Research map / Bandits and online learning / Online convex optimization and games
Regret Bounds without Lipschitz Continuity: Online Learning with Relative-Lipschitz Losses
Yihan Zhou, Victor Sanches Portella, Mark Schmidt, Nicholas Harvey
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 |
|---|---|---|---|
| Extend FTRL analysis to losses relatively Lipschitz with respect to its regularizer | FTRL · OCO with relative-Lipschitz losses | regret: Regret_T(z) ≤ 2 L √(K(T+1)) | Improved |
| Require losses to be relatively strongly convex as well as relatively Lipschitz with respect to the same reference function | FTL · OCO with relative-Lipschitz and relative-strongly-convex losses | regret: L^2/(2M) (log(T) + 1) | Improved |
| Stabilize dual iterates with γ_t = η_{t+1}/η_t | DS-OMD · OCO with relative-Lipschitz losses | regret: Regret_T(z) ≤ 2L√(K(T+1)) | Improved |
| Use γ_t = 1, skipping dual stabilization, when losses are relatively strongly convex | OMD · OCO with relative-Lipschitz and relative-strongly-convex losses | regret: L^2/(2M)(log T+1) | Improved |
| Add a known nonnegative convex extra regularizer Ψ, with Ψ(x_1)=0 | FTRL · Composite OCO with relative-Lipschitz losses | composite regret: Regret_T^Ψ(z) ≤ 2 L √(K(T+1)) | Improved |
Closest papers by meaning
- From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization (NeurIPS 2026 · similarity 0.87)
- Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets (NeurIPS 2024 · similarity 0.86)
- Universal Online Convex Optimization with $1$ Projection per Round (NeurIPS 2024 · similarity 0.86)
- Fully Unconstrained Online Learning (NeurIPS 2024 · similarity 0.86)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 2024 · similarity 0.86)
- Optimal Algorithms for Online Convex Optimization with Adversarial Constraints (NeurIPS 2024 · similarity 0.85)
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.
