12 citations · 22 across the 11 of their papers we have counts for
3 papers · 1 filter
Neural collapse with unconstrained features
Dustin G. Mixon, Hans Parshall, Jianzong Pi
Neural collapse is an emergent phenomenon in deep learning that was recently discovered by Papyan, Han and Donoho. We propose a simple "unconstrained features model" in which neura…
Lie PCA: Density estimation for symmetric manifolds
Jameson Cahill, Dustin G. Mixon, Hans Parshall
We introduce an extension to local principal component analysis for learning symmetric manifolds. In particular, we use a spectral method to approximate the Lie algebra correspondi…
Uniquely optimal codes of low complexity are symmetric
Emily J. King, Dustin G. Mixon, Hans Parshall +1
We formulate explicit predictions concerning the symmetry of optimal codes in compact metric spaces. This motivates the study of optimal codes in various spaces where these predict…