9 papers
Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints
Jiayu Li, Enpei Zhang, Dawei Zhou +2
We study workflow learning in a setting where specialized agents hand off control through a shared artifact, each agent observes only a local function of that artifact and its own…
Dual-Channel Tensor Neural Networks: Finite-Sample Theory and Conformal Structure Selection
Elynn Chen, Jiayu Li, Zheshi Zheng +1
Tensor-valued data arise naturally in neuroimaging, genomics, climate science, and spatiotemporal networks, where multilinear dependencies across modes carry information that is de…
Modewise Additive Factor Model for Matrix Time Series
Elynn Chen, Yuefeng Han, Jiayu Li +1
We introduce a Modewise Additive Factor Model (MAFM) for matrix-valued time series that captures row-specific and column-specific latent effects through an additive structure, offe…
Quantifying Epistemic Uncertainty in Diffusion Models
Aditi Gupta, Raphael A. Meyer, Yotam Yaniv +2
To ensure high quality outputs, it is important to quantify the epistemic uncertainty of diffusion models. Existing methods are often unreliable because they mix epistemic and alea…
High-Dimensional Tensor Discriminant Analysis: Low-Rank Discriminant Structure, Representation Synergy, and Theoretical Guarantees
Elynn Chen, Yuefeng Han, Jiayu Li
High-dimensional tensor-valued predictors arise in modern applications, increasingly as learned representations from neural networks. Existing tensor classification methods rely on…
Tensor Neyman-Pearson Classification: Theory, Algorithms, and Error Control
Lingchong Liu, Elynn Chen, Yuefeng Han +1
Biochemical discovery increasingly relies on classifying molecular structures when the consequences of different errors are highly asymmetric. In mutagenicity and carcinogenicity,…