A Talk on ‘A Dynamical View on Optimization Algorithms’ by Dr. Mayank Baranwal

ABOUT THE TALK
Optimization algorithms are the driving force behind many machine-learning formulations, and the recent progress in this field has been greatly aided by a better understanding of these algorithms and their implementation for specific machine-learning problems. The study of gradient flow and its connection to dynamical systems has a long history in mathematics, and this talk aims to further explore this relationship from a continuous-time, variational perspective. We hope to show the relevance of a large class of gradient, projected-gradient and proximal algorithms for optimization problems that not only converge, but do so quickly. In particular, we introduce a generalized framework for designing accelerated optimization algorithms based on the recent advances in fixed-time stability theory of continuous-time dynamical systems. This framework allows for the strongest possible convergence guarantees, and easily extends to a subclass of non-convex functions. This talk is part of a larger effort to connect the fields of dynamical systems and optimization, and to advance our understanding of the underlying mathematical principles.

ABOUT THE SPEAKER
Mayank Baranwal is a Senior Scientist with the Tata Consultancy Services (TCS) research division in Mumbai. He also holds an Adjunct appointment with the Systems and Control group at the Indian Institute of Technology, Bombay (IITB), and a Guest appointment with the Indian Institute of Management, Mumbai (IIM-Mumbai). Before joining TCS, he was a postdoctoral scholar in the Department of Electrical and Computer Engineering at the University of Michigan, Ann Arbor. He received his Bachelor in Mechanical Engineering in 2011 from the Indian Institute of Technology, Kanpur (IITK), an MS in Mechanical Science and Engineering in 2014, an MS in Mathematics in 2015, and PhD in Mechanical Science and Engineering in 2018, all from the University of Illinois at Urbana-Champaign (UIUC). His research interests are modeling, optimization, control, and inference in network systems with applications to distributed optimization, supply-chain networks, power networks, control of microgrids, bioinformatics, computational biology, and deep learning theory. Mayank is a recipient of the Institute Silver Medal in 2011 (IIT Kanpur), the ME Outstanding Publication Award in 2017 (the University of Illinois), the Young Scientist Award in 2022 (Tata Consultancy Services), the Gold Award for Best Smart Technology in Electricity Transmission in 2023 (India Smart Grid Forum), the AV Luminary Award for Top 10 AI Community Contributors in 2024 (Analytics Vidhya), and the AI Research Award in 2024 (Nasscom AI).

Click to Attend