J
John C. Duchi
Researcher at Stanford University
Publications - 196
Citations - 32001
John C. Duchi is an academic researcher from Stanford University. The author has contributed to research in topics: Stochastic optimization & Minimax. The author has an hindex of 61, co-authored 186 publications receiving 27273 citations. Previous affiliations of John C. Duchi include Istituto Italiano di Tecnologia & University of California, Berkeley.
Papers
More filters
Proceedings Article
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization.
TL;DR: Adaptive subgradient methods as discussed by the authors dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradient-based learning, which allows us to find needles in haystacks in the form of very predictive but rarely seen features.
Journal Article
Adaptive Subgradient Methods for Online Learning and Stochastic Optimization
TL;DR: This work describes and analyze an apparatus for adaptively modifying the proximal function, which significantly simplifies setting a learning rate and results in regret guarantees that are provably as good as the best proximal functions that can be chosen in hindsight.
Proceedings ArticleDOI
Efficient projections onto the l1-ball for learning in high dimensions
TL;DR: Efficient algorithms for projecting a vector onto the l1-ball are described and variants of stochastic gradient projection methods augmented with these efficient projection procedures outperform interior point methods, which are considered state-of-the-art optimization techniques.
Journal ArticleDOI
Dual Averaging for Distributed Optimization: Convergence Analysis and Network Scaling
TL;DR: This work develops and analyze distributed algorithms based on dual subgradient averaging and provides sharp bounds on their convergence rates as a function of the network size and topology, and shows that the number of iterations required by the algorithm scales inversely in the spectral gap of thenetwork.
Proceedings ArticleDOI
Local Privacy and Statistical Minimax Rates
TL;DR: This paper provides a treatment of two canonical problem families: mean estimation in location family models and convex risk minimization, providing lower and upper bounds for estimation of population quantities that match up to constant factors, giving privacy-preserving mechanisms and computationally efficient estimators that achieve the bounds.