Research map / Learning theory and algorithms / Sample complexity
The Sample Complexity of Online One-Class Collaborative Filtering
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 |
|---|---|---|---|
| Use positive-only feedback rather than positive and negative feedback | User-CF · Online CF cold start | ratings required for initial exploration: by a factor of $1/\pf$ | Hurt |
| Reduce the positive-response probability $\pf$ | User-CF · Online one-class CF cold start | recommendations required for cold start: proportional to $(1/\pf^2)^{\frac{1}{1-\alpha}}$ | Hurt |
| Reduce the positive-response probability $\pf$ | User-CF · Online one-class CF preference learning | recommendations needed to learn preferences: proportional to $1/\pf$ | Hurt |
| Add negative ratings to positive-only feedback | User-CF · MovieLens-derived simulation | accumulated reward: almost twice | Helped |
| Split the item space into batches and explore batches sequentially instead of exploring the whole item space at the beginning | User-CF · Online one-class CF | time to begin exploitation: the whole item space ... proportional to $M$ | Helped |
| Start cold-start exploration substantially earlier than the order of $1/\pf^2$ recommendations | Any online algorithm · Online one-class CF worst-case instances | normalized accumulated reward: for all $T \leq \frac{\lambda}{\pf^2}$, ... $\leq \lambda + \frac{1}{K}$ | Hurt |
Closest papers by meaning
- Regret in Online Recommendation Systems (NeurIPS 2020 · similarity 0.89)
- Preference Diffusion for Recommendation (ICLR 2025 · similarity 0.88)
- Adaptive Hardness Negative Sampling for Collaborative Filtering (AAAI 2024 · similarity 0.87)
- Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation (NeurIPS 2025 · similarity 0.87)
- Recommendations with Sparse Comparison Data: Provably Fast Convergence for Nonconvex Matrix Factorization (ICML 2025 · similarity 0.87)
- From Pairwise to Ranking: Climbing the Ladder to Ideal Collaborative Filtering with Pseudo-Ranking (AAAI 2025 · 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.