5 papers
Stochastic Penalty-Barrier Methods for Constrained Machine Learning
Adam Bosák, Andrii Kliachkin, Jana Lepšová +2
Constrained machine learning enables fairness-aware training, physics-informed neural networks, and integration of symbolic domain knowledge into statistical models. Despite its pr…
Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks
Andrii Kliachkin, Jana Lepšová, Gilles Bareilles +1
The ability to train Deep Neural Networks (DNNs) with constraints is instrumental in improving the fairness of modern machine-learning models. Many algorithms have been analysed in…
EVEREST: An Evidential, Tail-Aware Transformer for Rare-Event Time-Series Forecasting
Antanas Zilinskas, Robert N. Shorten, Jakub Marecek
Forecasting rare events in multivariate time-series data is challenging due to severe class imbalance, long-range dependencies, and distributional uncertainty. We introduce EVEREST…
humancompatible.detect: a Python Toolkit for Detecting Bias in AI Models
German M. Matilla, Jiri Nemecek, Illia Kryvoviaz +1
There is a strong recent emphasis on trustworthy AI. In particular, international regulations, such as the AI Act, demand that AI practitioners measure data quality on the input an…
humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems
Andrii Kliachkin, Jana Lepšová, Gilles Bareilles +1
There has been a considerable interest in constrained training of deep neural networks (DNNs) recently for applications such as fairness and safety. Several toolkits have been prop…