Scholar
Hilal Asi
Google Scholar ID: QGcz9-kAAAAJ
Apple
Citations & Impact
Citations
972
H-index
15
i10-index
18
Publications
20
Co-authors
18
list available
Contact
Publications
Resume (English only)
Academic Achievements
- - Preprints:
- - Private Online Leaning via Lazy Algorithms
- - DP-Dueling: Learning from Preference Feedback without Compromising User Privacy
- - Near Instance-Optimality in Differential Privacy
- - Conference publications:
- - Universally Instance-Optimal Mechanisms for Private Statistical Estimation (COLT, 2024)
- - Private Vector Mean Estimation in the Shuffle Model: Optimal Rates Require Many Messages (ICML, 2024)
- - User-level differentially private stochastic convex optimization: Efficient algorithms with optimal rates (AISTATS, 2024)
- - Faster optimal LDP mean estimation via random projections (NeurIPS, 2023)
- - Near-Optimal Algorithms for Private Online Optimization in the Realizable Regime (ICML, 2023)
- - From Robustness to Privacy and Back (ICML, 2023)
- - Private Online Prediction from Experts: Separations and Faster Rates (COLT, 2023)
- - Optimal Algorithms for Mean Estimation under Local Differential Privacy (ICML, 2022)
- - Private optimization in the interpolation regime: faster rates and hardness results (ICML, 2022)
- - Element Level Differential Privacy (PPAI, 2022)
- - Stochastic Bias-Reduced Gradient Methods (NeurIPS, 2021)
- - Adapting to function difficulty and growth conditions in private optimization (NeurIPS, 2021)
- - Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry (ICML, 2021)
- - Private Adaptive Gradient Methods for Convex Optimization (ICML, 2021)
- - Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms (NeurIPS, 2020)
- - Minibatch Stochastic Approximate Proximal Point Methods (NeurIPS, 2020)
- - Modeling simple structures and geometry for better stochastic optimization algorithms (AISTATS, 2019)
- - Nearly Optimal Constructions of PIR and Batch Codes (ISIT, 2017)
- - Journal publications:
- - The importance of better models in stochastic optimization (Proceedings of the National Academy of Sciences, 2019)
- - Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity (SIAM Journal on Optimization, 2019)
- - Nearly Optimal Constructions of PIR and Batch Codes (IEEE Transactions on Information Theory, 2019)
Research Experience
- - Researcher in the Machine Learning Research (MLR) team at Apple, working primarily on privacy-preserving machine learning
- - During his PhD, he also spent some time at Apple, working with Vitaly Feldman and Kunal Talwar
Education
- - PhD, Stanford University, Advisor: John Duchi
- - M.Sc., Technion, Department of Computer Science, Advisor: Eitan Yaakobi
- - B.Sc., Technion, Department of Computer Science, Advisor: Eitan Yaakobi
Background
- Research interests include privacy-preserving machine learning and its intersection with other fields such as optimization and robustness.
