The Probabilitas Seminar series focuses on high-dimensional problems that combine statistics, probability, artificial intelligence, information theory, computer science, and other related fields. The upcoming seminar takes place on Tuesday, October 28, at 1:30pm in Science Center 705. This week's speaker will be Sadhika Malladi of Microsoft Research NYC.
Mathematical Views on Modern Deep Learning Optimization
This talk focuses on how rigorous mathematical tools can be used to describe the optimization of large, highly non-convex neural networks. We start by covering how stochastic differential equations (SDEs) provide a rigorous yet flexible model of how deep networks change over the course of training. We then cover how the SDEs yield practical insights into scaling training to highly distributed settings while preserving generalization performance. In the second half of the talk, we will explore the new deep learning paradigm of pre-training and fine-tuning large language models. We show that fine-tuning can be described by a very simplistic mathematical model, and insights allow us to develop a highly efficient and performant optimizer to fine-tune LLMs at scale. The talk will focus on various mathematical tools and the extent to which they can describe modern day deep learning.
Sadhika Malladi is a postdoctoral researcher at Microsoft Research NYC. In Fall 2026, she will join UCSD as a tenure-track assistant professor in Computer Science. She completed her PhD in Computer Science at Princeton University advised by Sanjeev Arora. Her research advances deep learning theory to capture modern-day training settings, yielding practical training improvements and meaningful insights into model behavior.
LOCATION:Science Center 705 STATUS:CONFIRMED DTSTART:20251118T183000Z DTEND:20251118T193000Z END:VEVENT END:VCALENDAR