Polynomial regression under arbitrary product distributions

DOI10.1007/s10994-010-5179-6zbMath1470.68084OpenAlexW2065015368MaRDI QIDQ1959600

Karl Wimmer, Eric Blais, Ryan O'Donnell

Publication date: 7 October 2010

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-010-5179-6

zbMATH Keywords

polynomial regressionnoise sensitivityagnostic learninglinear threshold functions

Mathematics Subject Classification ID

General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (3)

Learning $$AC^0$$ Under k-Dependent Distributions ⋮ Approximating the Noise Sensitivity of a Monotone Boolean Function ⋮ Homomorphic Evaluation Requires Depth

Cites Work

• Unnamed Item
• Learning intersections and thresholds of halfspaces
• Noise stability of functions with low influences: invariance and optimality
• An Efron-Stein inequality for nonsymmetric statistics
• Applications of ANOVA type decompositions for comparisons of conditional variance statistics including jackknife estimates
• Toward efficient agnostic learning
• A slight sharpening of LMN
• Support-vector networks
• Noise stability of weighted majority
• Constant depth circuits, Fourier transform, and learnability
• Learning Mixtures of Product Distributions over Discrete Domains
• Agnostically Learning Halfspaces
• Hardness of Learning Halfspaces with Noise
• A theory of the learnable
• PAC Learning Axis-Aligned Mixtures of Gaussians with No Separation Assumption
• A Class of Statistics with Asymptotically Normal Distribution
• On the Asymptotic Distribution of Differentiable Statistical Functions
• New degree bounds for polynomial threshold functions
• Noise sensitivity of Boolean functions and applications to percolation

This page was built for publication: Polynomial regression under arbitrary product distributions