Research map / Learning theory and algorithms / Sample complexity
Lifelong Learning with Weighted Majority Votes
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 |
|---|---|---|---|
| Learn each new task via weighted majority votes over stored base hypotheses (reuse representation) instead of learning every task in isolation, when the task is γ-separated-compatible with the base set | Lifelong learning of majority votes (Algorithm 1) · Theoretical sample complexity (stream of realizable tasks) | total labeled examples | Helped |
| Replace linear combinations of base predictors with weighted majority votes to obtain stability of the representation under arbitrary marginal distributions | Lifelong learning representation stability · Theoretical analysis (arbitrary marginals, discrepancy-bounded) | error propagation control | Helped |
| Unknown task horizon and effective dimension handled via doubling trick (Algorithm 2) instead of knowing n and k | Lifelong learning algorithm · Theoretical sample complexity | total labeled examples | Mixed |
Closest papers by meaning
- Active Lifelong Learning With "Watchdog" (AAAI 2018 · similarity 0.86)
- HOUDINI: Lifelong Learning as Program Synthesis (NeurIPS 2018 · similarity 0.86)
- On the Theory of Transfer Learning: The Importance of Task Diversity (NeurIPS 2020 · similarity 0.86)
- Lifelong Learning with a Changing Action Set (AAAI 2020 · similarity 0.85)
- Beyond task diversity: provable representation transfer for sequential multitask linear bandits (NeurIPS 2024 · similarity 0.84)
- Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning (NeurIPS 2025 · similarity 0.84)
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.