2 citations · 3 across the 8 of their papers we have counts for
11 papers
Assumption-lean logistic regression with missing covariates
Jyotishka Ray Choudhury, Kabir Aladin Verchand, Richard J. Samworth +1
Missing covariates are frequently encountered in supervised learning problems, and classical methods for estimation using such data use carefully chosen imputation schemes for miss…
Adaptive confidence intervals with missing data
Tianyi Ma, Kabir A. Verchand, Chao Gao +1
We consider the construction of confidence intervals for population means when observations are subject to missingness. To accommodate more general missingness mechanisms than miss…
High-dimensional estimation with missing data: Statistical and computational limits
Kabir Aladin Verchand, Ankit Pensia, Saminul Haque +1
We consider computationally-efficient estimation of population parameters when observations are subject to missing data. In particular, we consider estimation under the realizable…
State evolution beyond first-order methods I: Rigorous predictions and finite-sample guarantees
Michael Celentano, Chen Cheng, Ashwin Pananjady +1
We develop a toolbox for exact analysis of iterative algorithms on a class of high-dimensional nonconvex optimization problems with random data. While prior work has shown that low…
Accurate, provable and fast polychromatic tomographic reconstruction: A variational inequality approach
Mengqi Lou, Kabir Aladin Verchand, Sara Fridovich-Keil +1
We consider the problem of signal reconstruction for computed tomography (CT) under a nonlinear forward model that accounts for exponential signal attenuation, a polychromatic X-ra…
Estimation beyond Missing (Completely) at Random
Tianyi Ma, Kabir A. Verchand, Thomas B. Berrett +2
We study the effects of missingness on the estimation of population parameters. Moving beyond restrictive missing completely at random (MCAR) assumptions, we first formulate a miss…
High-dimensional logistic regression with missing data: Imputation, regularization, and universality
Kabir Aladin Verchand, Andrea Montanari
We study high-dimensional, ridge-regularized logistic regression in a setting in which the covariates may be missing or corrupted by additive noise. When both the covariates and th…
High-probability minimax lower bounds
Tianyi Ma, Kabir A. Verchand, Richard J. Samworth
The minimax risk is often considered as a gold standard against which we can compare specific statistical procedures. Nevertheless, as has been observed recently in robust and heav…
Low-degree phase transitions for detecting a planted clique in sublinear time
Jay Mardia, Kabir Aladin Verchand, Alexander S. Wein
We consider the problem of detecting a planted clique of size in a random graph on vertices. When the size of the clique exceeds , polynomial-time algorithms f…
Hyperparameter tuning via trajectory predictions: Stochastic prox-linear methods in matrix sensing
Mengqi Lou, Kabir Aladin Verchand, Ashwin Pananjady
Motivated by the desire to understand stochastic algorithms for nonconvex optimization that are robust to their hyperparameter choices, we analyze a mini-batched prox-linear iterat…
Alternating minimization for generalized rank one matrix sensing: Sharp predictions from a random initialization
Kabir Aladin Chandrasekher, Mengqi Lou, Ashwin Pananjady
We consider the problem of estimating the factors of a rank- matrix with i.i.d. Gaussian, rank- measurements that are nonlinearly transformed and corrupted by noise. Consider…