7 papers
Exposing Vulnerability Monoculture Through Systemic Adversarial Robustness
Leo Elmecker-Plakolm, Lukasz Szpruch, Avishek Joey Bose +1
Beneath the apparent diversity of foundation models lies an increasingly homogeneous technical stack of common training pipelines, distillation methods, and data. These shared algo…
Statistical Inference for Continuous Action Bandits
Raphael C Kim, Michele Santacatterina, Ramin Zabih +2
Statistical inference under adaptively collected data is becoming increasingly popular across e-commerce and mobile health. Many methods exist for discrete action settings, ranging…
Improved Variance Estimation in Homoskedastic Nonparametric Random-Design Regression via a Two-Scale Approach
Edgar Dobriban, Rajarshi Mukherjee, James M. Robins +1
We study estimation of a constant conditional variance in nonparametric regression with a -dimensional random design. This is an important problem, and similar questions a…
Sharp minimax risks and phase transitions in sparse submatrix detection
Subhajit Goswami, Rajarshi Mukherjee
In this paper, we study the minimax risk of detecting a sparse, elevated-mean Gaussian submatrix planted in a larger noisy matrix. When the planted submatrix has size a…
Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics
Sean McGrath, Debarghya Mukherjee, Rajarshi Mukherjee +1
In this paper, we explore the asymptotically optimal tuning parameter choice in ridge regression for estimating nuisance functions of a statistical functional that has recently gai…
Inference on Gaussian mixture models with dependent labels
Seunghyun Lee, Rajarshi Mukherjee, Sumit Mukherjee
Gaussian mixture models are widely used to model data generated from multiple latent sources. Despite its popularity, most theoretical research assumes that the labels are either i…
Method-of-Moments Inference for GLMs and Doubly Robust Functionals under Proportional Asymptotics
Xingyu Chen, Lin Liu, Rajarshi Mukherjee
In this paper, we consider the estimation of regression coefficients and signal-to-noise (SNR) ratio in high-dimensional Generalized Linear Models (GLMs), and explore their implica…