14 citations · 25 across the 27 of their papers we have counts for
14 papers · 1 filter
Primal-Dual Flow Matching for Sample-Wise Constrained Generation
Zhengyan Huan, Peter Y. Lu, Shuchin Aeron
We consider the problem of learning to generate data while satisfying a prescribed \emph{sample-wise} constraint with a user-specified probability of constraint satisfaction. Start…
Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets
Thuan Nguyen, Shuchin Aeron, D. Richard Brown +1
In this paper, we provide a computable characterization of the geometry of optimal representations in Contrastive Learning (CL) when the classes are imbalanced. When classes are ba…
Inverse Problems Conditioned on Observation Ensembles: Applications and Methods
Zhengyan Huan, Camila Pazos, Martin Klassen +3
We introduce a new multivariate statistical problem that we refer to as the Ensemble-conditioned Inverse Problem (EIP). The aim of EIP is to invert for an ensemble that is distribu…
Generative Modeling with Continuous Flows: Sample Complexity of Flow Matching
Mudit Gaur, Prashant Trivedi, Shuchin Aeron +3
Flow matching has recently emerged as a promising alternative to diffusion-based generative models, offering faster sampling and simpler training by learning continuous flows gover…
Constraint-Aware Flow Matching via Randomized Exploration
Zhengyan Huan, Jacob Boerma, Li-Ping Liu +1
We consider the problem of designing constraint-aware flow matching (FM) models that address the issue of constraint violations commonly observed in vanilla generative models. We c…
Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse
Ruijie Jiang, Thuan Nguyen, Shuchin Aeron +1
For a widely-studied data model and general loss and sample-hardening functions we prove that the losses of Supervised Contrastive Learning (SCL), Hard-SCL (HSCL), and Unsupervised…
A principled approach to model validation in domain generalization
Boyang Lyu, Thuan Nguyen, Matthias Scheutz +2
Domain generalization aims to learn a model with good generalization ability, that is, the learned model should not only perform well on several seen domains but also on unseen dom…
Trade-off between reconstruction loss and feature alignment for domain generalization
Thuan Nguyen, Boyang Lyu, Prakash Ishwar +2
Domain generalization (DG) is a branch of transfer learning that aims to train the learning models on several seen domains and subsequently apply these pre-trained models to other…
Geometric Sparse Coding in Wasserstein Space
Marshall Mueller, Shuchin Aeron, James M. Murphy +1
Wasserstein dictionary learning is an unsupervised approach to learning a collection of probability distributions that generate observed distributions as Wasserstein barycentric co…
Supervised Contrastive Learning with Hard Negative Samples
Ruijie Jiang, Thuan Nguyen, Prakash Ishwar +1
Through minimization of an appropriate loss function such as the InfoNCE loss, contrastive learning (CL) learns a useful representation function by pulling positive samples close t…
Joint covariate-alignment and concept-alignment: a framework for domain generalization
Thuan Nguyen, Boyang Lyu, Prakash Ishwar +2
In this paper, we propose a novel domain generalization (DG) framework based on a new upper bound to the risk on the unseen domain. Particularly, our framework proposes to jointly…
Conditional entropy minimization principle for learning domain invariant representation features
Thuan Nguyen, Boyang Lyu, Prakash Ishwar +2
Invariance-principle-based methods such as Invariant Risk Minimization (IRM), have recently emerged as promising approaches for Domain Generalization (DG). Despite promising theory…
Hard Negative Sampling via Regularized Optimal Transport for Contrastive Representation Learning
Ruijie Jiang, Prakash Ishwar, Shuchin Aeron
We study the problem of designing hard negative sampling distributions for unsupervised contrastive representation learning. We propose and analyze a novel min-max framework that s…
Barycentric-alignment and reconstruction loss minimization for domain generalization
Boyang Lyu, Thuan Nguyen, Prakash Ishwar +2
This paper advances the theory and practice of Domain Generalization (DG) in machine learning. We consider the typical DG setting where the hypothesis is composed of a representati…