BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Department of Computer Science - ECPv6.15.20//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Department of Computer Science
X-ORIGINAL-URL:https://www.cs.jhu.edu
X-WR-CALDESC:Events for Department of Computer Science
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20250218T103000
DTEND;TZID=America/New_York:20250218T120000
DTSTAMP:20260430T111328
CREATED:20250204T160507Z
LAST-MODIFIED:20250204T160528Z
UID:1986031-1739874600-1739880000@www.cs.jhu.edu
SUMMARY:CS Seminar Series: Deep Learning Theory in the Age of Generative AI
DESCRIPTION:Refreshments are available starting at 10:30 a.m. The seminar will begin at 10:45 a.m. \nAbstract\nModern deep learning has achieved remarkable results\, but the design of training methodologies largely relies on guess-and-check approaches. Thorough empirical studies of recent massive language models is prohibitively expensive\, underscoring the need for theoretical insights\, but classical machine learning theory struggles to describe modern training paradigms. Sadhika Malladi presents a novel approach to developing prescriptive theoretical results that can directly translate to improved training methodologies for LMs. Her research has yielded actionable improvements in model training across the LM development pipeline; for example\, her theory motivates the design of MeZO\, a fine-tuning algorithm that reduces memory usage by up to 12x and halves the number of GPU hours required. Throughout this talk\, to underscore the prescriptiveness of her theoretical insights\, Malladi will demonstrate the success of these theory-motivated algorithms on novel empirical settings published after the theory. \nSpeaker Biography\nSadhika Malladi is a final-year PhD student 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. She has co-organized multiple workshops\, including Mathematical and Empirical Understanding of Foundation Models at the 2024 International Conference on Learning Representations and Mathematics for Modern Machine Learning at the 2024 Conference on Neural Information Processing Systems. Malladi was recently named a 2025 Siebel Scholar. \nZoom link >>
URL:https://www.cs.jhu.edu/event/cs-seminar-series-deep-learning-theory-in-the-age-of-generative-ai/
LOCATION:228 Malone Hall
CATEGORIES:Seminars and Lectures
END:VEVENT
END:VCALENDAR