Research map / Bandits and online learning / Online convex optimization and games
Online Optimization with Memory and Competitive Control
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 |
|---|---|---|---|
| Extend ROBD to structured switching costs with multi-step memory | ROBD · OCO with structured memory, exact prediction | competitive ratio | Helped |
| Add accurate-sequence tracking and optimistic selection over the estimation set | ROBD · OCO with structured memory, inexact prediction | competitive cost | Helped |
| Reduce Input-Disturbed Squared Regulators to OCO with structured memory | Optimistic ROBD · Input-Disturbed Squared Regulators | competitive cost | Helped |
| Use the estimation-set diameter to tune the bound when disturbance estimates are good | Algorithm using Optimistic ROBD · Input-Disturbed Squared Regulators with bounded estimation-set diameter | competitive cost | Helped |
| Use a bound independent of the disturbance estimation-set size | Algorithm using Optimistic ROBD · Input-Disturbed Squared Regulators with unbounded estimation-set diameter | competitive ratio | Helped |
| Replace the true offline-optimal benchmark with the best offline linear controller | Online control evaluation · Input-Disturbed Squared Regulators | cost | Hurt |
Closest papers by meaning
- Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization (NeurIPS 2019 · similarity 0.91)
- Constrained Online Convex Optimization with Memory and Predictions (AAAI 2026 · similarity 0.90)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.90)
- Online Convex Optimization with Unbounded Memory (NeurIPS 2023 · similarity 0.89)
- Best of Both Worlds Guarantees for Smoothed Online Quadratic Optimization (ICML 2024 · similarity 0.88)
- A Simple and Optimal Approach for Universal Online Learning with Gradient Variations (NeurIPS 2024 · 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.