PINS combines an outer proximal-point loop over shifted entropic OT problems with inner Sinkhorn warm-up and sparse-Newton refinement to reach unregularized OT solutions with global convergence and lower error than Sinkhorn baselines.
Computational optimal transport: With applications to data science
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
A mean-field dynamical analysis of LoRA in transformers identifies phase transitions in catastrophic forgetting driven by perturbation norm and transformer depth.
citing papers explorer
-
PINS: Proximal Iterations with Sparse Newton and Sinkhorn for Optimal Transport
PINS combines an outer proximal-point loop over shifted entropic OT problems with inner Sinkhorn warm-up and sparse-Newton refinement to reach unregularized OT solutions with global convergence and lower error than Sinkhorn baselines.
-
Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics
A mean-field dynamical analysis of LoRA in transformers identifies phase transitions in catastrophic forgetting driven by perturbation norm and transformer depth.