Research map / Bandits and online learning / Online convex optimization and games
Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Improves regret bounds for online-within-online meta learning of initialization and step size in the non-convex setting.
Problem
Online-within-online (OWO) meta learning, where tasks and their data arrive sequentially, learning the initialization and step size of within-task online algorithms under non-convex losses.
Approach
Provides improved regret bounds for OWO meta learning of initialization and step size in the non-convex setting under mild assumptions on the loss functions, improving over previous analyses.
Experimental setup
Metrics: regret bound
Closest papers by meaning
- Online Non-convex Learning in Dynamic Environments (NeurIPS 2024 · similarity 0.88)
- From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model (NeurIPS 2026 · similarity 0.87)
- A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds (NeurIPS 2024 · similarity 0.87)
- Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning (NeurIPS 2024 · similarity 0.87)
- Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes (NeurIPS 2025 · similarity 0.87)
- Small-loss Adaptive Regret for Online Convex Optimization (ICML 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.