7k citations
- University of California, Santa BarbaraUS79 papers
- ETH ZurichCH24 papers
- University of California, BerkeleyUS24 papers
- University of Maryland, College ParkUS24 papers
- California Institute of TechnologyUS22 papers
- Princeton UniversityUS18 papers
- Microsoft Research (United Kingdom)GB17 papers
- University of California, Los AngelesUS16 papers
- Stanford UniversityUS15 papers
- Board of the Swiss Federal Institutes of TechnologyCH11 papers
- Cornell UniversityUS11 papers
- Microsoft Research New England (United States)US10 papers
25 papers · 2 filters
Stochastic Gradient Descent for Non-smooth Optimization: Convergence Results and Optimal Averaging Schemes
Ohad Shamir, Tong Zhang
Stochastic Gradient Descent (SGD) is one of the simplest and most popular stochastic optimization methods. While it has already been theoretically studied for decades, the classica…
Staged Mixture Modelling and Boosting
Christopher Meek, Bo Thiesson, David Heckerman
In this paper, we introduce and evaluate a data-driven staged mixture modeling technique for building density, regression, and classification models. Our basic approach is to seque…
Markov Random Walk Representations with Continuous Distributions
Chen-Hsiang Yeang, Martin Szummer
Representations based on random walks can exploit discrete data distributions for clustering and classification. We extend such representations from discrete to continuous distribu…
Large-Sample Learning of Bayesian Networks is NP-Hard
David Maxwell Chickering, Christopher Meek, David Heckerman
In this paper, we provide new complexity results for algorithms that learn discrete-variable Bayesian networks from data. Our results apply whenever the learning algorithm uses a s…
Bayesian Hierarchical Mixtures of Experts
Christopher M. Bishop, Markus Svensen
The Hierarchical Mixture of Experts (HME) is a well-known tree-based model for regression and classification, based on soft probabilistic splits. In its original formulation it was…
Distributed Non-Stochastic Experts
Varun Kanade, Zhenming Liu, Bozidar Radunovic
We consider the online distributed non-stochastic experts problem, where the distributed system consists of one coordinator node that is connected to sites, and the sites are r…