A moment-matching approach to testable learning and a new characterization of Rademacher complexity
From MaRDI portal
Publication:6499330
DOI10.1145/3564246.3585206MaRDI QIDQ6499330
Pravesh K. Kothari, Adam R. Klivans, Aravind Gollakota
Publication date: 8 May 2024
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Log-concavity and strong log-concavity: a review
- The Gaussian surface area and noise sensitivity of degree-\(d\) polynomial threshold functions
- Learnability with respect to fixed distributions
- Almost \(k\)-wise independence versus \(k\)-wise independence
- Stability of the characterization of the multivariate normal distribution in the Skitovich-Darmois theorem
- Toward efficient agnostic learning
- Surprises in high-dimensional ridgeless least squares interpolation
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- Cryptographic hardness for learning intersections of halfspaces
- Local Rademacher complexities
- The Methods of Distances in the Theory of Probability and Statistics
- Constant depth circuits, Fourier transform, and learnability
- A Remark on Stirling's Formula
- Probability Metrics
- Agnostically Learning Halfspaces
- Hardness of Learning Halfspaces with Noise
- Polylogarithmic independence fools AC 0 circuits
- Polylogarithmic Independence Can Fool DNF Formulas
- Cryptographic limitations on learning Boolean formulae and finite automata
- On the Fourier spectrum of monotone functions
- Rademacher penalties and structural risk minimization
- On polynomial approximations to AC
- High-Dimensional Probability
- 10.1162/153244303321897690
- Agnostic Learning of Monomials by Halfspaces Is Hard
- Benign overfitting in linear regression
- List Decodable Learning via Sum of Squares
- Complexity theoretic limitations on learning halfspaces
- Bounded Independence Fools Halfspaces
- Advanced Lectures on Machine Learning
- Understanding Machine Learning
- Approximating the Noise Sensitivity of a Monotone Boolean Function
- Deep learning: a statistical viewpoint
- Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolation
- Introduction to nonparametric estimation
- Model selection and error estimation
This page was built for publication: A moment-matching approach to testable learning and a new characterization of Rademacher complexity
