Kfir Y. Levy
I am an Associate Professor at the ECE 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 Hazan. Before that, I completed my master's at the EE Department of the Technion under the guidance of Prof. Nahum Shimkin.
Office: Zisapel, 621 Contact: kfirylevy@technion.ac.il
Publications
Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning
Ze'ev Zukerman, Bassel Hamoud, Kfir Y. Levy
To appear in ICML, 2025.
Privacy-Preserving Federated Convex Optimization: Balancing Partial Participation and Efficiency via Noise Cancellation
Roie Reshef, Kfir Y. Levy
To appear in ICML, 2025.
Enhancing Parallelism in Decentralized Stochastic Convex Optimization
Ofri Eisen, Ron Dorfman, Kfir Y. Levy
To appear in ICML, 2025.
Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism
Tehila Dahan, Kfir Y. Levy
Global Convergence of Policy Gradient in Average Reward MDPs
Navdeep Kumar, Yashaswini Murthy , Itai Shufaro , Kfir Y Levy , R. Srikant , Shie Mannor In ICLR, 2025. [pdf]
Safety in the Face of Adversity: Achieving Zero Constraint Violation in Online Learning with Slowly
Changing Constraints Convex Optimization
Bassel Hamoud, Ilnura Usmanova, Kfir Y. Levy
SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
Tehila Dahan, Kfir Y. Levy
Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML Training
Tehila Dahan, Kfir Y. Levy
Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
Tehila Dahan, Kfir Y. Levy
In ICML, 2024. [arXiv]
Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers
Ron Dorfman, Naseem Amin Yehya, Kfir Y. Levy
In ICML, 2024. [arXiv]
Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
Uri Gadot, Kaixin Wang, Navdeep Kumar, Kfir Y. Levy, Shie Mannor
In ICML, 2024. [arXiv]
Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems
In ICML, 2024. [pdf]
A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle
Nadav Hallak, Kfir Y. Levy
In ICML, 2024. [pdf]
Efficient Value Iteration for s-rectangular Robust Markov Decision Processes
Navdeep Kumar, Kaixin Wang, Kfir Yehuda Levy, Shie Mannor
In ICML, 2024. [arXiv]
Learning the Uncertainty Set in Robust Markov Decision Process
Navdeep Kumar, Kaixin Wang, Uri Gadot, Kfir Y. Levy, Shie Mannor
In ICLR Tiny Papers Track, 2024. [pdf]
Policy Gradient with Tree Search (PGTS) in Reinforcement Learning Evades Local Maxima
Navdeep Kumar, Priyank Agrawal, Kfir Y. Levy, Shie Mannor
In ICLR Tiny Papers Track, 2024. [pdf]
Towards Faster Global Convergence of Robust Policy Gradient Methods
Navdeep Kumar, Ilnura Usmanova, Kfir Yehuda Levy, Shie Mannor
In ICLR Tiny Papers Track, 2024. [pdf]
Policy Gradient for Reinforcement Learning with General Utilities
Navdeep Kumar, Kaixin Wang, Utkarsh Pratiush, Kfir Y. Levy, Shie Mannor
In ICLR Tiny Papers Track, 2024. [pdf]
Solving Non-rectangular Reward-robust MDPs via Frequency Regularization
Uri Gadot, Esther Derman, Navdeep Kumar, Maxence Mohamed Elfatihi, Kfir Levy, Shie Mannor
In AAAI, 2024. [arXiv]
Policy Gradient for Rectangular Robust Markov Decision Processes
Navdeep Kumar, Esther Derman, Matthieu Geist, Kfir Y. Levy, Shie Mannor
In NeurIPS, 2023. [pdf]
Meta-learning Adversarial Bandit Algorithms
Mikhail Khodak, Ilya Osadchiy, Keegan Harris, Maria-Florina Balcan, Kfir Y. Levy, Ron Meir, Steven Wu
In NeurIPS, 2023. [arXiv]
Dropcompute: Simple and more Robust Distributed Synchronous Training via Compute Variance Reduction
Niv Giladi, Shahar Gottlieb, Moran Shkolnik, Asaf Karnieli, Ron Banner, Elad Hoffer, Kfir Y. Levy, Daniel Soudry
In NeurIPS, 2023. [arXiv]
No-Regret Dynamics in the Fenchel Game: A Unified Framework
for Algorithmic Convex Optimization
Jun-Kun Wang, Jacob Abernethy and Kfir Y. Levy
In Mathematical Programming, 2023. [arXiv]
DocoFL : Downlink Compression for cross-device
Federated Learning
Ron Dorfman, Shay Vargaftik, Yaniv Ben-Itzhak, and Kfir Y. Levy
Robust linear regression for general feature distribution
Tom Norman, Nir Weinberger and Kfir Y. Levy
Explainable artificial intelligence (xai) techniques for energy and power systems: Review, challenges and opportunities.
Ram Machlev, Leena Heistrene, Michael Perl, Kfir Y. Levy, Juri Belikov, Shie Mannor and Yoash Levron
Adapting to Mixing Time in Stochastic Optimization with Markovian Data
Ron Dorfman, and Kfir Y. Levy
In ICML 2022. [pdf][arXiv], Spotlight Presentation
UNDERGRAD: A Universal Black-Box Optimization Method with Almost Dimension-Free Convergence Rate Guarantees
Kimon Antonakopoulos, Dong Quan Vu, Volkan Cevher, Kfir Y. Levy, and Panayotis Mertikopoulos
In ICML 2022. [pdf][arXiv], Spotlight Presentation
High probability bounds for a class of nonconvex algorithms with adagrad stepsize
Kfir Y. Levy, Ali Kavis and Volkan Cevher
Faster Neural Network Training with Approximate Tensor Operations
Menachem Adelman, Kfir Y. Levy, Ido Hakimi and Mark Silberstein
In NeurIPS 2021. [pdf]
STORM+: Fully Adaptive SGD with Momentum for Non-convex Optimization
Kfir Y. Levy, Ali Kavis and Volkan Cevher
In NeurIPS 2021. [pdf][arXiv]
Learning Measuring Explainability and Trustworthiness of Power Quality
Disturbances Classifiers Using XAI - Explainable Artificial Intelligence
Ram Machlev, Michael Perl, Juri Belikov, Kfir Y. Levy and Yoash Levron
In IEEE Transactions on Industrial Informatics 2021. [pdf]
LAGA: Lagged AllReduce with Gradient Accumulation for Minimal Idle Time
Ido Hakimi, Rotem Aviv, Kfir Y. Levy and Assaf Schuster
In ICDM 2021. [pdf]
Learning under Delayed Feedback: Implicitly Adapting to Gradient Delays
Rotem Aviv, Ido Hakimi, Assaf Schuster and Kfir Y. Levy
Fast Projection onto Convex Smooth Constraints
Ilnura Usmanuva, Kfir Y. Levy, Maryam Kamgarpour and Andreas Krause
In ICML 2021. [pdf]
Multi-Player Bandits: The Adversarial Case
Pragnya Alatur, Kfir Y. Levy and Andreas Krause
In JMLR 2020. [arXiv]
Adaptive Sampling for Stochastic Risk-averse Learning
Sebastian Curi, Kfir Y. Levy, Stefanie Jegelka and Andreas Krause.
In NeurIPS 2020. [pdf]
Online Convex Optimization In the Random Order Model
Dan Garber, Gal Korcia and Kfir Y. Levy
In ICML 2020. [pdf]
UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization
Ali Kavis, Kfir Y. Levy, Francis Bach, and Volkan Cevher
In NeurIPS 2019. [arXiv]
Evaluating GANs via Duality
Paulina Grnarova, Kfir Y. Levy, Aurelien Lucchi, Nathanael Perraudin,
Ian Goodfellow, Thomas Hofmann and Andreas Krause
In NeurIPS 2019. [arXiv]
Online Variance Reduction with Mixtures
Zalán Borsos, Sebastian Curi, Kfir Y. Levy, and Andreas Krause
In ICML 2019. [pdf]
A Universal Algorithm for Variational Inequalities Adaptive to Smoothness and Noise
In COLT 2019. [arXiv]
Unsupervised Imitation Learning
Sebastian Curi, Kfir Y. Levy, and Andreas Krause
In CDC 2019. [arXiv]
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 Borsos, Andreas Krause, and Kfir Y. Levy
In COLT 2018. [pdf] [arXiv] [Code]
Faster Rates for Convex-Concave Games
Jacob Abernethy, Kevin A. Lai, Kfir Y. Levy, and Jun-Kun Wang
An Online Learning Approach to Generative Adversarial Networks
Paulina Grnarova, Kfir Y. Levy, Aurelien Lucchi, Thomas Hofmann, and Andreas Krause
Online to Offline Conversions, Universality and Adaptive Minibatch Sizes
Continuous DR-submodular Maximization: Structure and Algorithms
An Bian, Kfir Y. Levy, Andreas Krause, and Joachim M. Buhmann
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]
Faster Evasion of Saddle Points.
Preprint 2016.[arXiv]
Beyond Convexity: Stochastic Quasi-Convex Optimization
Elad Hazan, Kfir Y. Levy, and Shai Shalev-Shwartz
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
Unified Inter and Intra Options Learning Using Policy Gradient Methods
Kfir Y. Levy and Nahum Shimkin
In EWRL 2011. [pdf]