PPaperPicks

Kfir Yehuda Levy

Technion, Haifa, Faculty of Industrial Engineering and Management

24 papers at tracked venues · 23 at CORE A* · active 2024–2025

DBLP profile ↗ORCID search ↗Homepage ↗

Venues

ICML ×9NeurIPS ×7ICLR ×6AAAI ×1AISTATS ×1

Frequent coauthors

Navdeep Kumar
DBLP profile ↗ORCID search ↗
×8
Tehila Dahan
DBLP profile ↗ORCID search ↗
×4
Roie Reshef
DBLP profile ↗ORCID search ↗
×2
Uri Gadot
DBLP profile ↗ORCID search ↗
×2
Ze'ev Zukerman
DBLP profile ↗ORCID search ↗
×1
Ofir Gaash
DBLP profile ↗ORCID search ↗
×1
Ofri Eisen
DBLP profile ↗ORCID search ↗
×1
Yuheng Zhao
DBLP profile ↗ORCID search ↗
×1
Noa Shoham
DBLP profile ↗ORCID search ↗
×1
Bassel Hamoud
DBLP profile ↗ORCID search ↗
×1
Nadav Hallak
DBLP profile ↗ORCID search ↗
×1
Ron Dorfman
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Beyond Communication Overhead: A Multilevel Monte Carlo Approach for Mitigating Compression Bias in Distributed Learning
    ICML 2025 ·
    Ze'ev Zukerman
    DBLP profile ↗ORCID search ↗
  2. Convergence of Clipped SGD on Convex (L0, L1)-Smooth Functions
    NeurIPS 2025 ·
    Ofir Gaash
    DBLP profile ↗ORCID search ↗
  3. Do Stochastic, Feel Noiseless: Stable Stochastic Optimization via a Double Momentum Mechanism
    ICLR 2025 ·
    Tehila Dahan
    DBLP profile ↗ORCID search ↗
  4. Enhancing Parallelism in Decentralized Stochastic Convex Optimization
    ICML 2025 ·
    Ofri Eisen
    DBLP profile ↗ORCID search ↗
  5. Global Convergence of Policy Gradient in Average Reward MDPs
    ICLR 2025 ·
    Navdeep Kumar
    DBLP profile ↗ORCID search ↗
  6. Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness
    NeurIPS 2025 ·
    Yuheng Zhao
    DBLP profile ↗ORCID search ↗
  7. Non-rectangular Robust MDPs with Normed Uncertainty Sets
    NeurIPS 2025 ·
    Navdeep Kumar
    DBLP profile ↗ORCID search ↗
  8. On the Convergence of Single-Timescale Actor-Critic
    NeurIPS 2025 ·
    Navdeep Kumar
    DBLP profile ↗ORCID search ↗
  9. Prediction-Powered Semi-Supervised Learning with Online Power Tuning
    NeurIPS 2025 ·
    Noa Shoham
    DBLP profile ↗ORCID search ↗
  10. Privacy-Preserving Federated Convex Optimization: Balancing Partial-Participation and Efficiency via Noise Cancellation
    ICML 2025 ·
    Roie Reshef
    DBLP profile ↗ORCID search ↗
  11. Safety in the Face of Adversity: Achieving Zero Constraint Violation in Online Learning with Slowly Changing Constraints
    AISTATS 2025 ·
    Bassel Hamoud
    DBLP profile ↗ORCID search ↗
  12. A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle
    ICML 2024 ·
    Nadav Hallak
    DBLP profile ↗ORCID search ↗
  13. Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
    ICML 2024 ·
    Uri Gadot
    DBLP profile ↗ORCID search ↗
  14. Dynamic Byzantine-Robust Learning: Adapting to Switching Byzantine Workers
    ICML 2024 ·
    Ron Dorfman
    DBLP profile ↗ORCID search ↗
  15. Efficient Value Iteration for s-rectangular Robust Markov Decision Processes
    ICML 2024 ·
    Navdeep Kumar
    DBLP profile ↗ORCID search ↗
  16. Fault Tolerant ML: Efficient Meta-Aggregation and Synchronous Training
    ICML 2024 ·
    Tehila Dahan
    DBLP profile ↗ORCID search ↗
  17. Learning the Uncertainty Set in Robust Markov Decision Process
    ICLR 2024 ·
    Navdeep Kumar
    DBLP profile ↗ORCID search ↗
  18. Policy Gradient for Reinforcement Learning with General Utilities
    ICLR 2024 ·
    Navdeep Kumar
    DBLP profile ↗ORCID search ↗
  19. Policy Gradient with Tree Search (PGTS) in Reinforcement Learning Evades Local Maxima
    ICLR 2024 ·
    Navdeep Kumar
    DBLP profile ↗ORCID search ↗
  20. Private and Federated Stochastic Convex Optimization: Efficient Strategies for Centralized Systems
    ICML 2024 ·
    Roie Reshef
    DBLP profile ↗ORCID search ↗
  21. SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
    NeurIPS 2024 ·
    Tehila Dahan
    DBLP profile ↗ORCID search ↗
  22. Solving Non-rectangular Reward-Robust MDPs via Frequency Regularization
    AAAI 2024 ·
    Uri Gadot
    DBLP profile ↗ORCID search ↗
  23. Towards Faster Global Convergence of Robust Policy Gradient Methods
    ICLR 2024 ·
    Navdeep Kumar
    DBLP profile ↗ORCID search ↗
  24. Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML
    NeurIPS 2024 ·
    Tehila Dahan
    DBLP profile ↗ORCID search ↗