Seminars: Data Science and Machine Learning
Date
Time
Venue
Time
Venue
Speaker
Affiliation
Title of Talk
Affiliation
Title of Talk
30 Jul 2024
15:00
S17 #04-05 (SR2)
15:00
S17 #04-05 (SR2)
19 Jun 2024
14:00
S17 #04-04 (SR3)
14:00
S17 #04-04 (SR3)
Yuan Yancheng
Hong Kong Polytechnic University
Some recent progress on convex clustering: Feature representation learning, dimension reduction, and a GPU solver
Hong Kong Polytechnic University
Some recent progress on convex clustering: Feature representation learning, dimension reduction, and a GPU solver
18 Jun 2024
16:00
S17 #04-05 (SR2)
16:00
S17 #04-05 (SR2)
Weng Kee Wong
University of California at Los Angeles
Optimal Experimental designs and Metaheuristics
University of California at Los Angeles
Optimal Experimental designs and Metaheuristics
29 May 2024
16:00
S17 #04-05 (SR2)
16:00
S17 #04-05 (SR2)
Renbo Zhao
University of Iowa
Frank-Wolfe-Type Methods for Minimizing Log-Homogenous Self-Concordant Barriers
University of Iowa
Frank-Wolfe-Type Methods for Minimizing Log-Homogenous Self-Concordant Barriers
06 Mar 2024
15:40
S17 #05-12 (SR4)
15:40
S17 #05-12 (SR4)
Pierre-Louis Poirion
University of Tokyo
Random subspace Newton method for unconstrained non-convex optimization
University of Tokyo
Random subspace Newton method for unconstrained non-convex optimization
06 Mar 2024
15:00
S17 #05-12 (SR4)
15:00
S17 #05-12 (SR4)
Akiko Takeda
University of Tokyo
Random subspace optimization methods for large-scale optimization problems
University of Tokyo
Random subspace optimization methods for large-scale optimization problems
28 Feb 2024
15:00
S17 #04-05 (SR2)
15:00
S17 #04-05 (SR2)
Jiequn Han
Flatiron Institute, USA
Enjoy the Best of Both Worlds: A Neural-Network Warm-Start Approach for PDE Problems
Flatiron Institute, USA
Enjoy the Best of Both Worlds: A Neural-Network Warm-Start Approach for PDE Problems
20 Feb 2024
15:00
S17 #04-06 (SR1)
15:00
S17 #04-06 (SR1)
Yin Zhang
Chinese University of Hong Kong, Shenzhen
Why “classic” Transformers are shallow and how to make them go deep
Chinese University of Hong Kong, Shenzhen
Why “classic” Transformers are shallow and how to make them go deep
11 Jan 2024
16:00
S17 #05-12 (SR4)
16:00
S17 #05-12 (SR4)