Hilal Asi

I am a PhD student at Stanford University, advised by John Duchi. Previously, I obtained a B.Sc. and M.Sc. from the department of computer science at the Technion, where I was advised by Eitan Yaakobi.

My current research interests lie in the span of optimization, learning theory, and more recently differential privacy.

Email: (last name) @ stanford.edu

Preprints

• Private Stochastic Convex Optimization: Optimal Rates in L1 Geometry
  with Vitaly Feldman, Tomer Koren, Kunal Talwar. [pdf]
• Near Instance-Optimality in Differential Privacy
  with John Duchi. [pdf]
• Element Level Differential Privacy
  with John Duchi, Omid Javidbakht. [pdf]
• Finding Planted Cliques in Sublinear Time
  with Jay Mardia, Kabir Aladin Chandrasekher. [pdf]

Conference publications

• Instance-optimality in differential privacy via approximate inverse sensitivity mechanisms
  with John Duchi.
  NeurIPS, 2020. [pdf]
• Minibatch Stochastic Approximate Proximal Point Methods
  with Karan Chadha, Gary Cheng, John Duchi.
  NeurIPS, 2020. [pdf]
• Modeling simple structures and geometry for better stochastic optimization algorithms
  with John Duchi.
  Artificial Intelligence and Statistics (AISTATS), 2019. [pdf]
• Nearly Optimal Constructions of PIR and Batch Codes
  with Eitan Yaakobi.
  International Symposium on Information Theory (ISIT), 2017. [pdf]

Journal publications

• The importance of better models in stochastic optimization
  with John Duchi.
  Proceedings of the National Academy of Sciences, 2019. [pdf] [code]
• Stochastic (Approximate) Proximal Point Methods: Convergence, Optimality, and Adaptivity
  with John Duchi.
  SIAM Journal on Optimization, 2019. [pdf]
• Nearly Optimal Constructions of PIR and Batch Codes
  with Eitan Yaakobi.
  IEEE Transactions on Information Theory, 2019. [pdf]