrad stepsizes · Smooth convex optimization | convex objective gap: \tfrac{1}{T} + \tfrac{\sigma(1+\sigma)}{\sqrt{T}} | Helped |
| Adapt stepsizes to observed gradient magnitudes under affine variance noise | SGD with AdaGrad stepsizes · Smooth convex and non-convex optimization | convergence rate: O(1/T+\sigma_0/\sqrt{T}) | Helped |
Closest papers by meaning
- Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction (NeurIPS 2024 · similarity 0.94)
- Towards Noise-adaptive, Problem-adaptive (Accelerated) Stochastic Gradient Descent (ICML 2022 · similarity 0.93)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.90)
- Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness (ICLR 2025 · similarity 0.90)
- Derivatives of Stochastic Gradient Descent in parametric optimization (NeurIPS 2024 · similarity 0.90)
- Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation (NeurIPS 2024 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.