pith. sign in

arxiv: 2202.01571 · v2 · pith:T6PZ3K75new · submitted 2022-02-03 · 🧮 math.OC · cs.LG· math.AG

Toric Geometry of Entropic Regularization

classification 🧮 math.OC cs.LGmath.AG
keywords entropicregularizationtoriclinearoptimalstartingalgorithmsanalytic
0
0 comments X
read the original abstract

Entropic regularization is a method for large-scale linear programming. Geometrically, one traces intersections of the feasible polytope with scaled toric varieties, starting at the Birch point. We compare this to log-barrier methods, with reciprocal linear spaces, starting at the analytic center. We revisit entropic regularization for unbalanced optimal transport, and we develop the use of optimal conic couplings. We compute the degree of the associated toric variety, and we explore algorithms like iterative scaling.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.