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
Global Error Bounds and Linear Convergence for Gradient-Based Algorithms for Trend Filtering and 𝓁 1 -Convex Clustering.
TL;DR: A class of first-order gradient-type optimization algorithms to solve structured filtering-clustering problems, which include trend filtering and $\ell_1$-convex clustering as special cases, establishes the linear convergence of deterministic gradient- type algorithms despite the extreme ill-conditioning of the difference operator matrices in these problems.
A variational principle for model-based interpolation
TL;DR: This work derives the Euler-Lagrange equations for extremal motion by assigning a cost to each path through space, based on two competing goals to interpolate through regions of high density and arc length.
Journal Article
Transferred Q-learning
TL;DR: The proposed transferred Q-learning algorithm contains a novel re-targeting step which enables vertical information-cascading along multiple steps in an RL task, besides the usual horizontal information-gathering as transfer learning (TL) for supervised learning.