16 citations · 37 across the 9 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Contrast encodes inductive bias: separating slow noise from dynamics in predictive representation learning
Paarth Gulati, Ilya Nemenman
Self-supervised methods that learn representations and predict dynamics fully in the latent space, such as JEPA, have been shown to confuse slowly varying noise with the dynamical…
cs.LG2026
Mutual information and task-relevant latent dimensionality
Paarth Gulati, Eslam Abdelaleem, Audrey Sederberg +1
Estimating the dimensionality of the latent representation needed for prediction -- the task-relevant dimension -- is a difficult, largely unsolved problem with broad scientific ap…