PhD Defense of Ahmet Alacaoglu
PhD defense of A. Alacaoglu © V. Cevher/ 2021 EPFL
On 25th August 2021, Ahmet Alacaoglu, a PhD student at LIONS lab, successfully defended his PhD thesis. The thesis, entitled "Adaptation in Stochastic Algorithms: From Nonsmooth Optimization to Min-Max Problems and Beyond" was supervised by Prof. Volkan Cevher.
ABSTRACT
Stochastic gradient descent (SGD) and randomized coordinate descent (RCD) are two of the workhorses for training modern automated decision systems. Intriguingly, convergence properties of these methods are not well-established as we move away from the specific case of smooth minimization. In this dissertation, we focus on related problems of nonsmooth optimization and min-max optimization to improve the theoretical understanding of stochastic algorithms, with applications from machine learning and reinforcement learning.