SQ Lower Bounds for Learning Halfspaces with Massart Noise

Published on ● Video Link: https://www.youtube.com/watch?v=G9iCs9Epwwg



Duration: 30:56
233 views
3


Daniel Kane (UC San Diego)
https://simons.berkeley.edu/talks/tbd-346
Rigorous Evidence for Information-Computation Trade-offs




Other Videos By Simons Institute for the Theory of Computing


2021-09-28Lower Bounds on Metropolized Sampling Methods for Well-Conditioned Distributions
2021-09-28Improved Dimension Dependence for the Metropolis-Adjusted Langevin...
2021-09-28Faster Polytope Rounding, Sampling, and Volume Computation via a Sub-Linear Ball Walk
2021-09-28The Mirror Langevin Algorithm Converges with Vanishing Bias
2021-09-27How Many Clusters - An Algorithmic Answer
2021-09-22Panel on Lattice Algorithms and Cryptography
2021-09-22An Efficient Quantum Algorithm for Lattice Problems Achieving Subexponential Approximation Factor
2021-09-21On Some Optimization Problems Involving a Large Number of Matrices
2021-09-18Computational Barriers For Learning Some Generalized Linear Models
2021-09-18Towards Lower Bounds for Efficient Robust Estimation From Worst Case Assumptions
2021-09-18SQ Lower Bounds for Learning Halfspaces with Massart Noise
2021-09-17Non-Gaussian Component Analysis: Statistical Query Hardness and its Applications
2021-09-17The Estimation Error of General First Order Methods
2021-09-17Differential Privacy And The Complexity Of Simple Queries
2021-09-17Refutation and Spectrally Quiet Planting of Cuts and Colorings in Random Graphs
2021-09-17Optimal Spectral Recovery Of A Planted Vector In A Subspace
2021-09-16Extractor-Based Approach To Memory-Sample Tradeoffs
2021-09-16Average-Case Hardness in Proof Complexity
2021-09-16Tight Algorithmic Thresholds for Spin Glass Hamiltonians
2021-09-16The Algorithmic Phase Transition of Random k-SAT for Low Degree Polynomials
2021-09-16Optimizing Noncommutative Polynomials: The SYK Model



Tags:
Simons Institute
theoretical computer science
UC Berkeley
Computer Science
Theory of Computation
Theory of Computing
Rigorous Evidence for Information-Computation Trade-offs
Daniel Kane