humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914056662679552 |
|---|---|
| author | Kliachkin, Andrii Lepšová, Jana Bareilles, Gilles Mareček, Jakub |
| author_facet | Kliachkin, Andrii Lepšová, Jana Bareilles, Gilles Mareček, Jakub |
| contents | 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 proposed for this task, yet there is still no industry standard. We present humancompatible.train (https://github.com/humancompatible/train), an easily-extendable PyTorch-based Python package for training DNNs with stochastic constraints. We implement multiple previously unimplemented algorithms for stochastically constrained stochastic optimization. We demonstrate the toolkit use by comparing two algorithms on a deep learning task with fairness constraints. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_21254 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems Kliachkin, Andrii Lepšová, Jana Bareilles, Gilles Mareček, Jakub Machine Learning Optimization and Control 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 proposed for this task, yet there is still no industry standard. We present humancompatible.train (https://github.com/humancompatible/train), an easily-extendable PyTorch-based Python package for training DNNs with stochastic constraints. We implement multiple previously unimplemented algorithms for stochastically constrained stochastic optimization. We demonstrate the toolkit use by comparing two algorithms on a deep learning task with fairness constraints. |
| title | humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2509.21254 |