6 papers
Minimax Optimal Estimator and Improved Error Rate for the MLE in Logistic Regression with Gaussian Design
Junren Chen, Arya Mazumdar
We study finite-sample parameter estimation in logistic regression with Gaussian design, where the goal is to estimate with f…
Near-Optimal Lower Bounds on One-Bit Compressed Sensing of Approximately Sparse Signals
Junren Chen, Arya Mazumdar, Ming Yuan
This paper provides the first near-optimal lower bounds for one-bit compressed sensing of approximately sparse signals lying in a scaled ball, which is a commonly adopted…
Finite-Sample Performance of Gradient Descent in Logistic Regression with Gaussian Design
Junren Chen, Arya Mazumdar
We consider the parameter estimation problem in logistic regression with Gaussian design: the estimation of a fixed unknown parameter () fro…
The Noisy Quantitative Group Testing Problem
Tenghao Li, Neha Sangwan, Xiaxin Li +1
In this paper, we study the problem of quantitative group testing (QGT) and analyze the performance of three models: the noiseless model, the additive Gaussian noise model, and the…
Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
Yilan Chen, Zhichao Wang, Wei Huang +3
Gradient-based optimization methods have shown remarkable empirical success, yet their theoretical generalization properties remain only partially understood. In this paper, we est…
Exact Recovery of Sparse Binary Vectors from Generalized Linear Measurements
Arya Mazumdar, Neha Sangwan
We consider the problem of exact recovery of a -sparse binary vector from generalized linear measurements (such as logistic regression). We analyze the linear estimation algorit…