Research map / Bandits and online learning / Online convex optimization and games
Adaptive Realizable Regression from Two Online Learners
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.
Studies realizable regression under absolute loss with a finite or countable function class, proposing a reduction that runs two online learners to build an adaptive estimator.
Problem
Estimating the true regression function f* from i.i.d. realizable data under absolute loss, over a finite or countably infinite function class F.
Approach
A simple reduction that runs two online learner instances to produce an adaptive estimator for realizable regression; only the abstract is available, so the precise mechanism is not specified here.
Closest papers by meaning
- Minimax Adaptive Online Nonparametric Regression over Besov spaces (NeurIPS 2025 · similarity 0.87)
- Robust Sparse Regression with Non-Isotropic Designs (NeurIPS 2024 · similarity 0.87)
- From Average Sensitivity to Small-Loss Regret Bounds under Random-Order Model (NeurIPS 2026 · similarity 0.87)
- Robustly Learning Single-Index Models via Alignment Sharpness (ICML 2024 · similarity 0.86)
- Optimal Rates in Continual Linear Regression via Increasing Regularization (NeurIPS 2025 · similarity 0.86)
- Fully Unconstrained Online Learning (NeurIPS 2024 · similarity 0.86)
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.