Model Accuracy

Model accuracy, a crucial metric in machine learning, assesses a model's ability to correctly predict outcomes. Current research focuses on improving accuracy by addressing data limitations, such as noisy labels and data heterogeneity in federated learning, and by developing more efficient training and evaluation methods, including techniques like coreset selection and stratified sampling. These advancements are vital for enhancing the reliability and trustworthiness of machine learning models across diverse applications, from object recognition to financial forecasting, and for optimizing model deployment in resource-constrained environments. Furthermore, research is actively exploring methods to quantify and mitigate biases that can lead to disparate impacts on model accuracy across different subgroups.

Papers

July 19, 2023

Measuring and Modeling Uncertainty Degree for Monocular Depth Estimation
Mochu Xiang, Jing Zhang, Nick Barnes, Yuchao Dai
Uncertainty Estimation Monocular Depth Estimation Depth Map Measurement System Model Accuracy

June 27, 2023

Evaluation of machine learning architectures on the quantification of epistemic and aleatoric uncertainties in complex dynamical systems
Stephen Guth, Alireza Mojahed, Themistoklis P. Sapsis
Global Evaluation Uncertainty Quantification Surrogate Model Bayesian Neural Network Aleatoric Uncertainty Complex Dynamical System Model Accuracy Machine Learning Architecture Data Driven Reduced Order

June 13, 2023

Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Nari Johnson, Ángel Alexander Cabrera, Gregory Plumb, Ameet Talwalkar
Machine Learning Human Evaluation Model Accuracy Slice Discovery

June 5, 2023

Sensitivity-Aware Finetuning for Accuracy Recovery on Deep Learning Hardware
Lakshmi Nair, Darius Bunandar
Deep Learning Accuracy Improvement Model Accuracy Dense Layer Analog Audio Effect

April 27, 2023

Oversampling Higher-Performing Minorities During Machine Learning Model Training Reduces Adverse Impact Slightly but Also Reduces Model Accuracy
Louis Hickman, Jason Kuruzovich, Vincent Ng, Kofi Arhin, Danielle Wilson
Machine Learning Machine Learning Model Model Accuracy Training Machine Learning Model Minority Group

October 24, 2022

Simultaneous Improvement of ML Model Fairness and Performance by Identifying Bias in Data
Bhushan Chaudhari, Akash Agarwal, Tanmoy Bhowmik
Machine Learning Model Raw Data System Performance Absolute Stance Bias Bias Mitigation Model Accuracy Potential Bias ML Fairness Simultaneous Improvement

October 21, 2022

Validation of Composite Systems by Discrepancy Propagation
David Reeb, Kanil Patel, Karim Barsim, Martin Schiegg, Sebastian Gerwinn
External Validation Semidefinite Programming Model Accuracy Accurate Simulation Discrepancy Aware Distribution Discrepancy

August 15, 2022

Three New Validators and a Large-Scale Benchmark Ranking for Unsupervised Domain Adaptation
Kevin Musgrave, Serge Belongie, Ser-Nam Lim
Domain Adaptation Large Scale Unsupervised Domain Adaptation Hyperparameter Tuning Related Hyperparameters Model Accuracy Model Checkpoint Skilled Non Expert Validators

May 26, 2022

February 20, 2022

Deconstructing Distributions: A Pointwise Framework of Learning
Gal Kaplun, Nikhil Ghosh, Saurabh Garg, Boaz Barak, Preetum Nakkiran
Machine Learning LeArning Abstract Model Accuracy Single Model Point Wise Operation Structured Distribution Accuracy on the Line

January 7, 2022

Optimizing the Communication-Accuracy Trade-off in Federated Learning with Rate-Distortion Theory
Nicole Mitchell, Johannes Ballé, Zachary Charles, Jakub Konečný
Model Performance Rate Distortion Model Accuracy

December 17, 2021

Quality of Data in Machine Learning
Antti Kariluoto, Arto Pärnänen, Joni Kultanen, Jukka Soininen, Pekka Abrahamsson
Machine Learning Machine Learning Model Raw Data Quality Issue Ensemble Model Model Accuracy Input Feature Student Data

November 18, 2021

Automatic Neural Network Pruning that Efficiently Preserves the Model Accuracy
Thibault Castells, Seul-Ki Yeom
Neural Network Pruning Method Model Accuracy Floating Point Neural Network Performance Training Bottleneck Automatic Pruning

November 10, 2021

SGD Through the Lens of Kolmogorov Complexity
Gregory Schwartzman
Stochastic Gradient Descent Camera Lens Model Accuracy Classification Accuracy Kolmogorov Complexity