Classification Error

Classification error, the discrepancy between predicted and true class labels, is a central challenge in machine learning, driving research aimed at improving model accuracy and understanding error sources. Current research focuses on developing novel loss functions tailored to specific problem structures (e.g., multi-objective optimization, long-tailed distributions), analyzing error probabilities using large deviations theory and other statistical methods, and exploring techniques like metric learning and label correction to mitigate errors. These advancements are crucial for improving the reliability and trustworthiness of machine learning systems across diverse applications, from medical diagnosis to autonomous driving, where accurate classification is paramount.

Papers

September 19, 2024

Selecting a classification performance measure: matching the measure to the problem
David J. Hand, Peter Christen, Sumayya Ziyad
Classification Code View Selection Right Problem Classification Algorithm Performance Metric Classification Error Classification Metric

August 20, 2024

Asymptotic Classification Error for Heavy-Tailed Renewal Processes
Xinhui Rong, Victor Solo
Classification Error Point Process Error Distribution

June 2, 2024

Differentiation of Multi-objective Data-driven Decision Pipeline
Peng Li, Lixia Wu, Chaoqun Feng, Haoyuan Hu, Lei Fu, Jieping Ye
Multi Objective Multi Objective Optimization Problem Single Objective Classification Error Auto Differentiation

May 9, 2024

Driving down Poisson error can offset classification error in clinical tasks
Charles B. Delahunt, Courosh Mehanian, Matthew P. Horning
Machine Learning System Classification Error Clinical Task Medical AI Algorithm

March 2, 2024

Neural Field Classifiers via Target Encoding and Classification Loss
Xindi Yang, Zeke Xie, Xiong Zhou, Boyu Liu, Buhua Liu, Yi Liu, Haoran Wang, Yunfeng Cai, Mingming Sun
Neural Radiance Field Neural Field Classification Error Target Encoders

February 17, 2024

Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach
Vijay Keswani, Anay Mehrotra, L. Elisa Celis
Neural Network Context Aware Classification Error Fair Classification Partial Feedback

February 16, 2024

One-Bit Quantization and Sparsification for Multiclass Linear Classification via Regularized Regression
Reza Ghane, Danil Akhtiamov, Babak Hassibi
Gaussian Mixture Model Linear Regression Random Sparsification Linear Classifier Multiclass Classification Classification Error Explicit Regularization One Bit

December 22, 2023

On Rate-Optimal Partitioning Classification from Observable and from Privatised Data
Balázs Csanád Csáji, László Györfi, Ambrus Tamás, Harro Walk
Classification Code Convergence Rate Classification Error Optimal Classifier Text Privatization Constraint Density Exponential Convergence

December 21, 2023

A Stochastic Approach to Classification Error Estimates in Convolutional Neural Networks
Jan Peleska, Felix Brüning, Mario Gleirscher, Wen-ling Huang
Neural Network Convolutional Neural Network Convolutional Neural Network Model Classification Error Obstacle Detection Stochastic Approach

November 13, 2023

Automated Classification of Model Errors on ImageNet
Momchil Peychev, Mark Niklas Müller, Marc Fischer, Martin Vechev
Computer Vision Supervised ImageNet ImageNet Dataset Classification Error Automatic Classification Error Classification Model Error

November 11, 2023

A Saliency-based Clustering Framework for Identifying Aberrant Predictions
Aina Tersol Montserrat, Alexander R. Loftus, Yael Daihes
Machine Learning Saliency Map Machine Learning Classifier Classification Error Unreliable Prediction

October 18, 2023

Robust Class-Conditional Distribution Alignment for Partial Domain Adaptation
Sandipan Choudhuri, Arunabha Sen
Feature Alignment Distribution Alignment Classification Error Robust Pseudo Label Partial Domain Adaptation Target Supervision

September 9, 2023

MultiCaM-Vis: Visual Exploration of Multi-Classification Model with High Number of Classes
Syed Ahsan Ali Dilawer, Shah Rukh Humayoun
Multi Camera Classification Error Visual Exploration Visual Based Class Large Number Visual Analytics System Multi Classification Visual Analytics Tool

August 30, 2023

Analysis of Diagnostics (Part I): Prevalence, Uncertainty Quantification, and Machine Learning
Paul N. Patrone, Raquel A. Binder, Catherine S. Forconi, Ann M. Moormann, Anthony J. Kearsley
Training Data Theoretical Understanding Modeling Assumption Classification Error Optimal Classifier Class Conditional

August 21, 2023

A step towards understanding why classification helps regression
Silvia L. Pintea, Yancong Lin, Jouke Dijkstra, Jan C. van Gemert
Classification Code Human Understanding Novel Regression Regression Task Sample STEP Deep Regression Classification Error Regression Loss

May 8, 2023

Algebra Error Classification with Large Language Models
Hunter McNichols, Mengxue Zhang, Andrew Lan
Classification Error Error Classification Math Question Student Error

March 10, 2023

Long-tailed Classification from a Bayesian-decision-theory Perspective
Bolian Li, Ruqi Zhang
Deep Ensemble Classification Error Long Tailed Classification Decision Theoretic Task Specific Loss

February 28, 2023

Metric Learning Improves the Ability of Combinatorial Coverage Metrics to Anticipate Classification Error
Tyler Cody, Laura Freeman
Metric Learning Critique Ability Classification Error Coverage Criterion Distributional Inequality Metric Coverage Metric

February 20, 2023

Why is the prediction wrong? Towards underfitting case explanation via meta-classification
Sheng Zhou, Pierre Blanchart, Michel Crucianu, Marin Ferecatu
Human Prediction Decision Tree Case Relevance Classification Error Meta Representation Meta Classifier

February 16, 2023

Counterfactual Reasoning for Bias Evaluation and Detection in a Fairness under Unawareness setting
Giandomenico Cornacchia, Vito Walter Anelli, Fedelucio Narducci, Azzurra Ragone, Eugenio Di Sciascio
Data Detection Procedural Fairness Counterfactual Reasoning Bias Evaluation Classification Error Counterfactual Example Self Awareness Counterfactual Sample

Classification Error

Papers

Selecting a classification performance measure: matching the measure to the problem

Asymptotic Classification Error for Heavy-Tailed Renewal Processes

Differentiation of Multi-objective Data-driven Decision Pipeline

Driving down Poisson error can offset classification error in clinical tasks

Neural Field Classifiers via Target Encoding and Classification Loss

Fair Classification with Partial Feedback: An Exploration-Based Data Collection Approach

One-Bit Quantization and Sparsification for Multiclass Linear Classification via Regularized Regression

On Rate-Optimal Partitioning Classification from Observable and from Privatised Data

A Stochastic Approach to Classification Error Estimates in Convolutional Neural Networks

Automated Classification of Model Errors on ImageNet

A Saliency-based Clustering Framework for Identifying Aberrant Predictions

Robust Class-Conditional Distribution Alignment for Partial Domain Adaptation

MultiCaM-Vis: Visual Exploration of Multi-Classification Model with High Number of Classes

Analysis of Diagnostics (Part I): Prevalence, Uncertainty Quantification, and Machine Learning

A step towards understanding why classification helps regression

Algebra Error Classification with Large Language Models

Long-tailed Classification from a Bayesian-decision-theory Perspective

Metric Learning Improves the Ability of Combinatorial Coverage Metrics to Anticipate Classification Error

Why is the prediction wrong? Towards underfitting case explanation via meta-classification

Counterfactual Reasoning for Bias Evaluation and Detection in a Fairness under Unawareness setting