Elad Hazan
Princeton University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Elad Hazan.
conference on learning theory | 2006
Elad Hazan; Adam Tauman Kalai; Satyen Kale; Amit Agarwal
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, it encounters a sequence of (possibly unrelated) convex cost functions. Zinkevich [Zin03] introduced this framework, which models many natural repeated decision-making problems and generalizes many existing problems such as Prediction from Expert Advice and Cover’s Universal Portfolios. Zinkevich showed that a simple online gradient descent algorithm achieves additive regret
compiler construction | 2006
Elad Hazan; Shmuel Safra; Oded Schwartz
O({\sqrt{T}})
latin american symposium on theoretical informatics | 2008
Elad Hazan
, for an arbitrary sequence of T convex cost functions (of bounded gradients), with respect to the best single decision in hindsight. In this paper, we give algorithms that achieve regret O(log(T)) for an arbitrary sequence of strictly convex functions (with bounded first and second derivatives). This mirrors what has been done for the special cases of prediction from expert advice by Kivinen and Warmuth [KW99], and Universal Portfolios by Cover [Cov91]. We propose several algorithms achieving logarithmic regret, which besides being more general are also much more efficient to implement. The main new ideas give rise to an efficient algorithm based on the Newton method for optimization, a new tool in the field. Our analysis shows a surprising connection to follow-the-leader method, and builds on the recent work of Agarwal and Hazan [AH05]. We also analyze other algorithms, which tie together several different previous approaches including follow-the-leader, exponential weighting, Cover’s algorithm and gradient descent.
foundations of computer science | 2005
Sanjeev Arora; Elad Hazan; Satyen Kale
Abstract.Given a k-uniform hypergraph, the Maximumk -Set Packing problem is to find the maximum disjoint set of edges. We prove that this problem cannot be efficiently approximated to within a factor of
international conference on machine learning | 2006
Amit Agarwal; Elad Hazan; Satyen Kale; Robert E. Schapire
Machine Learning | 2010
Elad Hazan; Satyen Kale
\Omega {\left( {k/\ln k} \right)}
SIAM Journal on Computing | 2011
Elad Hazan; Robert Krauthgamer
international workshop and international workshop on approximation randomization and combinatorial optimization algorithms and techniques | 2006
Sanjeev Arora; Elad Hazan; Satyen Kale
unless P = NP. This improves the previous hardness of approximation factor of
Journal of the ACM | 2012
Kenneth L. Clarkson; Elad Hazan; David P. Woodruff
symposium on the theory of computing | 2017
Naman Agarwal; Zeyuan Allen-Zhu; Brian Bullins; Elad Hazan; Tengyu Ma
k/2^{{O({\sqrt {\ln k} })}}