Research map / Learning theory and algorithms / Matrix and tensor methods
Mistake Bounds for Binary Matrix Completion
Mark Herbster, Stephen Pasteris, Massimiliano Pontil
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 |
|---|---|---|---|
| Use Matrix Exponentiated Gradient (Matrix Winnow-style) online prediction instead of per-task Kernel Perceptron with a fixed kernel | binary matrix completion in online setting · theoretical mistake bound (Theorem 3.1) | mistake bound scaling | No clear effect |
| Compare bound to trace-norm regret bounds: margin-complexity-based bound needs ~n examples vs ~n^{3/2} in [16] and ~n^{7/4} in [17] to become non-trivial | online matrix completion bound · theoretical comparison with [16], [17] | number of observed entries before bound is non-trivial | Improved |
Closest papers by meaning
- Online Matrix Completion with Side Information (NeurIPS 2020 · similarity 0.91)
- Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent (NeurIPS 2016 · similarity 0.87)
- Generalization Analysis of Deep Non-linear Matrix Completion (ICML 2024 · similarity 0.86)
- Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting (NeurIPS 2024 · similarity 0.85)
- Online Learning of Neural Networks (NeurIPS 2025 · similarity 0.85)
- Symmetric Matrix Completion with ReLU Sampling (ICML 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.
