I am an Assistant Professor at the EE Department of the Technion


My research is in Machine Learning and Optimization. I am focused on the design and analysis of efficient algorithms for a wide class of Machine Learning and decision making scenarios.

Short bio:

I did my post-doc at the Institute for Machine Learning at ETHZ working with Prof. Andreas Krause.  Previously, I did my PhD at the IE&M Department of the Technion, working under the guidance of Prof. Elad HazanBefore that, I completed my master's at the EE Department of the Technion under the guidance of Prof. Nahum Shimkin.

Office: Fishbach, 459     Contact: kfirylevy@technion.ac.il


Conference Publications

Projection Free Online Learning over Smooth Sets

    Kfir Y. Levy and Andreas Krause. 

    In AISTATS 2019. [pdf]


Online Adaptive Methods, Universality and Acceleration 

    Kfir Y. Levy, Alp Yurtsever, and Volkan Cevher. 

    In NeurIPS 2018. [pdf[arXiv


Online Variance Reduction for Stochastic Optimization

    Zalán BorsosAndreas Krause, and Kfir Y. Levy.

    In COLT 2018. [pdf] [arXiv] [Code]


Faster Rates for Convex-Concave Games

    Jacob AbernethyKevin A. LaiKfir Y. Levy, and Jun-Kun Wang.

    In COLT 2018. [pdf] [arXiv] 


An Online Learning Approach to Generative Adversarial Networks

    Paulina GrnarovaKfir Y. LevyAurelien LucchiThomas Hofmann,  and Andreas Krause.

    In ICLR 2018. [pdf][arXiv


Online to Offline Conversions, Universality and Adaptive Minibatch Sizes

    Kfir Y. Levy.

    In NIPS 2017. [pdf][arXiv


Continuous DR-submodular Maximization: Structure and Algorithms

    An BianKfir Y. LevyAndreas Krause, and Joachim M. Buhmann.

    In NIPS 2017. [pdf[arXiv


k*-Nearest Neighbors: From Global to Local

    Oren Anava and Kfir Y. Levy.

    In NIPS 2016. [pdf[arXiv] [Code]


On Graduated Optimization for Stochastic Non-Convex Problems

    Elad Hazan, Kfir Y. Levy, and Shai Shalev-Shwartz.

    In ICML 2016. [pdf[arXiv][Code]


Beyond Convexity: Stochastic Quasi-Convex Optimization

    Elad Hazan, Kfir Y. Levy, and Shai Shalev-Shwartz.

    In NIPS 2015. [pdf[arXiv]

Unsupervised Imitation Learning

    Sebastian Curi, Kfir Y. Levy, and Andreas Krause.

    To appear in CDC 2019. [arXiv] 


A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise

    Francis Bach and Kfir Y. Levy. 

     In COLT 2019. [arXiv


Online Variance Reduction with Mixtures

    Zalán BorsosSebastian Curi, Kfir Y. Levy, and Andreas Krause.

    In ICML 2019. [pdf] 


UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization 

    Ali Kavis, Kfir Y. Levy, Francis Bach, and Volkan Cevher. 

    To appear In NeurIPS 2019.  


Fast Rates for Exp-concave Empirical Risk Minimization

    Tomer Koren and Kfir Y. Levy.

    In NIPS 2015. [pdf]

Bandit Convex Optimization: Towards Tight Bounds

    Elad Hazan and Kfir Y. Levy.

    In NIPS 2014. [pdf] [Full Version]

Logistic Regression: Tight Bounds for Stochastic and Online Optimization

    Elad Hazan, Tomer Koren and Kfir Y. Levy.

    In COLT 2014. [pdf] [arXiv]

Unified Inter and Intra Options Learning Using Policy Gradient Methods

    Kfir Y. Levy and Nahum Shimkin.

    In EWRL 2011. [pdf]


Multi-Player Bandits: The Adversarial Case

    Pragnya Alatur, Kfir Y. Levy and Andreas Krause.



Faster Evasion of Saddle Points.

     Kfir Y. Levy.