5 papers
Embracing Biased Transition Matrices for Complementary-Label Learning with Many Classes
Tan-Ha Mai, Chao-Kai Chiang, Han-Hwa Shih +3
Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain…
LLM Routing with Dueling Feedback
Chao-Kai Chiang, Takashi Ishida, Masashi Sugiyama
We study LLM routing, the problem of selecting the best model for each query while balancing user satisfaction, model expertise, and inference cost. We formulate routing as context…
Domain Adaptation and Entanglement: an Optimal Transport Perspective
Okan Koç, Alexander Soen, Chao-Kai Chiang +1
Current machine learning systems are brittle in the face of distribution shifts (DS), where the target distribution that the system is tested on differs from the source distributio…
Unified Risk Analysis for Weakly Supervised Learning
Chao-Kai Chiang, Masashi Sugiyama
Among the flourishing research of weakly supervised learning (WSL), we recognize the lack of a unified interpretation of the mechanism behind the weakly supervised scenarios, let a…
The Choice of Noninformative Priors for Thompson Sampling in Multiparameter Bandit Models
Jongyeong Lee, Chao-Kai Chiang, Masashi Sugiyama
Thompson sampling (TS) has been known for its outstanding empirical performance supported by theoretical guarantees across various reward models in the classical stochastic multi-a…