Computational Barriers in Statistical Estimation and Learning

Computational Barriers in Statistical Estimation and Learning

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=1Ei0BP1Hz-o


Duration: 1:02:50
2,320 views
46

Andrea Montanari (Stanford)
https://simons.berkeley.edu/events/rmklectures2021-fall-2#
Richard M. Karp Distinguished Lecture



Other Videos By Simons Institute for the Theory of Computing


2021-10-13Panel on Securing Cryptography Against Quantum Adversaries | Quantum Colloquium
2021-10-13Post-Quantum Succinct Arguments: Breaking the Quantum Rewinding Barrier | Quantum Colloquium
2021-10-13Causal Matrix Estimation
2021-10-12Tractability And Overparametrization In Some Simple Models
2021-10-12Correlated Stochastic Block Models: Graph Matching And Community Recovery
2021-10-11Random Combinatorial Matrices
2021-10-11Statistical Estimation from Dependent Data
2021-10-07Locally Testable Codes with Constant Rate, Distance, and Locality
2021-10-06Panel on Quantum Interactive Dynamics | Quantum Colloquium
2021-10-06Towards a Quantum Interactive Dynamics | Quantum Colloquium
2021-10-05Computational Barriers in Statistical Estimation and Learning
2021-10-02Optimal Gradient-based Algorithms for Non-concave Bandit Optimization
2021-10-02On the Convergence of Monte Carlo Methods with Stochastic Gradients
2021-10-02Quantitative Faber-Krahn Inequalities and the ACF Monotonicity Formula
2021-10-02Adaptive Wavelet Distillation from Neural Networks through Interpretation
2021-10-02Sliced Normalizing Flow Optimization and Monte Carlo
2021-10-01MCMC Sampling Around Redistricting and Gerrymandering
2021-10-01Generative Models for Sampling on Supports Inspired by Observed Data
2021-10-01When Is the Convergence Time of Langevin Algorithms Dimension Independent: ...
2021-10-01High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm
2021-10-01Minimax Mixing Time of the Metropolis-Adjusted Langevin Algorithm for Log-Concave Sampling


Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Richard M. Karp Distinguished Lecture
Andrea Montanari