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
Posted Content
Optimal rates for zero-order convex optimization: the power of two function evaluations
TL;DR: Focusing on nonasymptotic bounds on convergence rates, it is shown that if pairs of function values are available, algorithms for d-dimensional optimization that use gradient estimates based on random perturbations suffer a factor of at most √d in convergence rate over traditional stochastic gradient methods.
Proceedings Article
Estimation, Optimization, and Parallelism when Data is Sparse
TL;DR: It is shown how leveraging sparsity leads to (still minimax optimal) parallel and asynchronous algorithms, providing experimental evidence complementing the theoretical results on several medium to large-scale learning tasks.
Proceedings Article
Variational MCMC
TL;DR: In this paper, a mixture of two MCMC kernels, a random walk Metropolis kernel and a block Metropolis-Hastings (MH) kernel with a variational approximation as proposal distribution, is proposed.
Proceedings ArticleDOI
Regression on manifolds using kernel dimension reduction
TL;DR: This work optimization cross-covariance operators in kernel feature spaces that are induced by the normalized graph Laplacian and results are a highly flexible method in which no strong assumptions are made on the regression function or on the distribution of the covariates.
Proceedings ArticleDOI
Word Alignment via Quadratic Assignment
TL;DR: This work addresses the limitations of the proposed bipartite matching model of Taskar et al. (2005) by enriching the model form, and gives estimation and inference algorithms for these enhancements.