Taj Jones-McCormick — accepted AI-conference papers

2026

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

Aukosh Jagannath, Taj Jones-McCormick, Varnan Sarangian

ICLR 2026poster

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 online SGD with some of its popular variants. We show that the scaling limits of SGD-M coincide with those of online SGD…

Cited by 0 Source ↗Scholar ↗

2025

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

Taj Jones-McCormick, Aukosh Jagannath, Subhabrata Sen

ICML 2025spotlight

Unsupervised pre-training and transfer learning are commonly used techniques to initialize training algorithms for neural networks, particularly in settings with limited labeled data. In this paper, we study the effects of unsupervised pre-training and transfer learning on the sample complexity of h…

Cited by 0 Source ↗PDF ↗Scholar ↗