From the 1 of 7 linked papers with an AI index.
7 papers
Minimax Theory of Likelihood-Based Deep Learning for Speckle Regression
Soham Jana
The paper develops a minimax theory for likelihood‑based deep neural network estimators in speckle regression, showing they achieve optimal nonparametric rates despite multiplicati…
Minimax Analysis of Estimation Problems in Coherent Imaging
Hao Xing, Soham Jana, Arian Maleki
Unlike conventional imaging modalities, such as magnetic resonance imaging, which are often well described by a linear regression framework, coherent imaging systems follow a signi…
Adversarially robust clustering with optimality guarantees
Soham Jana, Kun Yang, Sanjeev Kulkarni
We consider the problem of clustering data points coming from sub-Gaussian mixtures. Existing methods that provably achieve the optimal mislabeling error, such as the Lloyd algorit…
Optimal empirical Bayes estimation for the Poisson model via minimum-distance methods
Soham Jana, Yury Polyanskiy, Yihong Wu
The Robbins estimator is the most iconic and widely used procedure in the empirical Bayes literature for the Poisson model. On one hand, this method has been recently shown to be m…
Factor Informed Double Deep Learning For Average Treatment Effect Estimation
Jianqing Fan, Soham Jana, Sanjeev Kulkarni +1
We investigate the problem of estimating the average treatment effect (ATE) under a very general setup where the covariates can be high-dimensional, highly correlated, and can have…
Multilook Coherent Imaging: Theoretical Guarantees and Algorithms
Xi Chen, Soham Jana, Christopher A. Metzler +2
Multilook coherent imaging is a widely used technique in applications such as digital holography, ultrasound imaging, and synthetic aperture radar. A central challenge in these sys…