collaborators

9 papers

stat.ML2026

High-dimensional limit theorems for SGD: Momentum and Adaptive Step-sizes

Aukosh Jagannath, Taj Jones-McCormick, Varnan Sarangian

We develop a high-dimensional scaling limit for Stochastic Gradient Descent with Polyak Momentum (SGD-M) and adaptive step-sizes. This provides a framework to rigourously compare o…

math.ST2026

Local geometry of high-dimensional mixture models: Effective spectral theory and dynamical transitions

Gerard Ben Arous, Reza Gheissari, Jiaoyang Huang +1

We study the local geometry of empirical risks in high dimensions via the spectral theory of their Hessian and information matrices. We focus on settings where the data, $(Y_\ell)_…

stat.ML2025

Universality of high-dimensional scaling limits of stochastic gradient descent

Reza Gheissari, Aukosh Jagannath

We consider statistical tasks in high dimensions whose loss depends on the data only through its projection into a fixed-dimensional subspace spanned by the parameter vectors and c…

math.ST2025

Pseudo-Maximum Likelihood Theory for High-Dimensional Rank One Inference

Curtis Grant, Aukosh Jagannath, Justin Ko

We develop a pseudo-likelihood theory for rank one matrix estimation problems in the high dimensional limit. We prove a variational principle for the limiting pseudo-maximum likeli…

math.ST2025

Differentially private multivariate medians

Kelly Ramsay, Aukosh Jagannath, Shoja'eddin Chenouri

Statistical tools which satisfy rigorous privacy guarantees are necessary for modern data analysis. It is well-known that robustness against contamination is linked to differential…

stat.ML2025

Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models

Taj Jones-McCormick, Aukosh Jagannath, Subhabrata Sen

Unsupervised pre-training and transfer learning are commonly used techniques to initialize training algorithms for neural networks, particularly in settings with limited labeled da…