Year | Month |
2024 | Jan Feb Mar May |
2023 | Jan Feb Mar Apr May Jun Jul Aug Oct Nov Dec |
2022 | Jan Feb Jun Jul Aug Oct Nov Dec |
2021 | Jul Aug Sep Oct Nov |
Title: | Statistical Learning Theory of Stochastic Gradient Methods |
Speaker: | Dr. Yunwen Lei, School of Computer Science, University of Birmingham, UK |
Time/Place: | 15:00:00 - 16:00:00 Zoom, (Meeting ID: 926 4709 5162) |
Abstract: | Stochastic gradient methods have become the workhorse behind many machine learning problems. Despite their success in applications, the theoretical analysis is still not satisfactory. In this talk, I will discuss the learning theory of two representative stochastic gradient methods: stochastic gradient descent and stochastic gradient descent ascent. I will introduce new algorithmic stability concepts to relax the existing restrictive assumptions and to improve the existing learning rates. Our results show new connections between generalization and optimization, which illustrate how a best learning performance can be achieved by early stopping. |
The Department has a distinguished record in teaching and research. A number of faculty members have been recipients of relevant awards.
Learn MoreDr S. Hon recevied the Early Career Award (21/22) from the Research Grants Council.
DetailsFollow HKBU Math