Book contents
- Frontmatter
- Contents
- Preface
- List of Contributors
- 1 Introduction
- Part One Refinements of Worst-Case Analysis
- Part Two Deterministic Models of Data
- Part Three Semirandom Models
- Part Four Smoothed Analysis
- Part Five Applications in Machine Learning and Statistics
- 16 Noise in Classification
- 17 Robust High-Dimensional Statistics
- 18 Nearest Neighbor Classification and Search
- 19 Efficient Tensor Decompositions
- 20 Topic Models and Nonnegative Matrix Factorization
- 21 Why Do Local Methods Solve Nonconvex Problems?
- 22 Generalization in Overparameterized Models
- 23 Instance Optimal Distribution Testing and Learning
- Part Six Further Applications
- Index
16 - Noise in Classification
from Part Five - Applications in Machine Learning and Statistics
Published online by Cambridge University Press: 17 December 2020
Edited by
Book contents
- Frontmatter
- Contents
- Preface
- List of Contributors
- 1 Introduction
- Part One Refinements of Worst-Case Analysis
- Part Two Deterministic Models of Data
- Part Three Semirandom Models
- Part Four Smoothed Analysis
- Part Five Applications in Machine Learning and Statistics
- 16 Noise in Classification
- 17 Robust High-Dimensional Statistics
- 18 Nearest Neighbor Classification and Search
- 19 Efficient Tensor Decompositions
- 20 Topic Models and Nonnegative Matrix Factorization
- 21 Why Do Local Methods Solve Nonconvex Problems?
- 22 Generalization in Overparameterized Models
- 23 Instance Optimal Distribution Testing and Learning
- Part Six Further Applications
- Index
Summary
A summary is not available for this content so a preview has been provided. Please use the Get access link above for information on how to access this content.
- Type
- Chapter
- Information
- Beyond the Worst-Case Analysis of Algorithms , pp. 361 - 381Publisher: Cambridge University PressPrint publication year: 2021
- 2
- Cited by