PHS: A Toolbox for Parallel Hyperparameter Search

Foolbox: A Python toolbox to benchmark the robustness of machine learning models

Even todays most advanced machine learning models are easily fooled by almost imperceptible perturbations of their inputs. Foolbox is a new Python package to generate such adversarial perturbations and to quantify and compare the robustness of machine learning models. It is build around the idea that the most comparable robustness measure is the minimum perturbation needed to craft an adversarial example. To this end, Foolbox provides reference implementations of most published adversarial attack methods alongside some new ones, all of which perform internal hyperparameter tuning to find the m…

PyTorch 超参数调优——spotPython 教程

PyTorch Hyperparameter Tuning - A Tutorial for spotPython

本教程介绍如何将 spotPython 集成到 PyTorch 训练流程，并基于 CIFAR10 与 Ray Tune 比较，展示其相近或更优的调优效果及更高的灵活性和透明度。

Tetra-AML：基于张量网络的自动机器学习

Tetra-AML: Automatic Machine Learning via Tensor Networks

针对大型神经网络优化部署的资源问题，提出Tetra-AML工具箱，通过自定义张量列优化算法TetraOpt实现架构搜索与超参数优化，结合压缩技术，在CIFAR-10上性能优于贝叶斯优化，压缩ResNet-18内存减14.5倍且精度损失小，还支持硬件扩展。

调优可信度——在神经网络优化中平衡性能与解释一致性

Tuning for Trustworthiness -- Balancing Performance and Explanation Consistency in Neural Network Optimization

本文提出将XAI一致性纳入超参数调优的多目标优化框架，平衡预测性能与解释鲁棒性，并识别出权衡区域，为提升模型在分布外数据上的可靠性奠定基础。

基于黎曼优化的强化学习高斯混合模型 Q 函数

Gaussian-Mixture-Model Q-Functions for Reinforcement Learning by Riemannian Optimization

本文提出 GMM-QFs，用高斯混合模型逼近 Q 函数损失并通过黎曼优化学习高斯核参数，作为策略迭代中的新评估步骤，且在无经验数据时优于含 DQN 在内的方法。