2.5k citations
- IBM Research - Thomas J. Watson Research CenterUS28 papers
- California Institute of TechnologyUS9 papers
- Columbia UniversityUS6 papers
- Vassar CollegeUS6 papers
- Stanford UniversityUS5 papers
- University of Illinois Urbana-ChampaignUS5 papers
- Carnegie Mellon UniversityUS4 papers
- Cornell UniversityUS4 papers
- IBM Research - ZurichCH4 papers
- Instituto de Ciencia de Materiales de MadridES4 papers
- University of BristolGB4 papers
- University of MichiganUS4 papers
7 papers · 2 filters
An Information-Theoretic External Cluster-Validity Measure
Byron E Dom
In this paper we propose a measure of clustering quality or accuracy that is appropriate in situations where it is desirable to evaluate a clustering algorithm by somehow comparing…
Mechanism Design for Cost Optimal PAC Learning in the Presence of Strategic Noisy Annotators
Dinesh Garg, Sourangshu Bhattacharya, S. Sundararajan +1
We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a…
Efficient and Practical Stochastic Subgradient Descent for Nuclear Norm Regularization
Haim Avron, Satyen Kale, Shiva Kasiviswanathan +1
We describe novel subgradient methods for a broad class of matrix optimization problems involving nuclear norm regularization. Unlike existing approaches, our method executes very…
Projection-free Online Learning
Elad Hazan, Satyen Kale
The computational bottleneck in applying online learning to massive data sets is usually the projection step. We present efficient online learning algorithms that eschew projection…
Near-Optimal Algorithms for Online Matrix Prediction
Elad Hazan, Satyen Kale, Shai Shalev-Shwartz
In several online prediction problems of recent interest the comparison class is composed of matrices with bounded entries. For example, in the online max-cut problem, the comparis…
Bayesian Inference in Monte-Carlo Tree Search
Gerald Tesauro, V T Rajan, Richard Segal
Monte-Carlo Tree Search (MCTS) methods are drawing great interest after yielding breakthrough results in computer Go. This paper proposes a Bayesian approach to MCTS that is inspir…