#### Filter Results:

- Full text PDF available (36)

#### Publication Year

2009

2018

- This year (1)
- Last 5 years (44)
- Last 10 years (60)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Zeyuan Allen Zhu, Elad Hazan
- ICML
- 2016

We consider the fundamental problem in nonconvex optimization of efficiently reaching a stationary point. In contrast to the convex case, in the long history of this basic problem, the only knownâ€¦ (More)

- Zeyuan Allen Zhu, Yang Yuan
- ICML
- 2016

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 thatâ€¦ (More)

- Naman Agarwal, Zeyuan Allen Zhu, Brian Bullins, Elad Hazan, Tengyu Ma
- ArXiv
- 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 ourâ€¦ (More)

- Pinyan Lu, Xiaorui Sun, Yajun Wang, Zeyuan Allen Zhu
- EC
- 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 socialâ€¦ (More)

- Zeyuan Allen Zhu, Weizhu Chen, Tom Minka, Chenguang Zhu, Zheng Chen
- WSDM
- 2010

Recent advances in click model have positioned it as an attractive method for representing user preferences in web search and online advertising. Yet, most of the existing works focus on training theâ€¦ (More)

- Zeyuan Allen Zhu, Yang Yuan
- ICML
- 2016

Accelerated coordinate descent methods are widely used in optimization and machine learning. By taking cheap-to-compute coordinate gradients in each iteration, they are usually faster thanâ€¦ (More)

- Zeyuan Allen Zhu, Elad Hazan
- NIPS
- 2016

The diverse world of machine learning applications has given rise to a plethora of algorithms and optimization methods, finely tuned to the smoothness, convexity, and other parameterizations of theâ€¦ (More)

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 previouslyâ€¦ (More)

- Zeyuan Allen Zhu, Lorenzo Orecchia
- ITCS
- 2017

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 onâ€¦ (More)

- Zeyuan Allen Zhu, Weizhu Chen, Gang Wang, Chenguang Zhu, Zheng Chen
- 2009 Ninth IEEE International Conference on Dataâ€¦
- 2009

It is an extreme challenge to produce a nonlinear SVM classifier on very large scale data. In this paper we describe a novel P-packSVM algorithm that can solve the Support Vector Machine (SVM)â€¦ (More)