Explore mathematical theorems on agreement and learning in networks through this 23-minute conference talk presented by Elchanan Mossel from the Massachusetts Institute of Technology. Delivered at the Mathematics of Collective Intelligence Workshop hosted by the Institute for Pure & Applied Mathematics (IPAM) at UCLA on February 16, 2022, gain insights into the intersection of mathematics and network dynamics. Delve into the complexities of collective intelligence and discover how mathematical principles can be applied to understand agreement formation and learning processes within networked systems.
Some Mathematical Theorems on Agreement and Learning in Networks - IPAM at UCLA
Institute for Pure & Applied Mathematics (IPAM) via YouTube
Overview
Syllabus
Elchanan Mossel - Some mathematical theorems on agreement and learning in networks - IPAM at UCLA
Taught by
Institute for Pure & Applied Mathematics (IPAM)
Related Courses
-
Learning to Explore with Scalable Supervision - IPAM at UCLA
-
Learning from Dynamics in Linear Dynamical Systems
-
Introduction to Equivariant Machine Learning - IPAM at UCLA
-
Machine Learning for MIP Solving - IPAM at UCLA
-
A Perceptron Trio - Computational vs Statistical Gaps in Learning and Optimization
-
On the Hardness of Learning Under Symmetries
