7k citations
- University of California, Santa BarbaraUS110 papers
- Microsoft Research (United Kingdom)GB61 papers
- Carnegie Mellon UniversityUS48 papers
- ETH ZurichCH48 papers
- University of California, BerkeleyUS45 papers
- University of Maryland, College ParkUS44 papers
- University of WashingtonUS42 papers
- Stanford UniversityUS41 papers
- Princeton UniversityUS35 papers
- Cornell UniversityUS33 papers
- California Institute of TechnologyUS28 papers
- Georgia Institute of TechnologyUS27 papers
14 papers · 2 filters
Rich Component Analysis
Rong Ge, James Zou
In many settings, we have multiple data sets (also called views) that capture different and overlapping aspects of the same phenomenon. We are often interested in finding patterns…
Convex Risk Minimization and Conditional Probability Estimation
Matus Telgarsky, Miroslav Dudík, Robert Schapire
This paper proves, in very general settings, that convex risk minimization is a procedure to select a unique conditional probability model determined by the classification problem.…
Multi-class SVMs: From Tighter Data-Dependent Generalization Bounds to Novel Algorithms
Yunwen Lei, Ürün Dogan, Alexander Binder +1
This paper studies the generalization performance of multi-class classification algorithms, for which we obtain, for the first time, a data-dependent generalization error bound wit…
Robust Regression via Hard Thresholding
Kush Bhatia, Prateek Jain, Purushottam Kar
We study the problem of Robust Least Squares Regression (RLSR) where several response variables can be adversarially corrupted. More specifically, for a data matrix X \in R^{p x n}…
Selective Greedy Equivalence Search: Finding Optimal Bayesian Networks Using a Polynomial Number of Score Evaluations
David Maxwell Chickering, Christopher Meek
We introduce Selective Greedy Equivalence Search (SGES), a restricted version of Greedy Equivalence Search (GES). SGES retains the asymptotic correctness of GES but, unlike GES, ha…
Thompson Sampling for Budgeted Multi-armed Bandits
Yingce Xia, Haifang Li, Tao Qin +2
Thompson sampling is one of the earliest randomized algorithms for multi-armed bandits (MAB). In this paper, we extend the Thompson sampling to Budgeted MAB, where there is random…