seminars
-
Reinforcement Learning Algorithm for Learning Shadow Variables in Combinatorial Optimization Problems
Abstract: Many real-world decision-making problems are modeled as Mixed-Integer Linear Optimization (MILO) problems, and are solved by exact tree-search-based optimization algorithms. Some knowledge, such as preferences for the solution, often exists but is not explicitly modeled. We examine incorporating such knowledge as additional constraints to potentially shorten optimization. A wise choice of “equality preferences” (i.e.,… Continue Reading Reinforcement Learning Algorithm for Learning Shadow Variables in Combinatorial Optimization Problems
-
First-Order Methods for Two-Stage Stochastic Optimization
Abstract: The emergence of big data has highlighted the growing importance of data-driven approaches in stochastic optimization. Sample Average Approximation (SAA) is a widely used method, known for its simplicity and compatibility with first-order optimization techniques. However, SAA often exhibits overfitting when the amount of data is limited, and it struggles to obtain feasible solution… Continue Reading First-Order Methods for Two-Stage Stochastic Optimization
-
Deep Learning for approximating solutions to hard computational problems indirectly
Abstract: Computational reduction serves as a powerful tool in optimization by enabling the translation between different computational problems while preserving key structural and computational properties. This allows one problem to be reformulated in terms of another, often facilitating the solution of otherwise complex problems. Since reductions are mostly manual, it is plausible that alternative, better… Continue Reading Deep Learning for approximating solutions to hard computational problems indirectly
-
Computational and Statistical Limits in Modern Machine Learning – Job Talk
Abstract: Modern machine learning systems operate in regimes that challenge classical learning-theoretic assumptions. Models are highly overparameterized, trained with simple optimization algorithms, and rely critically on how data is collected and curated. Understanding the limits of learning in these settings requires revisiting both the computational and statistical foundations of learning theory. A central question in learning… Continue Reading Computational and Statistical Limits in Modern Machine Learning – Job Talk
-
Algorithms for Structured Simple Bilevel Problems
Abstract: Simple convex bilevel optimization problems, in which we seek to minimize an (outer) objective function over a feasible set, which itself is the set of minimizers of another (inner) function. Such problems can be found in the machine learning and signal processing applications. In this work, we address the case where both outer and… Continue Reading Algorithms for Structured Simple Bilevel Problems
-
Blackwell’s Approachability with Approximation Algorithms
Abstract: We revisit Blackwell’s celebrated approachability problem which considers a repeated vector-valued game between a player and an adversary. Motivated by settings in which the action set of the player or adversary (or both) is difficult to optimize over, for instance when it corresponds to the set of all possible solutions to some NP-Hard optimization… Continue Reading Blackwell’s Approachability with Approximation Algorithms
labs
news
people
-
Levin, Asaf
Professor Asaf Levin joined the Technion in 2008. He received his Ph.D. in Operations Research from Tel Aviv University in 2003. From 2003 to 2004 he was a Postdoctoral Fellow at the Minerva Optimization Center, the Technion, then, he joined the Department of Statistics at the Hebrew University of Jerusalem as a lecturer. Prof. Levin… Continue Reading Levin, Asaf
