HOT-AI: Horizons for Optimization in AI Workshop

The TILOS Horizons for Optimization in AI ("HOT-AI") Workshop will bring together leading researchers and practitioners to explore the evolving landscape of optimization for AI—and how AI itself is reshaping optimization. Over two days of engaging talks and interactive discussions participants will dive into cutting-edge research, share insights, and exchange ideas on the most pressing challenges and opportunities at the intersection of these fields.

Confirmed Speakers and Panelists

Caltech

University of Washington

University of California, Los Angeles

TILOS (UC San Diego)

The University Texas at Austin

University of California, Berkeley

University of Southern California

Stanford University

Schedule (tentative)

Thursday, April 17, 2025

8:30 - 9:00am Registration and Breakfast
9:00 - 9:10am Opening Remarks
9:10 - 9:55am Keynote Presentation
Aryan Mokhtari, The University of Texas at Austin
10:00 - 10:20am TILOS Faculty Talk
10:20 - 10:45am Break
10:45 - 11:30am Keynote Presentation
John Doyle, Caltech
11:35 - 11:55am TILOS Faculty Talk
12:00 - 1:30pm Lunch
1:30 - 2:15pm Keynote: Hunting the Hessian
Madeleine Udell, Stanford University
2:20 - 2:40pm TILOS Faculty Talk
2:40 - 3:00pm Break
3:00 - 3:45pm Keynote Presentation
Mahdi Soltanolkotabi, University of Southern California
3:50 - 4:10pm TILOS Faculty Talk

Friday, April 18, 2025

8:30 - 9:00am Registration and Breakfast
9:00 - 9:45am Keynote Presentation
Quanquan Gu, University of California, Los Angeles
9:50 - 10:35am Keynote Presentation
Maryam Fazel, University of Washington
10:35 - 11:00am Break
11:00am -12:00pm Panel Discussion
12:00 - 1:30pm Lunch
1:30 - 2:15pm Keynote Presentation
Benjamin Recht, University of California, Berkeley
2:15 - 2:45pm Break
2:45 - 4:00pm Student Lightning Talks

Date & Time

Thursday, April 17 | 8:30am - 4:30pm
[ THURSDAY SCHEDULE ]

Friday, April 18 | 8:30am - 4:00pm
[ FRIDAY SCHEDULE ]

Registration

Registration is complementary but required as space is limited. Register HERE by Friday, April 11, 2025.

Venue

Halıcıoğlu Data Science Institute Room 123
University of California, San Diego
3234 Matthews Lane
La Jolla, CA 92093
[MAP]

Parking

Gilman Parking Structure (252 Russell Ln, La Jolla, CA 92093; 5 minute walk to venue).

Hopkins Parking Structure (9800 Hopkins Dr, La Jolla, CA 92093; 10 minute walk to venue).

Parking fees are payable at pay stations or pay-by-phone. Note that many visitor spots are limited to two hours. Even though the app allows you to pay for longer periods, you will get a ticket after that time if parked in a 2-hour space.

Contacts

Abstracts

Hunting the Hessian

Ill conditioned loss landscapes are ubiquitous in machine learning, and they slow down optimization. Preconditioning the gradient to make the loss more isotropic is a natural solution, but is challenging for extremely large problems, as direct access to the problem Hessian is prohibitively expensive. We present two fresh approaches to preconditioning using tools from randomized numerical linear algebra and online convex optimization for efficient access to Hessian information, motivated by the question: what is the most useful information we can query from the problem Hessian using linear memory and compute?