Y
Yossi Arjevani
Researcher at New York University
Publications - 36
Citations - 759
Yossi Arjevani is an academic researcher from New York University. The author has contributed to research in topics: Optimization problem & Gradient descent. The author has an hindex of 12, co-authored 33 publications receiving 536 citations. Previous affiliations of Yossi Arjevani include Weizmann Institute of Science.
Papers
More filters
Posted Content
Lower Bounds for Non-Convex Stochastic Optimization.
TL;DR: It is proved that (in the worst case) any algorithm requires at least $\epsilon^{-4}$ queries to find an stationary point, and establishes that stochastic gradient descent is minimax optimal in this model.
Proceedings Article
Communication complexity of distributed convex learning and optimization
Yossi Arjevani,Ohad Shamir +1 more
TL;DR: The results indicate that without similarity between the local objective functions (due to statistical data similarity or otherwise) many communication rounds may be required, even if the machines have unbounded computational power.
Posted Content
Oracle Complexity of Second-Order Methods for Smooth Convex Optimization
TL;DR: This work proves tight bounds on the oracle complexity of second-order methods for smooth convex functions, or equivalently, the worst-case number of iterations required to optimize such functions to a given accuracy.
Journal ArticleDOI
Oracle complexity of second-order methods for smooth convex optimization
TL;DR: In this article, the authors prove tight bounds on the oracle complexity of second-order methods for smooth convex functions, or equivalently, the worst-case number of iterations required to optimize such functions to a given accuracy.
Journal Article
On lower and upper bounds in smooth and strongly convex optimization
TL;DR: A novel framework to study smooth and strongly convex optimization algorithms and presents a novel systematic derivation of Nesterov's well-known Accelerated Gradient Descent method, expressing it as an optimal solution for the corresponding optimization problem over polynomials.