3 papers
math.ST2025
Causal inference under interference: computational barriers and algorithmic solutions
Sohom Bhattacharya, Subhabrata Sen
We study causal effect estimation under interference from network data. We work under the chain-graph formulation pioneered in Tchetgen Tchetgen et. al (2021). Our first result sho…
stat.ML2025
Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models
Taj Jones-McCormick, Aukosh Jagannath, Subhabrata Sen
Unsupervised pre-training and transfer learning are commonly used techniques to initialize training algorithms for neural networks, particularly in settings with limited labeled da…
math.ST2024
Causal effect estimation under network interference with mean-field methods
Sohom Bhattacharya, Subhabrata Sen
We study causal effect estimation from observational data under interference. The interference pattern is captured by an observed network. We adopt the chain graph framework of Tch…