Coupled Training with Privileged Information and Unlabeled Data
基于特权信息与未标记数据的联合训练
Jiahao Shi, Omar Hagrass, Jason M. Klusowski
机构
*
Department of Electrical and Computer Engineering, Princeton University(普林斯顿大学电子与计算机工程系)
;
Department of Operations Research and Financial Engineering, Princeton University(普林斯顿大学运筹学与金融工程系)
How Many Different Outputs Can a Transformer Generate?
变换器能生成多少种不同的输出?
Maxime Meyer, Mario Michelessa, Caroline Chaux, Vincent Y. F. Tan
机构
*
Department of Mathematics, National University of Singapore, Singapore, 117543(新加坡国立大学数学系)
;
School of Computing, National University of Singapore, Singapore, 117543(新加坡国立大学计算学院)
;
Aix Marseille Univ, CNRS, I2M, Marseille, France(法国马赛大学、国家科学研究中心、I2M研究所)
;
Department of Electrical and Computer Engineering, National University of Singapore(新加坡国立大学电子与计算机工程系)
Characterization of Gaussian Universality Breakdown in High-Dimensional Empirical Risk Minimization
高维经验风险最小化中高斯普适性破坏的表征
Chiheb Yaakoubi, Cosme Louart, Malik Tiomoko, Zhenyu Liao
机构
*
School of Data Science, The Chinese University of Hong Kong, Shenzhen, China
;
Huawei Noah's Ark Lab, Huawei Technologies, Paris, France
;
School of Electronic Information
;
Communications, Huazhong University of Science \& Technology, China
机构
*
University of California San Diego(加州大学圣地亚哥分校)
;
The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳))
;
Peking University(北京大学)
;
University of California, Los Angeles(加州大学洛杉矶分校)
;
California Institute of Technology(加州理工学院)
;
ETH Zurich(苏黎世联邦理工学院)
Diving into Kronecker Adapters: Component Design Matters
深入Kronecker适配器:组件设计至关重要
Jiayu Bai, Danchen Yu, Zhenyu Liao, TianQi Hou, Feng Zhou, Robert C. Qiu, Zenan Ling
机构
*
School of Electronic Information and Communications, Huazhong University of Science and Technology(华中科技大学电子信息学院)
;
Huawei(华为)
;
Center for Applied Statistics and School of Statistics, Renmin University of China(中国人民大学应用统计中心和统计学院)
CommentsThis work was accepted for presentation and publication at the 25th IEEE International Conference on Machine Learning and Applications (ICMLA 2026)
CommentsAccepted at the Forty-third International Conference on Machine Learning (ICML 2026). Version 2: Corrected alphabetical author order, changed proofs of Proposition 1 and Lemma 6; Main conclusions unchanged. Version 3: Metadata author order fix
Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
强化学习中状态抽象的组成性行为语义
Yivan Zhang, Ziyan Luo, Manuel Baltieri
机构
*
The University of Tokyo(东京大学)
;
Mila - Quebec Artificial Intelligence Institute(魁北克人工智能研究所)
;
McGill University(麦吉尔大学)
;
Araya Inc., Tokyo, Japan(日本东京阿雷亚公司)
;
University of Sussex(Sussex大学)