A KL-relaxed formulation of bi-causal optimal transport is solved via policy gradients with proven convergence to the original problem and nonasymptotic regret guarantees for the resulting algorithm.
To establish the second equivalent representation, notice thatγ ϵ ∈ M bc(µ, µ′)⊂Π ΠΠbc and Wbc(µ, µ′) = inf π0∈Π(µ0,µ′
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scalable Bi-causal Optimal Transport via KL Relaxation and Policy Gradients
A KL-relaxed formulation of bi-causal optimal transport is solved via policy gradients with proven convergence to the original problem and nonasymptotic regret guarantees for the resulting algorithm.