Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Spectral Sparsification and Regret Minimization Beyond Matrix Multiplicative Updates

- Z. Zhu, Zhenyu Liao, L. Orecchia
- Computer Science, Mathematics
- STOC '15
- 14 June 2015

In this paper, we provide a novel construction of the linear-sized spectral sparsifiers of Batson, Spielman and Srivastava [11]. While previous constructions required Ω(n4) running time [11, 45], our… Expand

Variance Reduction for Faster Non-Convex Optimization

- Z. Zhu, Elad Hazan
- Computer Science, Mathematics
- ICML
- 17 March 2016

We consider the fundamental problem in non-convex optimization of efficiently reaching a stationary point. In contrast to the convex case, in the long history of this basic problem, the only known… Expand

Katyusha: the first direct acceleration of stochastic gradient methods

- Z. Zhu
- Computer Science
- STOC
- 2017

Finding approximate local minima faster than gradient descent

- Naman Agarwal, Z. Zhu, Brian Bullins, Elad Hazan, Tengyu Ma
- Computer Science, Mathematics
- STOC
- 3 November 2016

We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and the number of… Expand

Improved SVRG for Non-Strongly-Convex or Sum-of-Non-Convex Objectives

Many classical algorithms are found until several years later to outlive the confines in which they were conceived, and continue to be relevant in unforeseen settings. In this paper, we show that… Expand

Linear Coupling: An Ultimate Unification of Gradient and Mirror Descent

- Z. Zhu, L. Orecchia
- Mathematics, Computer Science
- ITCS
- 6 July 2014

First-order methods play a central role in large-scale convex optimization. Even though many variations exist, each suited to a particular problem form, almost all such methods fundamentally rely on… Expand

Even Faster Accelerated Coordinate Descent Using Non-Uniform Sampling

- Z. Zhu, Zheng Qu, Peter Richtárik, Y. Yuan
- Mathematics, Computer Science
- ICML
- 30 December 2015

Accelerated coordinate descent is widely used in optimization due to its cheap per-iteration cost and scalability to large-scale problems. Up to a primal-dual transformation, it is also the same as… Expand

Finding Approximate Local Minima for Nonconvex Optimization in Linear Time

- Naman Agarwal, Z. Zhu, Brian Bullins, Elad Hazan, Tengyu Ma
- Computer Science, Mathematics
- ArXiv
- 3 November 2016

We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which is linear in the input representation. The time complexity of our… Expand

Asymptotically optimal strategy-proof mechanisms for two-facility games

- Pinyan Lu, Xiaorui Sun, Y. Wang, Z. Zhu
- Computer Science
- EC '10
- 7 June 2010

We consider the problem of locating facilities in a metric space to serve a set of selfish agents. The cost of an agent is the distance between her own location and the nearest facility. The social… Expand

A simple, combinatorial algorithm for solving SDD systems in nearly-linear time

- J. Kelner, L. Orecchia, Aaron Sidford, Z. Zhu
- Computer Science, Mathematics
- STOC '13
- 28 January 2013

In this paper, we present a simple combinatorial algorithm that solves symmetric diagonally dominant (SDD) linear systems in nearly-linear time. It uses little of the machinery that previously… Expand