3 papers
cs.LG2026
Memory-Efficient Differentially Private Training with Gradient Random Projection
Alex Mulrooney, Devansh Gupta, James Flemings +4
Differential privacy (DP) protects sensitive data during neural network training, but standard methods like DP-Adam suffer from high memory overhead due to per-sample gradient clip…
math.NA2026
Generalized Canonical Polyadic Tensor Decompositions with General Symmetry
Alex Mulrooney, David Hong
Canonical Polyadic (CP) tensor decomposition is a workhorse algorithm for discovering underlying low-dimensional structure in tensor data. This is accomplished in conventional CP d…
cs.CV2024
Contrastive Learning to Fine-Tune Feature Extraction Models for the Visual Cortex
Alex Mulrooney, Austin J. Brockmeier
Predicting the neural response to natural images in the visual cortex requires extracting relevant features from the images and relating those feature to the observed responses. In…