5 papers
Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers
Sudarshan Manikantan, Abhishek Bhattacharjee
Adaptive arm selection changes the distribution of the observations collected by a bandit algorithm, but it need not change their limiting empirical spectrum. We study Gaussian ban…
Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits
Prakhar Singhvi, Yi Zou, Abhishek Bhattacharjee
We study Bayesian linear bandits with an isotropic Gaussian parameter, independent Gaussian candidate arms, and Gaussian reward noise when the horizon is proportional to the dimens…
Cluster-Based Dimensionality Reduction by Nonparametric Distributional Screening
Sanoja Jha, Rishikesh Muralimohan, Praveen Athauda Arachchi +1
We consider dimensionality reduction for high-dimensional observations accompanied by a supplied partition into two or more clusters. The objective is not to construct a low-rank p…
Design-Based Inference under Deep Domain Stratification: Language of Instruction and Private-Institution Choice in India's NSS 71st Round
Aksaj Goel, Abhishek Bhattacharjee
Large household surveys support precise national estimates but can become statistically fragile after repeated disaggregation by geography, sector, sex, age, and outcome category.…
Bayesian Distilled Clustering for High-Dimensional Mixture Models
Pulkita Aggarwal, Abhishek Bhattacharjee
Latent subgroup analysis is central to fields such as genomics, precision medicine, and social science, where the goal is to identify heterogeneous populations with distinct covari…