Efficient Algorithms for Outlier-Robust Regression

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=9nHrfWHjAQc


Duration: 41:09
961 views
6

Adam Klivans (University of Texas, Austin)
https://simons.berkeley.edu/talks/efficient-algorithms-outlier-robust-regression
Robust and High-Dimensional Statistics



Other Videos By Simons Institute for the Theory of Computing


2018-10-30A Modern Maximum-Likelihood Theory for High-Dimensional Logistic Regression
2018-10-30TAP Free Energy, Spin Glasses, and Variational Inference
2018-10-30Some Problems of Robust High-dimensional Statistics
2018-10-30Orthogonal Machine Learning: Power and Limitations
2018-10-30Generalization Bounds for Uniformly Stable Algorithms
2018-10-30Invariance, Causality and Novel Robustness
2018-10-30Mixture Models, Robustness, and Sum of Squares Proofs
2018-10-29The Importance of Better Models in Stochastic Optimization...
2018-10-29On Using Graph Distances to Estimate Euclidean and Related Distances
2018-10-29Detecting Weak Signals via Hypothesis Testing
2018-10-29Efficient Algorithms for Outlier-Robust Regression
2018-10-29Computational-Statistical Tradeoffs in Robust High-Dimensional Estimation
2018-10-29Robust List Decoding of Spherical Gaussians
2018-10-24Mathematical Theories of Communication: Old and New
2018-10-18Fully Understanding The Hashing Trick
2018-10-18Distributed Statistical Estimation of Matrix Products with Applications
2018-10-18The Sketching Complexity of Graph and Hypergraph Counting
2018-10-18Optimal Lower Bounds for Distributed and Streaming Spanning Forest Computation
2018-10-18On the Deterministic Complexity of Counting Events in a Stream
2018-10-18Sparse MDS Matrices: Proof of the GM-MDS Conjecture
2018-10-17Tight Cell Probe Bounds for Succinct Boolean Matrix-Vector Multiplication


Tags:
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley
Robust and High-Dimensional Statistics
Adam Klivans