Muawiz Chaudhary
muawizc.bsky.social
Muawiz Chaudhary
@muawizc.bsky.social
Mila

I do work in Computer Vision, Science For Deep Learning

Lookin to go to grad school
December 15, 2024 at 5:14 PM
Check out also our work which investigates holding the initialization of a convolution fixed while learning a structured covariance part.

Our 2nd paper uses this to sample trained DNNs and investigate eigenvalue distributions.

openreview.net/forum?id=bvJ...
openreview.net/forum?id=vWh...
Learning Stochastic Rainbow Networks
Random feature models are a popular approach for studying network learning that can capture important behaviors while remaining simpler than traditional training. Guth et al. [2024] introduced...
openreview.net
December 11, 2024 at 10:24 PM
A similar result is found in "A Rainbow in Deep Network Black Boxes". The initialization of networks stays the same over training and whats learned is the covariance. See figure 10 and pages 33-36. arxiv.org/pdf/2305.18512 @florentinguth.bsky.social
arxiv.org
December 11, 2024 at 10:24 PM
I'd like to be added :)
November 28, 2024 at 4:38 PM
always happy to chat about this work
November 27, 2024 at 4:52 PM