5 citations · 13 across the 13 of their papers we have counts for
8 papers · 1 filter
Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization
Ziyu Gong, Jim Lim, David I. Inouye
Distribution matching (DM) is a versatile domain-invariant representation learning technique that has been applied to tasks such as fair classification, domain adaptation, and doma…
Robust Collaborative Inference with Vertically Split Data Over Dynamic Device Environments
Surojit Ganguli, Zeyu Zhou, Christopher G. Brinton +1
When each edge device of a network only perceives a local part of the environment, collaborative inference across multiple devices is often needed to predict global properties of t…
Towards Practical Non-Adversarial Distribution Matching
Ziyu Gong, Ben Usman, Han Zhao +1
Distribution matching can be used to learn invariant representations with applications in fairness and robustness. Most prior works resort to adversarial matching methods but the r…
Benchmarking Algorithms for Federated Domain Generalization
Ruqi Bai, Saurabh Bagchi, David I. Inouye
While prior domain generalization (DG) benchmarks consider train-test dataset heterogeneity, we evaluate Federated DG which introduces federated learning (FL) specific challenges.…
Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models
Zeyu Zhou, Ruqi Bai, Sean Kulinski +2
Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when the causal variables are unobserved and the obs…
Discrete Tree Flows via Tree-Structured Permutations
Mai Elkady, Jim Lim, David I. Inouye
While normalizing flows for continuous data have been extensively researched, flows for discrete data have only recently been explored. These prior models, however, suffer from lim…
Cooperative Distribution Alignment via JSD Upper Bound
Wonwoong Cho, Ziyu Gong, David I. Inouye
Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned distribution given only samples from each distribution…
Iterative Alignment Flows
Zeyu Zhou, Ziyu Gong, Pradeep Ravikumar +1
The unsupervised task of aligning two or more distributions in a shared latent space has many applications including fair representations, batch effect mitigation, and unsupervised…