Efficient and automated design of optimizers plays a crucial role in full-stack AutoML systems. However, prior methods in optimizer search are often limited by their scalability, generability, or sample efficiency. With the goal of democratizing research and application of optimizer search, we present the first efficient, scalable and generalizable framework that can directly search on the tasks of interest. We first observe that optimizer updates are fundamentally mathematical expressions applied to the gradient. Inspired by the innate tree structure of the underlying math expressions, we re-arrange the space of optimizers into a super-tree, where each path encodes an optimizer. This way, optimizer search can be naturally formulated as a path-finding problem, allowing a variety of well-established tree traversal methods to be used as the search algorithm. We adopt an adaptation of the Monte Carlo method to tree search, equipped with rejection sampling and equivalent-form detection that leverage the characteristics of optimizer update rules to further boost the sample efficiency. We provide a diverse set of tasks to benchmark our algorithm and demonstrate that, with only 128 evaluations, the proposed framework can discover optimizers that surpass both human-designed counterparts and prior optimizer search methods.
carps: A Framework for Comparing N Hyperparameter Optimizers on M Benchmarks
Leibniz University Hannover(汉诺威莱布尼茨大学);Albert-Ludwigs University Freiburg(弗赖堡阿尔伯特-路易斯大学);University of St Andrews(圣安德鲁大学);Sorbonne Université Paris(巴黎索邦大学);LMU Munich(慕尼黑路德维希-马克西米利安大学);University of Tübingen(图宾根大学);ELLIS Institute Tübingen(图宾根ELLIS研究所);L3S Research Center(L3S研究中心);Munich Center for Machine Learning(慕尼黑机器学习中心)
GarmentX: Autoregressive Parametric Representations for High-Fidelity 3D Garment Generation
South China University of Technology(华南理工大学);National University of Singapore(新加坡国立大学);LIGHTSPEED(光速(公司));The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The University of Hong Kong(香港大学)
Taming the Instability: A Robust Second-Order Optimizer for Federated Learning over Non-IID Data
Key Laboratory of Collaborative Intelligence Systems of Ministry of Education, Xidian University(西安电子科技大学教育部协同智能系统重点实验室);Centre for Frontier AI Research, Institute of High Performance Computing, Agency for Science, Technology and Research(新加坡科技研究局高性能计算研究所前沿人工智能研究中心);State Key Laboratory of ISN, School of Cyber Engineering, Xidian University(西安电子科技大学网络与信息安全学院综合业务网理论及关键技术国家重点实验室);College of Computing and Data Science, Nanyang Technological University(南洋理工大学计算与数据科学学院);Department of Computing Technologies, Swinburne University of Technology(斯威本科技大学计算技术系)
Unsupervised Control Through Non-Parametric Discriminative Rewards
DeepMind(深度思考)
在没有手工制作的奖励或专家数据的情况下学习控制环境仍然具有挑战性,并且处于强化学习研究的前沿。我们提出了一个无监督学习算法,训练代理实现感知指定的目标,只使用一个流的观察和行动。我们的代理同时学习目标条件策略和目标实现奖励函数,该函数测量状态与目标状态的相似程度。这种双重优化导致了合作博弈,产生了一个学习的奖励函数,反映了环境可控方面的相似性,而不是观察空间中的距离。我们展示了我们的智能体在无监督的方式下学习的效率,以达到三个领域的不同目标- Atari,DeepMind Control Suite和DeepMind Lab。
MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences(中国科学院深圳先进技术研究院);Shenzhen University of Advanced Technology(深圳理工大学);Pengcheng Laboratory(鹏城实验室);University of Chinese Academy of Sciences(中国科学院大学)
Learning Diverse-Structured Networks for Adversarial Robustness
Hong Kong Baptist University(香港浸会大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);RIKEN(理化学研究所);University of Sydney(悉尼大学);Tencent AI Lab(腾讯人工智能实验室);University of Tokyo(东京大学)
Scaffolded Language Models with Language Supervision for Mixed-Autonomy: A Survey
Department of Computer Science and Technology, Tsinghua University, Beijing, China(计算机科学与技术系,清华大学,北京,中国);Department of Automation, Tsinghua University, Beijing, China(自动化系,清华大学,北京,中国);Shanghai AI Lab, Shanghai, China(上海人工智能实验室,上海,中国);Xi'an Jiaotong University, Xi'an, China(西安交通大学,西安,中国)
Differentially Private Non Parametric Copulas: Generating synthetic data with non parametric copulas under privacy guarantees
School of Applied Sciences and Engineering, Universidad EAFIT(应用科学与工程学院,埃法特大学);Digital Health and Biomedical Technologies, Vicomtech Foundation, Basque Research and Technology Alliance (BRTA)(数字健康与生物医学技术,维科姆科技基金会,巴斯克研究与技术联盟(BRTA));eHealth Group, Biogipuzkoa Health Research Institute(eHealth组,比戈普西亚健康研究 institutes)