CAD Seminar Series: Fundamental Convergence Analysis of Sharpness-Aware Minimization

Warning Icon This event is in the past.

When:
September 18, 2024
2:30 p.m. to 3:30 p.m.
Where:
Faculty/Administration
656 W. Kirby (Room #1146)
Detroit, MI 48202
Zoom Go to virtual location
Event category: Seminar
Hybrid
Speaker: Dat Tran, PhD Student, Department of Mathematics, WSU
 
Time: Wednesday, September 18, from 2:30 to 3:30 pm
 
Location for in-person participants: 1146 FAB 
 
 
Title: Fundamental Convergence Analysis of Sharpness-Aware Minimization
 
Abstract: Sharpness-Aware Minimization (SAM) is a recently proposed gradient-based optimization method (Foret et al., 2021) that significantly improves the generalization of neural networks. This talk presents a unified convergence analysis for the optimizer and its efficient variants. The stationarity of accumulation points, the convergence of the sequence of gradients to the origin, the sequence of function values to the optimal value, and the sequence of iterates to the optimal solution are considered. Numerical experiments are conducted on classification tasks using deep learning models to confirm the practical aspects of the analysis.
 
————————————————————————
 
CAD Seminar Series: Advancing Knowledge, Innovation, and Collaboration in Computation, AI, and Data Science (CAD)
 
The CAD Seminar Series is a dedicated platform for advancing knowledge, fostering innovation, and promoting collaboration across the fields of Computation, Artificial Intelligence, and Data Science. This series brings together leading experts, researchers, and professionals to explore the latest developments, tackle emerging challenges, and drive forward-thinking solutions at the convergence of these critical disciplines.
 
Objectives:
 
• Advance Knowledge: Share cutting-edge research and insights that push the boundaries of what is known in CAD.
• Foster Innovation: Encourage the development of novel ideas and solutions through interdisciplinary dialogue and creative thinking.
• Promote Collaboration: Unite expertise across disciplines and build bridges between academia, industry, and government to address complex problems and create opportunities for joint ventures.
Schedule: The seminars will be held on a weekly basis (unless otherwise noted) throughout the academic year. For Fall 2024, the seminars are tentatively scheduled for Wednesdays from 2:30 PM to 3:30 PM, and will be available both in-person at 1146 FAB and online. Each seminar will spotlight a particular topic, providing an in-depth exploration and fostering lively discussions. 
 
Target Audience: The CAD Seminar Series is designed for a diverse audience, including faculty, researchers, students, and professionals in Computation, AI, Data Science, and related fields. It serves as a forum for exchanging ideas, networking, and contributing to the growth of these rapidly evolving areas. We highly recommend in-person attendance to enhance engagement and networking opportunities with speakers and fellow participants.
 
Call for Participation: We welcome contributions from researchers, practitioners, and students. Whether presenting your work, participating in discussions, or attending as a learner, your involvement is crucial to the success of this collaborative initiative. 
—————————————————————————
 
 
September 2024
SU M TU W TH F SA
1234567
891011121314
15161718192021
22232425262728
293012345