2 papers
cs.LG2026
Functional Degeneracy in Neural Networks: Measurement and Pruning
Maria Matveev, Pascal Esser, Ayush Bharadwaj +2
A central question in modern machine learning is how much a trained model can be compressed without changing its behavior, to reduce the memory, compute and energy required to depl…
math.AG2023
Complex Critical Points of Deep Linear Neural Networks
Ayush Bharadwaj, Serkan Hoşten
We extend the work of Mehta, Chen, Tang, and Hauenstein on computing the complex critical points of the loss function of deep linear neutral networks when the activation function i…