Showing 2024Show all
3 papers · 1 filter
stat.ML2024
The Benefits of Balance: From Information Projections to Variance Reduction
Lang Liu, Ronak Mehta, Soumik Pal +1
Data balancing across multiple modalities and sources appears in various forms in foundation models in machine learning and AI, e.g. in CLIP and DINO. We show that data balancing a…
math.PR2024
Iterated Schrödinger bridge approximation to Wasserstein Gradient Flows
Medha Agarwal, Zaid Harchaoui, Garrett Mulcahy +1
We introduce a novel discretization scheme for Wasserstein gradient flows that involves successively computing Schrödinger bridges with the same marginals. This is different from b…
math.PR2024
Limiting partition function for the Mallows model: a conjecture and partial evidence
Soumik Pal
Let denote the set of permutations of labels. We consider a class of Gibbs probability models on that is a subfamily of the so-called Mallows model of random permut…