Sabyasachi Chatterjee

On risk bounds in isotonic and other shape restricted regression problems

We consider the problem of estimating an unknown

Information theoretic validity of penalized likelihood

\theta\in {\mathbb{R}}^n

An improved global risk bound in concave regression

from noisy observations under the constraint that

Denoising Flows on Trees

\theta

On matrix estimation under monotonicity constraints

belongs to certain convex polyhedral cones in

Adaptive Risk Bounds in Unimodal Regression

{\mathbb{R}}^n

Improved Risk Bounds in Isotonic Regression

. Under this setting, we prove bounds for the risk of the least squares estimator (LSE). The obtained risk bound behaves differently depending on the true sequence

Local Minimax Complexity of Stochastic Convex Optimization

\theta

On Estimation in Tournaments and Graphs under Monotonicity Constraints

which highlights the adaptive behavior of

Isotonic regression in general dimensions

\theta