Learning representations of neural network weights given a model zoo is an emerging and challenging area with many potential applications from model inspection, to neural architecture search or knowledge distillation. Recently, an autoencoder trained on a model zoo was able to learn a hyper-representation, which captures intrinsic and extrinsic properties of the models in the zoo. In this work, we extend hyper-representations for generative use to sample new model weights as pre-training. We propose layer-wise loss normalization which we demonstrate is key to generate high-performing models and a sampling method based on the empirical density of hyper-representations. The models generated using our methods are diverse, performant and capable to outperform conventional baselines for transfer learning. Our results indicate the potential of knowledge aggregation from model zoos to new models via hyper-representations thereby paving the avenue for novel research directions.
Hypernetworks for Zero-shot Transfer in Reinforcement Learning
McGill University(麦吉尔大学);Samsung AI Center Montreal(三星蒙特利尔人工智能中心)
在本文中,通过一种新的基于TD的训练目标和来自一组用于训练任务的接近最优的RL解决方案的数据,训练超网络以在一系列看不见的任务条件下生成行为。这项工作涉及Meta RL,上下文RL和迁移学习,特别关注测试时的zero-shot性能,通过任务参数(也称为上下文)的知识来实现。我们的技术方法基于将每个RL算法视为从MDP细节到接近最优值函数和策略的映射,并寻求用可以生成接近最优价值函数和策略的超网络来近似它,给定MDP的参数。我们表明,在一定条件下,这种映射可以被认为是一个监督学习问题。我们在DeepMind Control Suite的一系列连续控制任务上,实证评估了我们的方法在zero-shot转移到新奖励和过渡动态方面的有效性。我们的方法比多任务和Meta RL方法的基线有显着改进。
Hyperparameter Transfer for Dense Associative Memories
Rudolf Peierls Centre for Theoretical Physics, University of Oxford, Oxford OX1 3PU, UK(鲁道夫·皮尔士理论物理中心,牛津大学,牛津 OX1 3PU, 英国);Dynamical Mind, IBM Research(动态思维,IBM研究);Princeton ORFE(普林斯顿ORFE)
Department of Operations Research and Financial Engineering(运营研究与金融工程系);School of Engineering and Applied Science(工程与应用科学学院);Princeton University(普林斯顿大学)
Genetic Algorithm based hyper-parameters optimization for transfer Convolutional Neural Network
State Key Laboratory of High-end Server & Storage Technology(高端服务器与存储技术国家重点实验室);Inspur Group Co., Ltd(浪潮集团有限公司);Shandong Hailiang Information Technology Institutes(山东海量信息技术研究院);Inspur Electronic Information Industry Co., Ltd(浪潮电子信息产业股份有限公司);Guangdong Inspur Intelligent Computing Technology Co., Ltd(广东浪潮智慧计算技术有限公司)
Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate
Department of Physics, University of Maryland, College Park(马里兰大学物理系);Department of Computer Science, University of Maryland, College Park(马里兰大学计算机科学系);Joint Quantum Institute, University of Maryland, College Park(马里兰大学联合量子研究所);Meta Superintelligence Labs, Fundamental AI Research(Meta超智能实验室,基础人工智能研究)
Deep Linear Network Training Dynamics from Random Initialization: Data, Width, Depth, and Hyperparameter Transfer
John Paulson School of Engineering and Applied Sciences, Harvard University(哈佛大学约翰·保罗森工程与应用科学学校);Center for Brain Sciences(脑科学研究中心);Kempner Institute(凯普纳研究所)