Nadav Hallak
Assistant Professor
The Faculty of Data and Decision Sciences
The Technion

Contact:

Nadav Hallak,
Assistant Professor
The Faculty of Data and Decision Sciences, The Technion
Office: Bloomfield Building, room 508
Phone: +972-77-887-4415
E-mail: ndvhllk@technion.ac.il

Research Interests:

• Continuous Optimization: Theory and Algorithms

• First and Second Order Methods

• Nonconvex Optimization

• Sparse Optimization: Theory and Algorithms

• Applications in Machine Learning, Engineering, Finance and Science

News (June 2024):

• ICML2024: Will present my joint work with Kfir Levy on A Study of First-Order Methods with a Deterministic Relative-Error Gradient Oracle in ICML2024 held in Vienna, Austria

• EurOPT2024: Will present my joint work with Amir Beck on The Regularized Feasible Directions Method for Nonconvex Optimization in EurOPT2024 held in Lund, Sweden

• ML Seminar at Tel-Aviv University: Will give a talk on  first-order methods in sparse optimization on June 19 at the Machine Learning Seminar at Tel Aviv University, thanks to Tomer Koren for inviting me

• ML and Statistics Seminar at Weizmann: Talked about first-order methods in sparse optimization at the ML and Statistics Seminar at Weizmann, thanks to Boaz Nadler and Ohad Shamir for inviting me

--------------------------------------------------------------------------------------------------------------------------

• Research Projects for undergrads:

• Investigation of online nonconvex optimization algorithms in market / game-theory applications

• Investigation of optimization methods with relative-error gradient (compressed gradient, zero-order gradient approximation, gradient quantization)

--------------------------------------------------------------------------------------------------------------------------

• Msc positions available

• Postdoc position available