MLLGGNFeb 8, 2023

Monge, Bregman and Occam: Interpretable Optimal Transport in High-Dimensions with Feature-Sparse Maps

Apple
arXiv:2302.04065v119 citationsh-index: 51
Originality Incremental advance
AI Analysis

This work addresses the challenge of interpretability in high-dimensional optimal transport for applications like genomics, offering a method to retain gene-level insights, though it is incremental in building on existing entropic map approaches.

The authors tackled the problem of estimating interpretable optimal transport maps in high-dimensional spaces by proposing a new model that uses sparsity-inducing regularizers to produce feature-sparse displacement vectors, enabling meaningful analysis of single-cell transcription data in a 34,000-dimensional gene count space without dimensionality reduction.

Optimal transport (OT) theory focuses, among all maps $T:\mathbb{R}^d\rightarrow \mathbb{R}^d$ that can morph a probability measure onto another, on those that are the ``thriftiest'', i.e. such that the averaged cost $c(x, T(x))$ between $x$ and its image $T(x)$ be as small as possible. Many computational approaches have been proposed to estimate such Monge maps when $c$ is the $\ell_2^2$ distance, e.g., using entropic maps [Pooladian'22], or neural networks [Makkuva'20, Korotin'20]. We propose a new model for transport maps, built on a family of translation invariant costs $c(x, y):=h(x-y)$, where $h:=\tfrac{1}{2}\|\cdot\|_2^2+τ$ and $τ$ is a regularizer. We propose a generalization of the entropic map suitable for $h$, and highlight a surprising link tying it with the Bregman centroids of the divergence $D_h$ generated by $h$, and the proximal operator of $τ$. We show that choosing a sparsity-inducing norm for $τ$ results in maps that apply Occam's razor to transport, in the sense that the displacement vectors $Δ(x):= T(x)-x$ they induce are sparse, with a sparsity pattern that varies depending on $x$. We showcase the ability of our method to estimate meaningful OT maps for high-dimensional single-cell transcription data, in the $34000$-$d$ space of gene counts for cells, without using dimensionality reduction, thus retaining the ability to interpret all displacements at the gene level.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes