Research map / Learning theory and algorithms / Sample complexity
Sample-Efficient Agnostic Boosting
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
The paper studies sample-efficient agnostic boosting, aiming to match ERM-level sample complexity for aggregating weak learners in the agnostic setting.
Problem
Boosting in the agnostic setting has been less sample-efficient than ERM; the paper targets agnostic boosting that matches the sample complexity of ERM while retaining computational efficiency via weak learners.
Approach
Provides an agnostic boosting procedure whose sample complexity matches that of ERM, as known in the realizable case, using only approximate weak learners. The supplied text is only the NeurIPS template, so the specific method details could not be extracted.
Experimental setup
Builds on: AdaBoost
Closest papers by meaning
- Sample-Optimal Agnostic Boosting with Unlabeled Data (ICML 2025 · similarity 0.96)
- Revisiting Agnostic Boosting (NeurIPS 2025 · similarity 0.93)
- A Boosting Approach to Reinforcement Learning (NeurIPS 2022 · similarity 0.91)
- The Many Faces of Optimal Weak-to-Strong Learning (NeurIPS 2024 · similarity 0.89)
- Statistical Inference for Gradient Boosting Regression (NeurIPS 2025 · similarity 0.87)
- Optimal Parallelization of Boosting (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.