Picture for Promit Ghosal

Promit Ghosal

LoSAM: Local Search in Additive Noise Models with Unmeasured Confounders, a Top-Down Global Discovery Approach

Add code
Oct 15, 2024
Viaarxiv icon

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent

Add code
Sep 13, 2024
Viaarxiv icon

Hybrid Global Causal Discovery with Local Search

Add code
May 23, 2024
Viaarxiv icon

From Stability to Chaos: Analyzing Gradient Descent Dynamics in Quadratic Regression

Add code
Oct 02, 2023
Viaarxiv icon

Towards Understanding the Dynamics of Gaussian--Stein Variational Gradient Descent

Add code
May 23, 2023
Viaarxiv icon

High-dimensional scaling limits and fluctuations of online least-squares SGD with smooth covariance

Add code
Apr 03, 2023
Viaarxiv icon

High-dimensional Central Limit Theorems for Linear Functionals of Online Least-Squares SGD

Add code
Feb 20, 2023
Viaarxiv icon

Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable

Add code
May 24, 2022
Figure 1 for Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable
Figure 2 for Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable
Figure 3 for Randomly Initialized One-Layer Neural Networks Make Data Linearly Separable
Viaarxiv icon

Rates of Estimation of Optimal Transport Maps using Plug-in Estimators via Barycentric Projections

Add code
Jul 04, 2021
Viaarxiv icon