Resource allocation and transceivers in wireless networks are usually designed by solving optimization problems subject to specific constraints, which can be formulated as variable or functional optimization. If the objective and constraint functions of a variable optimization problem can be derived, standard numerical algorithms can be applied for finding the optimal solution, which however incur high computational cost when the dimension of the variable is high. To reduce the on-line computational complexity, learning the optimal solution as a function of the environment's status by deep neural networks (DNNs) is an effective approach. DNNs can be trained under the supervision of optimal solutions, which however, is not applicable to the scenarios without models or for functional optimization where the optimal solutions are hard to obtain. If the objective and constraint functions are unavailable, reinforcement learning can be applied to find the solution of a functional optimization problem, which is however not tailored to optimization problems in wireless networks. In this article, we introduce unsupervised and reinforced-unsupervised learning frameworks for solving both variable and functional optimization problems without the supervision of the optimal solutions. When the mathematical model of the environment is completely known and the distribution of environment's status is known or unknown, we can invoke unsupervised learning algorithm. When the mathematical model of the environment is incomplete, we introduce reinforced-unsupervised learning algorithms that learn the model by interacting with the environment. Our simulation results confirm the applicability of these learning frameworks by taking a user association problem as an example.
Unsupervised Learning of Solutions to Differential Equations with Generative Adversarial Networks
IACS（应用计算科学研究所）；Harvard University（哈佛大学）
微分方程的解具有重要的科学和工程意义。近年来，人们对用神经网络求解微分方程的兴趣越来越大。本文提出了一种利用无监督神经网络求解微分方程的新方法，该方法将生成对抗网络（GANs）应用于\emph{learn the loss function}，以优化神经网络。我们目前的实证结果表明，我们的方法，我们称之为微分方程GAN（DEQ GAN），可以获得多个数量级的均方误差比替代的无监督神经网络方法的基础上（平方）$L_2$，$L_1$，和Huber损失函数。此外，我们表明，DEQGAN实现的解决方案的精度是有竞争力的传统数值方法。最后，我们分析了我们的方法的稳定性，发现它对超参数的选择很敏感，我们在附录中提供了这些参数。代码可在https://github.com/dylanrandle/denn获得。请将任何电子邮件发送至dylanrandle@alumni.harvard.edu。
Quark: Controllable Text Generation with Reinforced Unlearning
Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；Paul G. Allen School of Computer Science, University of Washington（华盛顿大学保罗·G·艾伦计算机科学学院）
大规模的语言模型经常学习与用户期望不一致的行为。生成的文本可能包含攻击性或有毒语言，包含大量重复，或者与用户期望的不同情绪。我们考虑的任务是通过微调语言模型的信号不做什么来消除这些错位。我们引入了量化奖励约束（Quark），这是一种优化奖励函数的算法，该函数量化了（不）想要的属性，同时不会偏离原始模型太远。Quark在（i）收集具有当前语言模型的样本，（ii）基于奖励将它们分类为分位数，每个分位数由预先添加到语言模型的输入的奖励令牌标识，以及（iii）在来自每个分位数的以其奖励令牌为条件的样本上使用标准语言建模损失，同时通过KL发散惩罚保持在原始语言模型附近。通过在生成时以高奖励令牌为条件，该模型生成的文本显示出较少的不需要的属性。对于消除毒性，消极情绪和重复，我们的实验表明Quark优于强基线和最先进的强化学习方法，如PPO（Schulman et al. 2017），同时仅依赖于标准语言建模原语。
ReinDSplit: Reinforced Dynamic Split Learning for Pest Recognition in Precision Agriculture
Department of Computer Science, Missouri University of Science and Technology, USA（计算机科学系，密苏里科技大学）；Department of Mechanical Engineering, Iowa State University, USA（机械工程系，爱荷华州立大学）；Department of Agronomy, Iowa State University, USA（农业学系，爱荷华州立大学）
Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspective
Computer Network Information Center, Chinese Academy of Sciences（中国科学院计算机网络信息中心）；University of Chinese Academy of Sciences（中国科学院大学）；University of Central Florida（中佛罗里达大学）；Institute for Infocomm Research, Agency for Science（新加坡科技研究局资讯通信研究院）；Portland State University（波特兰州立大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Guangzhou HKUST Fok Ying Tung Research Institute（广州香港科技大学霍英东研究院）
Optimizing Case-Based Reasoning System for Functional Test Script Generation with Large Language Models
School of Artificial Intelligence, International Center of Future Science（人工智能学院，未来科学国际中心）；Huawei Technologies Ltd.（华为技术有限公司）；School of Artificial Intelligence（人工智能学院）；AI Centre University College London（伦敦大学学院人工智能中心）
RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning
Carnegie Mellon University（卡内基梅隆大学）；UC San Diego（加州大学圣地亚哥分校）；MIT（麻省理工学院）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Petuum Inc.（Petuum公司）
Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent
School of Computing and Augmented Intelligence, Arizona State University（亚利桑那州立大学计算与增强智能学院）；Department of Computer Science, University of Kansas（堪萨斯大学计算机科学系）；Department of Statistics and Data Science, University of Central Florida（中佛罗里达大学统计与数据科学系）；NEC Laboratories America Inc（美国电气公司实验室）
Predicting Stress and Damage in Carbon Fiber-Reinforced Composites Deformation Process using Composite U-Net Surrogate Model
Department of Chemical and Biomolecular Engineering, University of Notre Dame（化学与生物分子工程系，圣母大学）；Department of Aerospace Engineering, University of Colorado Boulder（航空航天工程系，科罗拉多大学波德分校）；Department of Aerospace and Mechanical Engineering, University of Notre Dame（航空航天与机械工程系，圣母大学）；Air Force Research Laboratory, Wright-Patterson Air Force Base（空军研究实验室，威格斯-帕特森空军基地）
Enhancing Tabular Data Optimization with a Flexible Graph-based Reinforced Exploration Strategy
CNIC, CAS（中国科学院计算机网络信息中心）；University of CAS（中国科学院大学）；University of Kansas（堪萨斯大学）；Great Bay University（大湾区大学）；IR A*STAR（新加坡科技研究局智能研究院）；Tsinghua University（清华大学）
A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features
Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning
University of California, Los Angeles（加州大学洛杉矶分校）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；The Hong Kong University of Science and Technology（香港科学与技术大学）
Realistic Unsupervised CLIP Fine-tuning with Universal Entropy Optimization
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；University of Science and Technology of China（中国科学技术大学）；Nanjing University（南京大学）
Unsupervised Seismic Footprint Removal With Physical Prior Augmented Deep Autoencoder
University of Electronic Science and Technology of China（电子科技大学）；Sichuan University（四川大学）；Sinopec Geophysical Research Institute（中国石油化工股份有限公司石油物探技术研究院）
