Search Results for author: Samuel K. Ainsworth

Found 3 papers, 1 papers with code

Git Re-Basin: Merging Models modulo Permutation Symmetries

3 code implementations11 Sep 2022 Samuel K. Ainsworth, Jonathan Hayase, Siddhartha Srinivasa

The success of deep learning is due in large part to our ability to solve certain massive non-convex optimization problems with relative ease.

Linear Mode Connectivity Re-basin

oi-VAE: Output Interpretable VAEs for Nonlinear Group Factor Analysis

no code implementations ICML 2018 Samuel K. Ainsworth, Nicholas J. Foti, Adrian K. C. Lee, Emily B. Fox

Deep generative models have recently yielded encouraging results in producing subjectively realistic samples of complex data.

Disentangled VAE Representations for Multi-Aspect and Missing Data

no code implementations24 Jun 2018 Samuel K. Ainsworth, Nicholas J. Foti, Emily B. Fox

Many problems in machine learning and related application areas are fundamentally variants of conditional modeling and sampling across multi-aspect data, either multi-view, multi-modal, or simply multi-group.

Disentanglement Sentence

Cannot find the paper you are looking for? You can Submit a new open access paper.