Research map / Optimization / Nonconvex and smooth optimization
Online Adaptive Methods, Universality and Acceleration
Kfir Y. Levy, Alp Yurtsever, Volkan Cevher
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 AcceleGrad instead of AdaGrad | deterministic regression optimization · Synthetic smooth and non-smooth regression | convergence | Improved |
| Use AcceleGrad instead of universal line-search methods | stochastic regression optimization · Synthetic regression with minibatch noisy gradients | convergence | Improved |
| Increase minibatch size | AcceleGrad · Real-dataset large-minibatch experiments | performance per gradient calculation | Improved |
| Increase minibatch size | AdaGrad · Real-dataset large-minibatch experiments | performance | Hurt |
| Use a smaller line-search parameter ε | universal gradient methods · Smooth regression | convergence | Improved |
| Use a smaller line-search parameter ε | universal gradient methods · Non-smooth regression | convergence | Hurt |
| Use a larger line-search parameter ε | universal gradient methods · Non-smooth regression | convergence | Hurt |
| Use AcceleGrad's final iterates instead of its weighted average | AcceleGrad · Offline optimization experiments | convergence | Improved |
| Use universal line-search methods with noisy gradients | universal gradient methods · Stochastic regression optimization | convergence | Hurt |
Closest papers by meaning
- Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization (NeurIPS 2025 · similarity 0.89)
- Universal Gradient Methods for Stochastic Convex Optimization (ICML 2024 · similarity 0.89)
- Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness (NeurIPS 2025 · similarity 0.89)
- Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality (NeurIPS 2025 · similarity 0.88)
- Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction (NeurIPS 2024 · similarity 0.87)
- An Online Adaptive Sampling Algorithm for Stochastic Difference-of-convex Optimization with Time-varying Distributions (ICML 2025 · similarity 0.87)
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.
