3 papers
math.ST2026
Generalization error of min-norm interpolators in transfer learning
Yanke Song, Kenneth Gu, Sohom Bhattacharya +1
This paper establishes the generalization error of pooled min--norm interpolation in transfer learning, where data from diverse distributions are available. Min-norm interp…
stat.ML2026
Preventing Model Collapse Under Overparametrization: Optimal Mixing Ratios for Interpolation Learning and Ridge Regression
Anvit Garg, Sohom Bhattacharya, Pragya Sur
Model collapse occurs when generative models degrade after repeatedly training on their own synthetic outputs. We study this effect in overparameterized linear regression in a sett…
stat.ME2025
Late Fusion Multi-task Learning for Semiparametric Inference with Nuisance Parameters
Sohom Bhattacharya, Yongzhuo Chen, Muxuan Liang
In the age of large and heterogeneous datasets, the integration of information from diverse sources is essential to improve parameter estimation. Multi-task learning offers a power…