M
Michael I. Jordan
Researcher at University of California, Berkeley
Publications - 1110
Citations - 241763
Michael I. Jordan is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Computer science & Inference. The author has an hindex of 176, co-authored 1016 publications receiving 216204 citations. Previous affiliations of Michael I. Jordan include Stanford University & Princeton University.
Papers
More filters
Proceedings Article
Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization.
TL;DR: In this article, the authors introduce a new class of structured nonconvex-nonconcave min-max optimization problems, and propose a generalization of the extragradient algorithm which provably converges to a stationary point.
Posted Content
Optimal Rates and Tradeoffs in Multiple Testing
TL;DR: This work derives a precise non-asymptotic tradeoff between FNR and FDR for a variant of the generalized Gaussian sequence model and proves that the Benjamini-Hochberg algorithm as well as the Barber-Candes algorithm are both rate-optimal up to constants across these regimes.
Proceedings ArticleDOI
Improved Sample Complexity for Stochastic Compositional Variance Reduced Gradient.
TL;DR: A new stochastic compositional variance-reduced gradient algorithm with the sample complexity of O((m + n)log(1/ε) + 1/ε3) where m + n is the total number of samples and the dependence on m is optimal up to a logarithmic factor.
Mixed Membership Matrix Factorization.
TL;DR: This work develops a fully Bayesian framework for integrating the two approaches into unified Mixed Membership Matrix Factorization (M3F) models, and introduces two M3F models, derive Gibbs sampling inference procedures, and validate the methods on the EachMovie, MovieLens, and Netflix Prize collaborative filtering datasets.
Journal ArticleDOI
Mining Massive Amounts of Genomic Data: A Semiparametric Topic Modeling Approach
TL;DR: This work uses large-scale gene expression and chromatin immunoprecipitation data corpuses to conduct high-throughput TF-biological context association analysis and establishes a robust method to identify the association between TFs and biological contexts.