3 papers
stat.ML2026
Detecting Metastable Basins in High Dimensions via Marginal Trajectory Distribution Discrimination
Taj Jones-McCormick
We study the problem of identifying dynamically distinct basins of attraction in high dimensional time-homogeneous Markov processes using only trajectory sampling. This problem is…
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…
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…