Bilkent University
Department of Computer Engineering
SEMINAR
Learning under Uncertainty: Adaptive and Robust Optimization for Machine Learning
Dr. Ali Kaviş
University of Texas at Austin
https://alikavis.github.io/
Abstract: An overarching goal in large scale machine learning (ML) is to design fast, robust and adaptive algorithms for training which are self-adjusting to unknown properties of the model and the dataset, as well as variations in the loss landscape.
In this talk, I will investigate shortcomings of classical approaches and explain how data-driven, adaptive mechanisms could help in theory and application. First, I will present a novel framework that could automatically adjust its convergence rate with respect to the curvature of the loss function while simultaneously adapting to the unknown noise levels in the gradients. Second, we will consider the more general non-convex setting and I will explain an adaptive mechanism for controlling the noise in gradient computation for faster optimization.
Finally, I will talk about a simple and resource-efficient adaptive framework for solving min-max problems, involving multi-agent scenarios, which outperforms existing algorithms in runtime.
Biography: Ali Kavis is a postdoctoral fellow in the Department of Electrical and Computer Engineering at the University of Texas at Austin, where he works with Sujay Sanghavi and Aryan Mokhtari. He earned his PhD in Computer and Communication Sciences from École Polytechnique Fédérale de Lausanne (EPFL) in 2023, under the supervision of Volkan Cevher. He received his BSc in Computer Engineering from Bilkent University in 2017.
His research targets the algorithmic foundations of ML, and studies theoretical and practical behavior of adaptive optimization methods for convex and non-convex problems as well as multi-agent and adversarial training problems. He aims to develop robust and efficient algorithms which automatically adapt to the loss landscape, noisy computations and the unknown nature of the data by means of monitoring trajectory-related information on-the-fly.
He is the recipient of Swiss National Science Foundation (SNSF) Postdoc.Mobility grant (CHF 120,000) and Postdoc.Mobility Return grant (CHF 115,000).
DATE: March 25, 2026 Wednesday @ 13:30
Place: EA 409