2 papers
cs.LG2026
How Controlling the Variance can Improve Training Stability of Sparsely Activated DNNs and CNNs
Emily Dent, Jared Tanner
The Edge-of-Chaos (EoC) theory developed for the random initialization of deep networks allows more efficient training by both preserving information in the initial outputs of the…
cs.LG2026
Theory of Minimal Weight Perturbations in Deep Networks and its Applications for Low-Rank Activated Backdoor Attacks
Bethan Evans, Jared Tanner
The minimal norm weight perturbations of DNNs required to achieve a specified change in output are derived and the factors determining its size are discussed. These single-layer ex…