246 citations · 1k across the 29 of their papers we have counts for
31 papers
Fidelity-Diversity Metrics for Text
Amanda Wang, Tudor Manole, Florentina Bunea +1
As language modeling technology matures, there is an increasing research focus on the composition and curation of datasets used to train these models. For instance, practitioners c…
Beyond entropic regularization: Debiased Gaussian estimators for discrete optimal transport and general linear programs
Shuyu Liu, Florentina Bunea, Jonathan Niles-Weed
This work proposes new estimators for discrete optimal transport plans that enjoy Gaussian limits centered at the true solution. This behavior stands in stark contrast with the per…
The EM-algorithm and the Method of Moments in Softmax Mixture Models
Xin Bing, Florentina Bunea, Jonathan Niles-Weed +1
Softmax Mixture Models (SMMs) are discrete -component mixture models for the probabilities of selecting one of candidate feature vectors in h…
Asymptotic confidence sets for random linear programs
Shuyu Liu, Florentina Bunea, Jonathan Niles-Weed
Motivated by the statistical analysis of the discrete optimal transport problem, we prove distributional limits for the solutions of linear programs with random constraints. Such l…
Estimation and inference for the Wasserstein distance between mixing measures in topic models
Xin Bing, Florentina Bunea, Jonathan Niles-Weed
The Wasserstein distance between mixing measures has come to occupy a central place in the statistical analysis of mixture models. This work proposes a new canonical interpretation…
Likelihood estimation of sparse topic distributions in topic models and its applications to Wasserstein document distance calculations
Xin Bing, Florentina Bunea, Seth Strimas-Mackey +1
This paper studies the estimation of high-dimensional, discrete, possibly sparse, mixture models in topic models. The data consists of observed multinomial counts of words acro…