Efficient Minimax Optimal Strategies for Universal Prediction

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=8fWYT5MBWm8


Duration: 28:34
517 views
5

Peter Bartlett, UC Berkeley
Information Theory, Learning and Big Data
http://simons.berkeley.edu/talks/peter-bartlett-2015-03-17



Other Videos By Simons Institute for the Theory of Computing


2015-03-25Adaptive Coding over Countable Alphabets
2015-03-25Fundamental Limit of Community Detection in Stochastic Block Models
2015-03-25Constrained Rank Aggregation and Correlation Clustering
2015-03-25Sample Complexity of Estimating Entropy
2015-03-25Machine Learning from Human Comparative Judgments
2015-03-25Minimum Rényi Correlation Principle: From Marginals to Joint Distribution
2015-03-25Near-Optimal Hypothesis Testing via Convex Optimization
2015-03-25Sketching for M-Estimators: A Unified Approach to Robust Regression
2015-03-25Data Driven Convergence in Statistical Estimators
2015-03-25Learning a Hidden Basis through Imperfect Measurements: Why and How
2015-03-25Efficient Minimax Optimal Strategies for Universal Prediction
2015-03-25Information Measure Estimation and Applications: Boosting the Sample Size from n to n log n
2015-03-25Nearest Neighbor Based Greedy Coordinate Descent
2015-03-25Tradeoffs in Large Scale Learning: Statistical Accuracy vs. Numerical Precision
2015-03-25Spy vs Spy: Anonymous Messaging
2015-03-25Must One Learn the Channel to Communicate at Capacity?
2015-03-25Low Regret Recommendations and Item-Item Collaborative Filtering
2015-03-25Topic Modeling Approach for Rank Aggregation
2015-03-25Sample Starved Correlation Mining
2015-03-25Chebyshev Polynomials, Moment Matching and Optimal Estimation of the Unseen
2015-03-25How Large is the Norm of a Random Matrix?


Tags:
Simons Institute
UC Berkeley
computer science
theory of computing
Information Theory
Peter Bartlett