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
Blind One-microphone Speech Separation: A Spectral Learning Approach
Francis Bach,Michael I. Jordan +1 more
TL;DR: This work forms the problem of speech separation as a problem in segmenting the spectrogram of the signal into two or more disjoint sets, and develops an adaptive, speech-specific segmentation algorithm that can successfully separate one-microphone speech mixtures.
Posted Content
Uncertainty Sets for Image Classifiers using Conformal Prediction
TL;DR: An algorithm is presented that modifies any classifier to output a predictive set containing the true label with a user-specified probability, such as 90%, which provides a formal finite-sample coverage guarantee for every model and dataset.
Journal ArticleDOI
On statistics, computation and scalability
TL;DR: Some of the statistical consequences of computational perspectives on scability, in particular divide-and-conquer methodology and hierarchies of convex relaxations are investigated, with the goal of identifying “time-data tradeoffs.
Shaping and policy search in reinforcement learning
Andrew Y. Ng,Michael I. Jordan +1 more
TL;DR: A theory of reward shaping is given that shows how poorly chosen shaping rewards can be eliminated and guidelines for selecting good shaping rewards that in practice give significant speedups of the learning process are given.
Proceedings Article
Gradient Descent Can Take Exponential Time to Escape Saddle Points
TL;DR: This paper shows that even with fairly natural random initialization schemes and non-pathological functions, GD can be significantly slowed down by saddle points, taking exponential time to escape.