2011
NeurIPS
NeurIPS 2011
Efficient Online Learning via Randomized Rounding
Abstract
Most online algorithms used in machine learning today are based on variants of mirror descent or follow-the-leader. In this paper, we present an online algorithm based on a completely different approach, which combines ``random playout'' and randomized rounding of loss subgradients. As an application of our approach, we provide the first computationally efficient online algorithm for collaborative filtering with trace-norm constrained matrices. As a second application, we solve an open question linking batch learning and transductive online learning.
🌉
Interdisciplinary Bridge
- Artificial Intelligence and Data Science & Analytics and Mathematics & Optimization
📈
Trend Setter
- Recommender Systems
🐣
Hot Topic Early Bird
- mirror descent
Authors
Topics
Machine Learning > Optimization & Theory > Optimization
Data Science & Analytics > Applications > Recommender Systems
Mathematics & Optimization > Optimization > Stochastic Methods
Mathematics & Optimization > Optimization > Online Algorithms
Machine Learning > Learning Types > Online Learning
Machine Learning > Optimization & Theory > Online Algorithms
Machine Learning > Application Areas > Recommender Systems
Machine Learning > Learning Types > Collaborative Filtering