Learning by Local Entropy Maximization

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=_QZmnQKjzaE


Duration: 47:53
3,061 views
39

Riccardo Zecchina, Politecnico di Torino
Random Instances and Phase Transitions
https://simons.berkeley.edu/talks/riccardo-zecchina-2016-05-03



Other Videos By Simons Institute for the Theory of Computing


2016-06-28Algorithms for Risk Mitigation in Networks
2016-06-28What Does `Real Time' Mean
2016-06-28The Palomar Transient Factory
2016-06-28Market Dynamics of Best-Response with Lookahead
2016-06-27Crowdsourcing for Clustering: Algorithms and Information-Theoretic Lower Bounds
2016-06-27Local Computation Algorithms
2016-06-27Coding for Interactive Communication
2016-06-27Real-Time Convex Optimization
2016-06-27Warning When You Need It: Earthquakes and Smartphones
2016-06-27Physics at the LHC: Data Analysis and Global Network Challenges with Exascale Data
2016-05-10Learning by Local Entropy Maximization
2016-05-09The Large Deviations of the Whitening Process in Random Constraint Satisfaction Problems
2016-05-09Teaching an old code a new trick
2016-05-06Sum of Squares SDP Relaxations on Random Tensors
2016-05-06Counting Solutions to Random Constraint Satisfaction Problems
2016-05-06Phase Transitions in Random CSPs
2016-05-06A Framework for Imperfectly Observed Networks
2016-05-06Phase Transitions in Low-Rank Matrix Estimation
2016-05-06Analysis of Algorithms on Dense Matrices using Approximate Message Passing
2016-05-06Extremal Cuts of Sparse Random Graphs
2016-05-06Recent Advances in Counting Sparse Graphs


Tags:
Simons Institute
UC Berkeley
computer science
theory of computing
Counting Complexity and Phase Transitions
Riccardo Zecchina