Learning Some Ill-Conditioned Gaussian Graphical Models

Learning Some Ill-Conditioned Gaussian Graphical Models

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=qj1QnlqWD2M


Duration: 52:46
413 views
7

Raghu Meka (UCLA)
https://simons.berkeley.edu/talks/learning-some-ill-conditioned-gaussian-graphical-models
Learning and Testing in High Dimensions



Other Videos By Simons Institute for the Theory of Computing


2021-01-08Crypto and Privacy
2021-01-08Matchings
2021-01-08Introductory Remarks
2020-12-28David Harold Blackwell Summer Research Institute | Interview with Jelani Nelson
2020-12-19Recent Developments in Supervised Learning With Noise
2020-12-19Testing and Reconstruction via Decision Trees
2020-12-18An Equivalence Between Private Classification and Online Prediction
2020-12-18Small Covers for Near-Zero Sets of Polynomials and Learning Latent Variable Models
2020-12-18Hardness of Identity Testing for Potts models and RBMs
2020-12-18Near-Optimal Learning of Tree-Structured Distributions by Chow-Liu
2020-12-17Learning Some Ill-Conditioned Gaussian Graphical Models
2020-12-17Directed Graphical Models for Extreme Value Statistics
2020-12-17Learning Deep ReLU Networks is Fixed-Parameter Tractable
2020-12-17The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks in High Dimension
2020-12-16Analyzing Optimization and Generalization in Deep Learning via Dynamics of Gradient Descent
2020-12-16SGD Learns One-Layer Networks in WGANs
2020-12-16Recent Progress in Algorithmic Robust Statistics via the Sum-of-Squares Method
2020-12-16Phase Transitions for Detecting Latent Geometry in Random Graphs
2020-12-16Low-Degree Hardness of Random Optimization Problems
2020-12-15Counting and Sampling Subgraphs in Sublinear Time
2020-12-15Learning and Testing for Gradient Descent


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Learning and Testing in High Dimensions
Raghu Meka