paper-with-me

Papers

humancompatible.train: Implementing Optimization Algorithms for Stochastically-Constrained Stochastic Optimization Problems

2025-09-25 · Andrii Kliachkin, Jana Lepšová, Gilles Bareilles, Jakub Mareček arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.21254

Code (0)

등록된 구현이 없습니다.

Tasks

Stochastic Optimization

Similar Papers 제목 키워드 기반

Benchmarking Stochastic Approximation Algorithms for Fairness-Constrained Training of Deep Neural Networks

2025-07-05 · Andrii Kliachkin, Jana Lepšová, Gilles Bareilles, Jakub Mareček arxiv

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 recent years, and yet there is no stand…

humancompatible.detect: a Python Toolkit for Detecting Bias in AI Models

2025-09-29 · German M. Matilla, Jiri Nemecek, Illia Kryvoviaz, Jakub Marecek arxiv

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 and estimate bias on the output of high-ri…

Bias Detection

Escaping strict saddle points of the Moreau envelope in nonsmooth optimization

2021-06-17 · Damek Davis, Mateo Díaz, Dmitriy Drusvyatskiy

Recent work has shown that stochastically perturbed gradient methods can efficiently escape strict saddle points of smooth functions. We extend this body of work to nonsmooth optimization, by analyzing an inexact analogu…

imitation: Clean Imitation Learning Implementations

2022-11-22 · Adam Gleave, Mohammad Taufeeque, Juan Rocamonde, Erik Jenner 외

imitation provides open-source implementations of imitation and reward learning algorithms in PyTorch. We include three inverse reinforcement learning (IRL) algorithms, three imitation learning algorithms and a preferenc…

Imitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Distributed gradient-based optimization in the presence of dependent aperiodic communication

2022-01-27 · Adrian Redder, Arunselvan Ramaswamy, Holger Karl

Iterative distributed optimization algorithms involve multiple agents that communicate with each other, over time, in order to minimize/maximize a global objective. In the presence of unreliable communication networks, t…

Distributed Optimization