Discriminant Function

Discriminant function analysis aims to find optimal boundaries separating different classes in data, maximizing classification accuracy. Current research focuses on improving robustness to noisy labels and high-dimensional data, employing techniques like normalizing flows for decorrelation and Gaussian mixture models for handling complex data distributions. These advancements are crucial for enhancing the performance of machine learning classifiers in various applications, particularly where data scarcity or label uncertainty is a significant challenge, leading to more reliable and accurate classification systems. Furthermore, research explores methods for efficient knowledge transfer between tasks with varying data availability, improving generalization capabilities.

Papers

November 4, 2022

Decorrelation with conditional normalizing flows
Samuel Klein, Tobias Golling
Normalizing Flow Conditional Normalizing Flow Feature Decorrelation Jet Tagging Discriminative Response Discriminant Function

October 25, 2022

Interpolating Discriminant Functions in High-Dimensional Gaussian Latent Mixtures
Xin Bing, Marten Wegkamp
Binary Classification Gaussian Mixture High Dimensional Feature Low Dimensional Latent Dimensional Gaussian Mixture Discriminant Function

May 16, 2022

Fundamental Laws of Binary Classification
Denise M. Reeves
Binary Classification Binary Classifier Universal Law Discriminant Function

March 28, 2022

A Framework of Meta Functional Learning for Regularising Knowledge Transfer
Pan Li, Yanwei Fu, Shaogang Gong
New Framework Knowledge Transfer Logic Regularization Functional Regularization Functional Learning Discriminant Function

January 25, 2022

GMM Discriminant Analysis with Noisy Label for Each Class
Jian-wei Liu, Zheng-ping Ren, Run-kun Lu, Xiong-lin Luo
Noisy Label Label Noise True Class Discriminant Function

Discriminant Function

Papers

Decorrelation with conditional normalizing flows

Interpolating Discriminant Functions in High-Dimensional Gaussian Latent Mixtures

Fundamental Laws of Binary Classification

A Framework of Meta Functional Learning for Regularising Knowledge Transfer

GMM Discriminant Analysis with Noisy Label for Each Class