Optimization and learning are deeply intertwined in modern data science and intelligent systems. Optimization provides the tools for training models, fitting structured representations, and making decisions under uncertainty, while learning brings large-scale, stochastic, nonconvex, and often distributed challenges. As models grow and deployments become more complex, progress hinges on integrating insights from optimization theory, statistical learning, and system design. This workshop brings together researchers and practitioners to discuss recent advances at the intersection of learning and optimization, spanning both theoretical foundations and emerging applications.
| Time | Session |
|---|---|
| 09:00-09:15 | Opening Ceremony |
| 09:15-10:00 |
Gradient Networks: Why Learn the Function When You Only
Need the Vector?
Speaker: José M. F. Moura
|
| 10:00-10:30 | Group Photo and Tea Break |
| 10:30-11:15 |
On the Principles Behind Neural Network Optimizers
Speaker: Zhi-Quan (Tom) Luo
|
| 11:15-12:00 |
Transfer Learning via Shared Latent Geometry with
Applications to Graph Data
Speaker: Anna Scaglione
|
| 12:00-14:00 | Lunch |
| 14:00-14:45 |
Adaptive Networks
Speaker: Ali H. Sayed
|
| 14:45-15:30 |
Recent Research on Few-Bit Massive MIMO and Constant-Modulus Optimization
Speaker: Wing-Kin Ma
|
| 15:30-16:00 | Tea Break |
| 16:00-16:45 |
A Memory Efficient Randomized Subspace Optimization Method for Training Large Language Models
Speaker: Kun Yuan
|
| 17:30-20:00 | Welcome Dinner |
Cornell University/RPI
The Chinese University of Hong Kong, Shenzhen
The Chinese University of Hong Kong
Carnegie Mellon University
Université Côte d’Azur
University of Pennsylvania
École Polytechnique Fédérale de Lausanne
Cornell University
Purdue University
National University of Singapore
George Mason University
Imperial College London
Peking University
Zhejiang University
Peking University
École Polytechnique Fédérale de Lausanne
Peking University
Peking University
Sun Yat-sen University