Linear Classifier

Linear classifiers are fundamental machine learning models aiming to separate data points into different classes using a linear decision boundary. Current research focuses on improving their performance in challenging scenarios, such as imbalanced datasets (through techniques like AUC maximization) and high-dimensional spaces (using optimized algorithms and feature extraction methods), as well as exploring their integration within larger architectures like multi-center classifiers and ensembles. The widespread use of linear classifiers stems from their computational efficiency and interpretability, making them valuable baselines and components in various applications, from medical image analysis to natural language processing.

Papers

September 1, 2022

Fair learning with Wasserstein barycenters for non-decomposable performance measures
Solenne Gaucher, Nicolas Schreuder, Evgenii Chzhen
Fairness Constraint Linear Classifier Optimal Classifier Wasserstein Barycenter Demographic Parity Fair Regression Non Decomposable Performance Measure

August 16, 2022

Counterfactual Supervision-based Information Bottleneck for Out-of-Distribution Generalization
Bin Deng, Kui Jia
Strong Generalization Distribution Generalization Information Bottleneck Linear Classifier Invariant Feature Invariant Risk Minimization

July 8, 2022

Pruning Early Exit Networks
Alperen Görmez, Erdem Koyuncu
Deep Learning Model Edge Pruning Linear Classifier Computational Cost Early Exit Network

June 29, 2022

Variational Quantum Approximate Support Vector Machine with Inference Transfer
Siheon Park, Daniel K. Park, June-Koo Kevin Rhee
Quantum Machine Learning Linear Classifier Quantum Kernel Quantum Support Vector Machine Hypothesis Transfer

June 10, 2022

Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model
Fabian Deuser, Konrad Habel, Philipp J. Rösch, Norbert Oswald
Visual Question Answering Text Encoder Linear Classifier Multi Modal Task Answer Selection Linear Layer

June 9, 2022

Strong Memory Lower Bounds for Learning Natural Models
Gavin Brown, Mark Bun, Adam Smith
Lower Bound Linear Classifier General Bound Streaming Algorithm Simple Model Natural Learning

May 27, 2022

A Sea of Words: An In-Depth Analysis of Anchors for Text Data
Gianluigi Lopardo, Frederic Precioso, Damien Garreau
Text Classification Word List Linear Classifier Tf Idf Text Data Depth Analysis Upper Ocean Interpretable Rule Visual Information Anchor Inverse Document Frequency

May 26, 2022

Gaussian Universality of Perceptrons with Random Labels
Federica Gerace, Florent Krzakala, Bruno Loureiro, Ludovic Stephan, Lenka Zdeborová
Linear Classifier Gaussian Model Gaussian Data Random Label Elementary Perceptron Gaussian Universality

May 23, 2022

Why does Throwing Away Data Improve Worst-Group Error?
Kamalika Chaudhuri, Kartik Ahuja, Martin Arjovsky, David Lopez-Paz
Raw Data Empirical Risk Minimization Linear Classifier Extreme Value Theory Worst Group Accuracy Worst Group Generalization

May 16, 2022

The Role of Pseudo-labels in Self-training Linear Classifiers on High-dimensional Gaussian Mixture Data
Takashi Takahashi
Strong Generalization Pseudo Label Integral Role Generalization Performance Linear Classifier Convex Regularization Dimensional Gaussian Mixture

May 2, 2022

Revisiting Classical Multiclass Linear Discriminant Analysis with a Novel Prototype-based Interpretable Solution
Sayed Kamaledin Ghiasi-Shirazi
Linear Classifier Discriminant Analysis

March 20, 2022

Hybrid training of optical neural networks
James Spall, Xianxin Guo, A. I. Lvovsky
Neural Network Linear Classifier Optical Neural Network Training Time Optical Processor

March 17, 2022

Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
Yibo Yang, Shixiang Chen, Xiangtai Li, Liang Xie, Zhouchen Lin, Dacheng Tao
Deep Neural Network Neural Collapse Linear Classifier Annotated End State Imbalanced Learning Learning Classifier Frame Classification

March 7, 2022

Clustering and classification of low-dimensional data in explicit feature map domain: intraoperative pixel-wise diagnosis of adenocarcinoma of a colon in a liver
Dario Sitnik, Ivica Kopriva
Classification Code Inherent Interpretability Linear Classifier Surgical Scene Segmentation Low Dimensional Data Explicit Feature Map

February 28, 2022

On classification of strategic agents who can both game and improve
Saba Ahmadi, Hedyeh Beyhaghi, Avrim Blum, Keziah Naggita
Classification Code Game Content Linear Classifier Classification Rule Strategic Agent Credit Decision

February 5, 2022

Classification on Sentence Embeddings for Legal Assistance
Arka Mitra
Artificial Intelligence Classification Code Sentence Embeddings Retrieval Performance Linear Classifier Rhetorical Role Legal Education

November 15, 2021

Randomized Classifiers vs Human Decision-Makers: Trustworthy AI May Have to Act Randomly and Society Seems to Accept This
Gábor Erdélyi, Olivia J. Erdélyi, Vladimir Estivill-Castro
Decision Making Trustworthy Artificial Intelligence Human Decision Artificial Agent Linear Classifier Random Participation Societal Domain Human Decision Maker Moral Theory

August 11, 2021

Approximation and generalization properties of the random projection classification method
Mireille Boutin, Evzenie Coupkova
Average Approximation Learning Algorithm Generalization Gap Generalization Property Linear Classifier Random Projection

October 29, 2020

Understanding the Failure Modes of Out-of-Distribution Generalization
Vaishnavh Nagarajan, Anders Andreassen, Behnam Neyshabur
Machine Learning Model Distribution Generalization Spurious Correlation Linear Classifier Image Classification Datasets Failure Mode