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
Saturating Splines and Feature Selection
TL;DR: This work extends the adaptive regression spline model by incorporating saturation, the natural requirement that a function extend as a constant outside a certain range, and adapts the algorithm to fit generalized additive models with saturating splines as coordinate functions.
Journal ArticleDOI
Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization
TL;DR: This work presents a stochastic accelerated gradient-extragradient (AG-EG) descent-ascent algorithm that combines extragradients and Nesterov’s acceleration in general Stochastic settings, and achieves relatively mature characterization of optimality in saddle-point optimization.
Posted Content
Behavior-Guided Reinforcement Learning
Aldo Pacchiano,Jack Parker-Holder,Yunhao Tang,Anna Choromanska,Krzysztof Choromanski,Michael I. Jordan +5 more
TL;DR: A new approach for comparing reinforcement learning policies, using Wasserstein distances in a newly defined latent behavioral space, and utilizing the dual formulation of the WD to learn score functions over trajectories that can be in turn used to lead policy optimization towards (or away from) (un)desired behaviors.
Journal ArticleDOI
Incentive-Aware Recommender Systems in Two-Sided Markets
TL;DR: In this paper , a multi-agent bandit problem is modeled as a two-sided market with an incentive constraint induced by agents' opportunity costs, and an incentive-compatible recommendation policy is proposed.
Journal ArticleDOI
Function-Specific Mixing Times and Concentration Away from Equilibrium
TL;DR: In this article, the authors introduce function-specific analogs of mixing times and spectral gaps, and use them to prove Hoeffding-like function specific concentration inequalities for Monte Carlo approximations.