UBC Math Colloquium:Frederic Koehler

  • Date: 01/27/2023
  • Time: 15:00
Lecturer(s):
Frederic Koehler
Location: 

University of British Columbia

Topic: 

Towards the Statistically Principled Design of ML Algorithms

Description: 

What are the optimal algorithms for learning from data? Have we found them already, or are better ones out there to be discovered? Making these questions precise, and answering them, requires taking on the mathematically deep interplay between statistical and computational constraints. It also requires reconciling our theoretical toolbox with surprising new phenomena arising from practice, which seem to violate conventional rules of thumb regarding algorithm and model design. I will discuss progress along these lines: in terms of designing new algorithms for basic learning problems, controlling generalization in large statistical models, and understanding key statistical questions for generative modeling.

Other Information: 

Colloquium time: 3:00pm

Location: ESB 2012 

 

 

A reception will be held before the Colloquium: Tea/coffee and light snacks

Date/time: Friday, January 27, 2:15pm

Location: PIMS lounge ESB 4133