Kfir Y. Levy

• Postdoctoral Fellow
• External Website
• yehuda.levy@inf.ethz.ch
• CAB G 68
• +41 44 633 88 31
• My research interests lie broadly in Machine Learning and Stochastic Optimization. I am particularly interested in designing universal methods that apply to a wide class of learning scenarios, with a focus on problems where non-convex structure arises.

---

Publications

2021

Fast Projection Onto Convex Smooth Constraints I. Usmanova, M. Kamgarpour, A. Krause, K. Levy In Proc. International Conference on Machine Learning (ICML), 2021 [bibtex] [abstract] [pdf]

2020

Adaptive Sampling for Stochastic Risk-Averse Learning S. Curi, K. Y. Levy, S. Jegelka, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2020 [bibtex] [abstract] [pdf] [poster] [code]

Multi-Player Bandits: The Adversarial Case P. Alatur, K. Y. Levy, A. Krause In Journal of Machine Learning Research (JMLR), volume 21, 2020 [bibtex] [abstract] [pdf]

2019

A Domain Agnostic Measure for Monitoring and Evaluating GANs P. Grnarova, K. Y. Levy, A. Lucchi, N. Perraudin, I. Goodfellow, T. Hofmann, A. Krause In Proc. Neural Information Processing Systems (NeurIPS), 2019 [bibtex] [abstract] [pdf]

Online Variance Reduction with Mixtures Z. Borsos, S. Curi, K. Y. Levy, A. Krause In Proc. International Conference on Machine Learning (ICML), 2019 [bibtex] [abstract] [pdf]

Projection Free Online Learning Over Smooth Sets K. Y. Levy, A. Krause In Proc. International Conference on Artificial Intelligence and Statistics (AISTATS), 2019 [bibtex] [abstract] [pdf]

Adaptive Input Estimation in Linear Dynamical Systems with Applications to Learning-from-Observations S. Curi, K. Y. Levy, A. Krause In 2019 IEEE 58th Conference on Decision and Control (CDC), 2019 [bibtex] [abstract] [pdf]

2018

Online Adaptive Methods, Universality and Acceleration K. Y. Levy, A. Yurtsever, V. Cevher In Neural and Information Processing Systems (NeurIPS), 2018 [bibtex] [abstract] [pdf]

Online Variance Reduction for Stochastic Optimization Z. Borsos, A. Krause, K. Y. Levy In Proc. Conference on Learning Theory (COLT), 2018 [bibtex] [abstract] [pdf] [code]

An Online Learning Approach to Generative Adversarial Networks P. Grnarova, K. Y. Levy, A. Lucchi, T. Hofmann, A. Krause In Proc. International Conference on Learning Representations (ICLR), 2018 [bibtex] [abstract] [pdf]

2017

Non-monotone Continuous DR-submodular Maximization: Structure and Algorithms A. Bian, K. Levy, A. Krause, J. M. Buhmann In Neural Information Processing Systems (NeurIPS), 2017 [bibtex] [abstract] [pdf]

Online to Offline Conversions, Universality and Adaptive Minibatch Sizes K. Y. Levy Technical report, arXiv, 2017 [bibtex] [abstract] [pdf]

2016

k*-Nearest Neighbors: From Global to Local O. Anava, K. Y. Levy In Proc. Neural Information Processing Systems (NeurIPS), 2016 [bibtex] [abstract] [pdf] [video]

On graduated optimization for stochastic non-convex problems E. Hazan, K. Y. Levy, S. Shalev-Shwartz In International Conference on Machine Learning, 2016 [bibtex] [abstract]

2015

Beyond convexity: Stochastic quasi-convex optimization E. Hazan, K. Levy, S. Shalev-Shwartz In Advances in Neural Information Processing Systems, 2015 [bibtex] [abstract]

Fast rates for exp-concave empirical risk minimization T. Koren, K. Levy In Advances in Neural Information Processing Systems, 2015 [bibtex] [abstract]

2014

Bandit convex optimization: Towards tight bounds E. Hazan, K. Levy In Advances in Neural Information Processing Systems, 2014 [bibtex] [abstract]

Logistic regression: Tight bounds for stochastic and online optimization E. Hazan, T. Koren, K. Y. Levy In Conference on Learning Theory, 2014 [bibtex] [abstract]

2011

Unified inter and intra options learning using policy gradient methods K. Y. Levy, N. Shimkin In European Workshop on Reinforcement Learning, 2011 [bibtex] [abstract]