#### Filter Results:

- Full text PDF available (80)

#### Publication Year

2001

2019

- This year (12)
- Last 5 years (51)
- Last 10 years (91)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- John C. Duchi, Elad Hazan, Yoram Singer
- Journal of Machine Learning Research
- 2011

We present a new family of subgradient methods that dynamically incorporate knowledge of the geometry of the data observed in earlier iterations to perform more informative gradientbased learning.â€¦ (More)

- Elad Hazan, Adam Tauman Kalai, Satyen Kale, Amit Agarwal
- Machine Learning
- 2006

In an online convex optimization problem a decision-maker makes a sequence of decisions, i.e., chooses a sequence of points in Euclidean space, from a fixed feasible set. After each point is chosen,â€¦ (More)

- Sanjeev Arora, Elad Hazan, Satyen Kale
- Theory of Computing
- 2012

Algorithms in varied fields use the idea of maintaining a distribution over a certain set and use the multiplicative update rule to iteratively change these weights. Their analysis are usually veryâ€¦ (More)

- Elad Hazan
- 2015

- Jacob D. Abernethy, Elad Hazan, Alexander Rakhlin
- COLT
- 2008

We introduce an efficient algorithm for the problem of online linear optimization in the bandit setting which achieves the optimal Oâˆ—( âˆš T ) regret. The setting is a natural generalization of theâ€¦ (More)

- Elad Hazan, Satyen Kale
- COLT
- 2011

We give novel algorithms for stochastic strongly-convex optimization in the gradient oracle model which return a O( 1 T )-approximate solution after T iterations. The first algorithm isâ€¦ (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)

- Elad Hazan
- LATIN
- 2008

We propose an algorithm for approximately maximizing a concave function over the bounded semi-definite cone, which produces sparse solutions. Sparsity for SDP corresponds to low rank matrices, and isâ€¦ (More)

- Elad Hazan
- 2011

A well studied and general setting for prediction and decision making is regret minimization in games. Recently the design of algorithms in this setting has been influenced by tools from convexâ€¦ (More)

- Amit Agarwal, Elad Hazan, Satyen Kale, Robert E. Schapire
- ICML
- 2006

We experimentally study on-line investment algorithms first proposed by Agarwal and Hazan and extended by Hazan et al. which achieve almost the same wealth as the best constant-rebalanced portfolioâ€¦ (More)