This paper details a developing artistic practice around an ongoing series of works called (un)stable equilibrium. These works are the product of using modern machine toolkits to train generative models without data, an approach akin to traditional generative art where dynamical systems are explored intuitively for their latent generative possibilities. We discuss some of the guiding principles that have been learnt in the process of experimentation, present details of the implementation of the first series of works and discuss possibilities for future experimentation.
Non-equilibrium active noise enhances generative memory in diffusion models
Department of Chemistry, University of Chicago, Chicago, IL, 60637(化学系,芝加哥大学,芝加哥,IL,60637);The James Franck Institute, University of Chicago, Chicago, IL, 60637(弗朗克研究所,芝加哥大学,芝加哥,IL,60637);Department of Physics, University of Chicago, Chicago, IL, 60637(物理系,芝加哥大学,芝加哥,IL,60637)
Game-theoretic distributed learning of generative models for heterogeneous data collections
Faculty of Computer Science, Dresden University of Technology(计算机科学系,德累斯顿技术大学);Department of Cybernetics, Czech Technical University in Prague(cybernetics系,捷克技术大学布拉格分校)
Generative Quantum Data Embeddings for Supervised Learning
Department of Statistics and Data Science, Yonsei University, Seoul 03722, Republic of Korea(统计与数据科学系,延世大学,首尔03722,韩国);Department of Applied Statistics, Yonsei University, Seoul 03722, Republic of Korea(应用统计学系,延世大学,首尔03722,韩国);Department of Quantum Information, Yonsei University, Seoul 03722, Republic of Korea(量子信息系,延世大学,首尔03722,韩国)
Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Data
Institute for Physical Science and Technology, University of Maryland, College Park, MD, 20742, USA(物理科学与技术研究所,马里兰大学,College Park, MD);Institute for Health Computing, University of Maryland, Bethesda, MD, 20852, USA(健康计算研究所,马里兰大学,Bethesda, MD);Department of Physics(物理系);Department of Chemistry and Biochemistry(化学与生物化学系)
Equilibrium Training of Energy-Based Models with Parallel Trajectory Tempering
Université Paris-Saclay(巴黎萨克雷大学);CNRS(法国国家科学研究中心);INRIA(法国国家信息与自动化研究所);Escuela Técnica Superior de Ingenieros Industriales(工业工程师高等技术学院);Universidad Politécnica de Madrid(马德里理工大学);Universidad Complutense de Madrid(马德里康普顿斯大学)
Generative Modeling of Stochastic Dynamics for Long-Time Evolution
The University of Tokyo(东京大学);RIKEN Center for Interdisciplinary Theoretical and Mathematical Sciences (iTHEMS)(理化学研究所跨学科理论与数学科学中心(iTHEMS));KEK Theory Center, Institute of Particle and Nuclear Studies(高能加速器研究机构粒子与核科学研究所理论中心);Graduate University for Advanced Studies (SOKENDAI)(综合研究大学院大学(SOKENDAI))
Expressivity of Parameterized and Data-driven Representations in Quality Diversity Search
Leiden Institute of Advanced Computer Science(莱顿高级计算机科学研究所);Bonn-Rhein-Sieg University of Applied Sciences(波恩-莱茵-锡格应用科学大学);Queen Mary University of London(伦敦玛丽女王大学);SensiLab, Monash University(莫纳什大学SensiLab)
An Online Learning Approach to Generative Adversarial Networks
ETH Zürich(苏黎世联邦理工学院)
我们考虑用生成对抗网络(GAN)训练生成模型的问题。虽然GANs可以精确地模拟复杂的分布,但由于困难的极大极小优化问题导致的不稳定性,它们很难训练。在本文中,我们将训练GANs的问题视为在零和游戏中找到混合策略。基于在线学习的思想,我们提出了一种名为Chekhov GAN 1的新训练方法。在理论方面,我们证明了我们的方法可证明收敛到半浅GAN架构的平衡,即架构中的网络是一个单层网络和发电机是任意的。在实践方面,我们开发了一个有效的启发式指导我们的理论结果,我们适用于常用的深GAN架构。在几个现实世界的任务,我们的方法表现出改进的稳定性和性能相比,标准的GAN训练。
Generative Pseudo-Force Fields for Molecular Generation
Machine Learning Group, Technische Universität Berlin(技术大学柏林机器学习小组);BIFOLD – Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究院);Department of Mathematics and Computer Science, Freie Universität Berlin(柏林自由大学数学与计算机科学系);Zuse School ELIZA, Darmstadt, Germany(达姆施塔特德国Zuse学校ELIZA);Department of Physics, Freie Universität Berlin(柏林自由大学物理系);Microsoft Research AI4Science, Berlin, Germany(柏林德国微软研究院AI4Science);Department of Chemistry, Rice University, Houston, USA(美国休斯顿莱斯大学化学系);Max-Planck Institute for Informatics, Saarbrücken, Germany(德国萨尔布吕肯马克斯·普朗克信息研究所);Department of Artificial Intelligence, Korea University, Seoul, South Korea(韩国首尔韩国大学人工智能系)
Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling
Department of Physics;Astronomy, University of Padova, Via Marzolo 8, I-35131 Padova, Italy;LPTMS, CNRS, Universit\'e Paris-Saclay, 91405, Orsay, France
Filling the Missing: Exploring Generative AI for Enhanced Federated Learning over Heterogeneous Mobile Edge Devices
University of Macau(澳门大学);Zhejiang University of Technology(浙江工业大学);Guangdong University of Technology(广东工业大学);Nanyang Technological University(南洋理工大学);University of Waterloo(滑铁卢大学)