Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Modelsby Yongxian Wei, Zixuan Hu, Li Shen,…
Contextual Linear Optimization with Bandit Feedbackby Yichun Hu, Nathan Kallus, Xiaojie Mao, Yanchen WuFirst submitted…
Higher-Order Transformer Derivative Estimates for Explicit Pathwise Learning Guaranteesby Yannick Limmer, Anastasis Kratsios, Xuwei Yang,…
Reflected Flow Matchingby Tianyu Xie, Yu Zhu, Longlin Yu, Tong Yang, Ziheng Cheng, Shiyue Zhang,…
A Study on Unsupervised Anomaly Detection and Defect Localization using Generative Model in Ultrasonic Non-Destructive…
On Bits and Bandits: Quantifying the Regret-Information Trade-offby Itai Shufaro, Nadav Merlis, Nir Weinberger, Shie…
Fair Federated Learning under Domain Skew with Local Consistency and Domain Diversityby Yuhang Chen, Wenke…
Cost-Effective Online Multi-LLM Selection with Versatile Reward Modelsby Xiangxiang Dai, Jin Li, Xutong Liu, Anqi…
Training-Conditional Coverage Bounds under Covariate Shiftby Mehrdad Pournaderi, Yu XiangFirst submitted to arxiv on: 26…
Regularized Projection Matrix Approximation with Applications to Community Detectionby Zheng Zhai, Jialu Xu, Mingxin Wu,…