HyCNNs are a new architecture that learns convex functions with exponentially fewer parameters than ICNNs and outperforms them in convex regression and high-dimensional optimal transport on synthetic and single-cell RNA data.
Optimal transport tools (OTT): A JAX toolbox for all things Wasserstein
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A new constrained gradient flow on the space of transport maps converges to the OT map and enables more stable and accurate training of convexity-constrained neural networks for learning Monge maps.
FlashSinkhorn delivers up to 32x forward and 161x end-to-end speedups for entropic OT on A100 GPUs via IO-aware Triton kernels that fuse log-domain updates and streaming transport application.
Develops the first provably convergent stochastic fixed-point algorithm for free-support 2-Wasserstein barycenters of continuous measures under Caffarelli regularity, using a modified entropic OT map estimator.
cuRegOT is a new GPU solver for entropic OT that delivers speedups over prior GPU methods via amortized analysis, asynchronous iterates, and fused kernels, backed by convergence guarantees.
citing papers explorer
-
Hyper Input Convex Neural Networks for Shape Constrained Learning and Optimal Transport
HyCNNs are a new architecture that learns convex functions with exponentially fewer parameters than ICNNs and outperforms them in convex regression and high-dimensional optimal transport on synthetic and single-cell RNA data.
-
Learning Monge maps with constrained drifting models
A new constrained gradient flow on the space of transport maps converges to the OT map and enables more stable and accurate training of convexity-constrained neural networks for learning Monge maps.
-
FlashSinkhorn: IO-Aware Entropic Optimal Transport on GPU
FlashSinkhorn delivers up to 32x forward and 161x end-to-end speedups for entropic OT on A100 GPUs via IO-aware Triton kernels that fuse log-domain updates and streaming transport application.
-
Provably convergent stochastic fixed-point algorithm for free-support Wasserstein barycenter of continuous non-parametric measures
Develops the first provably convergent stochastic fixed-point algorithm for free-support 2-Wasserstein barycenters of continuous measures under Caffarelli regularity, using a modified entropic OT map estimator.
-
cuRegOT: A GPU-Accelerated Solver for Entropic-Regularized Optimal Transport
cuRegOT is a new GPU solver for entropic OT that delivers speedups over prior GPU methods via amortized analysis, asynchronous iterates, and fused kernels, backed by convergence guarantees.