SILO: Invariant Low-Dimensional Subspaces in Gradient Descent for Learning Deep Networks
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinQing Qu, UMich
Loading view.
IFDS is located in the Central and Pacific Time zone. Please note the zone when accessing a particular event.
IFDS Ideas Forum
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinTBD Speaker: Thanasis Pittas
IFDS Ideas Forum
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinTBD Speaker: Sushrut Karmalkar
SILO: Funsearch: a novel approach to using large language models as part of mathematical practice
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinJordan Ellenberg
How do neural networks learn features from data?
CSE (Allen) 403Speaker Bio: Adit is currently the George F. Carrier Postdoctoral Fellow >
SILO: A scalable method to exploit screening in Gaussian process models with noise
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinChris Geoga
Towards a new toolbox of optimal statistical primitives
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinAbstract: Given society's increasing reliance on data, its collection and processing >
SILO: Universality in High-Dimensional Statistics
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinRishabh Dudeja
Policy Optimization with Compatible Mirror Approximation
ZoomSpeaker Bio: Zhihan is a fourth-year PhD student in the >
Theoretical exploration of foundation model adaption methods
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinSpeaker: Kangwook Lee
SILO: Theoretical Exploration of Foundation Model Adaptation Methods
Orchard View Room 330 N. Orchard Street, 3rd Floor NE, Madison, WisconsinKangwook Lee
Offline Multi-task Transfer RL with Representational Penalization
CSE (Allen) 403Speaker Bio: Avinandan is a second year PhD student, advised >