Pheno-GS: Phenoscape-scale Geodesic Sinkhorn

arXiv:2609.27633 · cs.LG, q-bio.QM · Submitted 2026-09-23 · Read on arXiv

cs.LG, q-bio.QM

Submitted: 2026-09-23

Updated: 2026-10-01

Comments: Camera-ready version accepted at IEEE MLSP 2026; notation corrections to mathematical typesetting

Code: https://github.com/KrishnaswamyLab/PhenoGS

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Optimal Transport — 8× in this paper · explained in 5 episodes
• Regularization — 6× in this paper · explained in 3 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Phenoscape-scale Geodesic Sinkhorn — 3× in this paper
• Alignment — 2× in this paper · explained in 1 episode
• Embeddings — 2× in this paper · explained in 2 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Wasserstein Distance — 2× in this paper · explained in 4 episodes
• 2-Wasserstein Distance — 1× in this paper · explained in 1 episode
• Adjacency Matrix — 1× in this paper · explained in 1 episode
• Chebyshev Polynomials — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Graph Connectivity Regularization Module — 1× in this paper
• Graph Construction — 1× in this paper · explained in 3 episodes
• Optimal Transport (OT) — 1× in this paper · explained in 4 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Sinkhorn Divergences for Unbalanced Optimal Transport

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks