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 ArticleDOI
Learning from measurements in exponential families
TL;DR: A Bayesian decision-theoretic framework is presented, which allows us to both integrate diverse measurements and choose new measurements to make, and a variational inference algorithm is used, which exploits exponential family duality.
Journal ArticleDOI
On the computational complexity of high-dimensional Bayesian variable selection
TL;DR: In this article, the authors study the computational complexity of Markov chain Monte Carlo (MCMC) methods for high-dimensional Bayesian linear regression under sparsity constraints and show that a Bayesian approach can achieve variable-selection consistency under relatively mild conditions on the design matrix.
Journal ArticleDOI
Obstacle avoidance and a perturbation sensitivity model for motor planning
TL;DR: This work explored whether the CNS plans arm movements based entirely on the visual space kinematics of the movements, or whether the planning process incorporates specific details of the biomechanical plant to optimize the trajectory plan.
Proceedings Article
An Analysis of the Convergence of Graph Laplacians
TL;DR: A kernel-free framework is introduced to analyze graph constructions with shrinking neighborhoods in general and apply it to analyze locally linear embedding (LLE) and how desirable properties such as a convergent spectrum and sparseness can be achieved by choosing the appropriate graph construction.
Proceedings Article
Underdamped Langevin MCMC: A non-asymptotic analysis
TL;DR: A MCMC algorithm based on its discretization is presented and it is shown that it achieves $\varepsilon$ error (in 2-Wasserstein distance) in $\mathcal{O}(\sqrt{d}/\varePSilon)$ steps, a significant improvement over the best known rate for overdamped Langevin MCMC.