Support Topology and Gradient Mixing in Sinkhorn Layers
Quick summary
arXiv:2609.07954v1 Announce Type: new Abstract: Sparse Sinkhorn layers use a fixed support graph to restrict transport between tokens. How does this graph control gradient propagation through the scaling iterations. We develop a fixed-support calculus showing that each row-column cycle induces a row-stochastic operator on column-potential perturbations modulo constants. Its transpose propagates zero-mass reverse-mode cotangents. The finite-cycle operator uses two distinct half-step transport plans; at a balanced fixed point it reduces to a two-step walk determined by a single plan. We derive t
Key takeaways
- arXiv:2609.07954v1 Announce Type: new Abstract: Sparse Sinkhorn layers use a fixed support graph to restrict transport between tokens.
- How does this graph control gradient propagation through the scaling iterations.
- We develop a fixed-support calculus showing that each row-column cycle induces a row-stochastic operator on column-potential perturbations modulo constants.
Why it matters
The importance of “Support Topology and Gradient Mixing in Sinkhorn Layers” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments