Testing and Learning Distributions Under Local Information Constraints

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


Category:
Guide
Duration: 44:30
636 views
7

Clement Canonne (Stanford University)
https://simons.berkeley.edu/talks/testing-and-learning-distributions-under-local-information-constraints
Sublinear Algorithms and Nearest-Neighbor Search



Other Videos By Simons Institute for the Theory of Computing


2018-11-29High Dimensional Robust Sparse Regression
2018-11-28Certified Sub-Linear Lower Bounds for K-Means Clustering
2018-11-28Monte Carlo Approximation Certificates for K-Means Clustering
2018-11-28Sublinear Algorithms for (Delta + 1) Vertex Coloring
2018-11-28An Optimal Space Lower Bound for Approximating MAX-CUT
2018-11-28Labeling a Data Set Using Sublinearly Many Queries
2018-11-28Importance Sampling in High Dimensions via Hashing
2018-11-28Learning-Augmented Sketches for Frequency Estimation
2018-11-27Sublinear Time Local-Access Random Generators
2018-11-27Erasures vs. Errors in Local Decoding and Property Testing
2018-11-27Testing and Learning Distributions Under Local Information Constraints
2018-11-27Universal Sketches
2018-11-27Adaptive Sparse Recovery with Limited Adaptivity
2018-11-26The Limits of Proof
2018-11-07Sketching Big Data
2018-11-02Realizing Robustness
2018-11-02Efficient Profile Maximum Likelihood for Universal Symmetric Property Estimation
2018-11-02k-means and k-medians under Dimension Reduction
2018-11-02Scale Calibration for High-Dimensional Robust Regression
2018-11-01How Many Directions Determine a Shape: A VC Theory for Modulii Spaces of Shapes
2018-11-01Optimally Weighted PCA for High-Dimensional Heteroscedastic Data


Tags:
Clement Canonne
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley
Sublinear Algorithms and Nearest-Neighbor Search