6 papers
Self-Distillation is Optimal Among Spectral Shrinkage Estimators in Spiked Covariance Models
Radu Lecoiu, Debarghya Mukherjee, Pragya Sur
Self-distillation has emerged as a promising technique for improving model performance in modern machine learning systems. We develop the statistical foundations of self-distillati…
Adaptive Estimation and Inference in Semi-parametric Heterogeneous Clustered Multitask Learning via Neyman Orthogonality
Hanxiao Chen, Debarghya Mukherjee
We study clustered multitask learning in a semiparametric setting where tasks share a latent cluster structure in their target parameters but exhibit heterogeneous, potentially inf…
Minimax optimal adaptive structured transfer learning through semi-parametric domain-varying coefficient model
Hanxiao Chen, Debarghya Mukherjee
Transfer learning aims to improve inference in a target domain by leveraging information from related source domains, but its effectiveness critically depends on how cross-domain h…
CINDES: Classification induced neural density estimator and simulator
Dehao Dai, Jianqing Fan, Yihong Gu +1
Neural network-based methods for (un)conditional density estimation have recently gained substantial attention, as various neural density estimators have outperformed classical app…
Estimation and Inference for the Average Treatment Effect in a Score-Explained Heterogeneous Treatment Effect Model
Kevin Christian Wibisono, Debarghya Mukherjee, Moulinath Banerjee +1
In many practical situations, randomly assigning treatments to subjects is uncommon due to feasibility constraints. For example, economic aid programs and merit-based scholarships…
Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
Jiawei Ge, Debarghya Mukherjee, Jianqing Fan
As machine learning models are increasingly deployed in dynamic environments, it becomes paramount to assess and quantify uncertainties associated with distribution shifts. A distr…