Learning Sparse Data with Near-optimal Speed and Efficiency from a Variety of Measurement Processes

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=8cFF0oQcuEQ


Duration: 25:30
265 views
3

Sidharth Jaggi, Chinese University of Hong Kong
Information Theory, Learning and Big Data
http://simons.berkeley.edu/talks/sidharth-jaggi-2015-03-20



Other Videos By Simons Institute for the Theory of Computing


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?
2015-03-25Analytic Pattern Matching: From DNA to Twitter
2015-03-25Learning and Testing Structured Distributions
2015-03-25Statistical Property Testing and Estimation Beyond the i.i.d. Setting
2015-03-25Computation-Statistics Tradeoffs in Unsupervised Learning via Data Summarization
2015-03-25On Learning Distributions from their Samples
2015-03-25Confidence-Based Active Learning
2015-03-25Learning Sparse Data with Near-optimal Speed and Efficiency from a Variety of Measurement Processes
2015-03-25Lucky Talk: From Coding to Clustering
2015-03-25Testing Distribution Families
2015-03-25Robust Inference and Local Algorithms
2015-03-18Deciphering the Good-Turing Enigma: Estimating Probabilities of Unlikely and Unseen Events
2015-02-24Symmetric Product Codes
2015-02-19Non-malleable Codes Against Constant Split-state Tampering
2015-02-19Reed-Muller and Other Subcodes of the Sierpinski Matrix
2015-02-19New Problems in Coding Theory with Applications to Modern Data Storage and Memories
2015-02-19Polar Codes over q-ary Alphabets and Polynomially Fast Convergence to Shannon Capacity
2015-02-19A Student's View of Locally Repairable Codes


Tags:
Simons Institute
UC Berkeley
computer science
theory of computing
Information Theory
Sidharth Jaggi