betaFeedback

WorksMathematics

Schrödinger-Bass Bridge Barycenter Models for Measure-Valued Data

Abstract

Barycenter models, based on stochastic and deterministic optimal transport bridges between probability measures, have proven to be useful for supervised and unsupervised learning for (probability) measure-valued data. In this paper, we utilize the directional asymmetry and dual drift-diffusion control arising in the recently proposed Schrödinger-Bass Bridge (SBB) between two measures, and propose SBB-encoder, SBB-decoder, SBB-symmetric, and SBB-Markovian barycenter models. For each of these novel models, our first theoretical result establishes the existence of the SBB-barycenter under mild assumptions. Our second theoretical result characterizes the decoder SBB-barycenter of Gaussians where we show that for Gaussian input measures, the decoder formulation admits a Gaussian minimizer, reducing barycenter computation to a finite-dimensional optimization and yielding a compact algorithm. For general input measures, we derive a hybrid Wasserstein gradient particle descent scheme for all four formulations using the SBB dual representation. Finally, we utilize these algorithms for solving distributional-inverse/interpolation problems arising in the context of spatial images and single-cell RNA sequencing data, where we show that the SBB-decoder and Markovian barycenter allow us to interpolate between successive time points. Results show that our method outperforms existing barycenter models for measure interpolation and inference.

INTRODUCTION

Barycenter models, that use metrics and divergences between probability measures, provide a means for averaging and analyzing (probability) measure-valued data, where each observation may itself be a distribution rather than a single vector, in both supervised and unsupervised settings. Among the most popular models, are the Wasserstein barycenter model Xu et al. [ [43], Schmitz et al. [ [36], Werenski et al. [ [41], Cheng et al. [ [14] which defines a geometric average through optimal displacement, and Schrödinger-bridge based formulations which incorporate entropic regularization into the transport process Mallery et al. [ [31]. Other examples include Werenski et al. [ [42], Gunsilius et al. [ [21], Bai et al. [ [8]. Such models have proved useful whenever one seeks a representative distribution that summarizes several heterogeneous populations. However, in many applications, the observed distributions are not simply different realizations of the same population. Rather, they may arise from a common latent source through a combination of systematic transformation and stochastic dispersion. For instance, multiple cell populations can correspond to different stages of a developmental process, while several image distributions may share the same latent shape but differ through translation, rescaling, and spatial diffusion. In such settings, directly averaging the observed endpoint distributions may fail to recover the underlying latent structure, because the variability introduced by the observation process is itself part of the geometry that should be modeled. This motivates a barycenter construction that can distinguish deterministic transport from stochastic spreading. The recently introduced Schrödinger–Bass Bridge (SBB) provides exactly such a mechanism by jointly controlling the drift and the volatility of a stochastic process [24, 23]. Unlike the classical Schrödinger Bridge, whose volatility is fixed, SBB allows the diffusion component to adapt; unlike Bass martingale transport, it does not impose a zero-drift or convex-order constraint on the endpoints. Building on this flexibility, we introduce SBB barycenter models, in which a shared probability measure is connected to the input distributions through SBB bridges. Because the SBB cost is intrinsically asymmetric, the position of the barycenter relative to the input measures carries modeling meaning, leading naturally to encoder, decoder, symmetric, and Markovian formulations.

Main Contributions.

  • We introduce the encoder, decoder, symmetric, and Markovian SBB barycenter formulations and establish their existence on P2(Rd)\mathcal{P}_2(\mathbb{R}^d).

  • We derive the marginal first variations of the SBB objective. Using these we derive a hybrid Wasserstein gradient particle descent scheme that is orientation-specific, to solve these barycenter computation problems efficiently.

  • For the decoder SBB problem with Gaussian distributions, we present a static Gaussian projection result that reduces the decoder search to Gaussian laws, together with a covariance-action description for Gaussian pairs. We then specialize the particle update to means and covariances.

  • Finally, we provide two applications that showcase the utility of the SBB barycenter models: (1) Recovery of 2-D measures from geometric deformation and spatial blur; (2) Ancestor reconstruction and held-out interpolation reconstruction in single-cell RNA sequencing data. We show that SBB models and proposed methods significantly outperform existing barycenter models/methods and baselines.

RELATED WORK

Wasserstein barycenter and entropic regularization. Wasserstein barycenters average probability measures through optimal displacement [1], whose dynamic formulation minimizes kinetic transport energy [10]. Entropic regularization enabled scalable barycenter algorithms, notably the methods of Cuturi and Doucet [2014] and the iterative Bregman projections of Benamou et al. [2015]. At the same time, entropic regularization modifies the underlying averaging geometry: entropy terms that are constant when both marginals are fixed become nonconstant once one marginal is an optimized variable, and can therefore change the resulting barycenter. On studying EOT barycenter, debiased Sinkhorn barycenters [26] address the resulting entropic bias, while Chizat [2023] distinguishes regularization of the transport plans from an additional entropy penalty imposed directly on the barycenter. Mallery et al. [2025] studies the recovery of marginal measure weights through quadratic optimization.

In the Gaussian setting, Wasserstein barycenters inherit Gaussian structure with Bures–Wasserstein covariance geometry [1, 32], and related Gaussian closure and closed-form results are known for entropic transport [19, 30, 27, 13]. Computationally, prior barycenter methods include fixed-point schemes [5], first-order methods with convergence guarantees [4, 32], and particle descent for regularized barycenters [15].

Schrödinger bridges and multi-marginal barycenters. The Schrödinger problem originates with Schrödinger [1931] and connects entropy minimization to stochastic control [18, 29]. For a Brownian reference, the diffusion coefficient is prescribed and the drift is controlled. Multi-marginal extensions already provide stochastic formulations of distributional averaging: Haasler et al. [2021] study tree-structured transport costs and Schrödinger problems; Noble et al. [2023] develop TreeDSB and apply it to barycenters through a star-shaped construction; and Howard et al. [2025] extend bridge matching to tree-structured problems and entropic barycentres. Thus, coupling multiple distributions through a shared stochastic representation has attracted substantial attention in prior work.

Bass martingales and weak optimal transport. Bass’s stochastic-integral construction [9] underlies the martingale Benamou–Brenier problem studied by Backhoff-Veraguas et al. [ [7]. Here the drift is fixed to zero, volatility is optimized, and endpoint feasibility requires convex order. The static formulation belongs to weak optimal transport, where the cost depends on conditional distributions rather than only on pairs of points. General foundations were developed by Gozlan et al. [ [20] and Backhoff-Veraguas et al. [ [6]. This distinction is essential for SBB: its finite-parameter static cost is also a weak transport cost, but allowing nonzero drift removes the martingale convex-order restriction on its endpoints [23].

Schrödinger–Bass Bridge. Joint drift and diffusion control belongs to the broader theory of semimartingale optimal transport [39]. Within this framework, Alouadi et al. [ [3] give a one-dimensional PDE derivation of the Schrödinger–Bass bridge, while Henry-Labordère et al. [ [24] develop its semimartingale formulation, duality, and coupled bridge characterization. Hasenbichler et al. [ [23] establish an equivalent static weak-transport formulation and a dual-ascent computational scheme. On the computational side, Alouadi et al. [ [2] introduce LightSBB-M for sample-based pairwise bridge estimation. These works provide the pairwise theoretical foundations on which our work builds.

SCHRÖDINGER-BASS BRIDGE (SBB)

Let T>0T > 0 be lenght of time and let Ω=C([0,T],Rd)\Omega= C([0,T],\mathbb{R}^{d}) be the canonical space with a canonical process XX, i.e. Xt(ω)=ω(t)X_t(\omega) = \omega(t) for all ω∈Ω,t∈[0,T]\omega\in\Omega, t \in[0,T]. We denote by P=:P(Ω)\mathcal{P} =: \mathcal{P}(\Omega) the set of probability measures P\mathbb{P} on Ω\Omega under which XX has the controlled dynamic

dXt=αt dt+σt dWt,\mathrm{d}X_t = \alpha_t\,\mathrm{d}t + \sigma_t\,\mathrm{d}W_t,

with drift αt\alpha_t and volatility σt\sigma_t. Its action according to a specific law P\mathbb{P} is defined by

J(P)=EP∫0T[12∥αt∥2+β2∥σt−εId∥F2] dt.(1)J(\mathbb{P}) = \mathbb{E}_{\mathbb{P}}\int_{0}^{T} \left[\frac{1}{2}\lVert\alpha_t\rVert^{2} + \frac{\beta}{2}\lVert\sigma_t - \sqrt{\varepsilon}I_d\rVert_{F}^{2}\right]\,\mathrm{d}t. \tag*{(1)}

Let P2(Rd)\mathcal{P}_2(\mathbb{R}^{d}) denote the probability measures on Rd\mathbb{R}^{d} with a finite second moment. For two distributions μ,ν∈P2(Rd)\mu,\nu\in\mathcal{P}_2(\mathbb{R}^{d}), the Schrödinger–Bass cost [24, 23] is

SBB⁡β,ε,T(μ,ν)=inf⁡P∈P(Ω): X0∼μ, XT∼νJ(P).(2)\operatorname{SBB}_{\beta,\varepsilon,T}(\mu,\nu) = \inf_{\mathbb{P}\in\mathcal{P}(\Omega):\,X_0\sim\mu,\,X_T\sim\nu} J(\mathbb{P}). \tag*{(2)}

See Appendix § 11 for the comparison table of formulation between Schrödinger Bridge, Bass Martingale and SBB. The SBB unifies these two viewpoints by allowing both the drift (αt)(\alpha_t) and volatility (σt)(\sigma_t) to be controlled, thereby interpolating between entropic diffusion transport and martingale transport. Importantly, SBB is asymmetric. Indeed, let HTμ=μ∗N(0,τId)H_T\mu= \mu* \mathcal{N}(0,\tau I_d) with τ=εT\tau= \varepsilon T and ∗* is convolution operator. Consider αt=0,σt=εId\alpha_t = 0,\sigma_t = \sqrt{\varepsilon}I_d, leading to control dynamic dXt=ε dWt\mathrm{d}X_t = \sqrt{\varepsilon}\,\mathrm{d}W_t, X0∼μX_0 \sim\mu, which gives XT∼HTμX_T \sim H_T\mu and hence, SBB⁡(μ,HTμ)=0\operatorname{SBB}(\mu,H_T\mu)=0. Now reverse the endpoints. If a zero-cost process existed from HTμH_T\mu to μ\mu, then necessarily αt=0,σt=εId\alpha_t = 0,\sigma_t = \sqrt{\varepsilon}I_d almost everywhere, since both nonnegative terms in the SBB action would have to vanish. Starting instead from X0∼HTμX_0 \sim H_T\mu, this dynamic gives XT∼HT(HTμ)=H2Tμ≠μX_T \sim H_T(H_T\mu)=H_{2T}\mu\ne\mu for every μ∈P2(Rd)\mu\in\mathcal{P}_2(\mathbb{R}^{d}) whenever τ>0\tau> 0. Therefore the reverse transport SBB⁡(HTμ,μ)≠0\operatorname{SBB}(H_T\mu,\mu)\ne0. Thus SBB is asymmetric, hence not a metric. More properties of SBB appear in Appendix § 11.

PROPOSED SBB BARYCENTERS MODELS

Because the SBB cost is directed, the position of the barycenter variable in Equation (2) matters.

Given input measures μi∈P2(Rd)\mu_i \in\mathcal{P}_2(\mathbb{R}^{d}) and weights λi>0\lambda_i > 0 with ∑iλi=1\sum_i \lambda_i = 1, we define different oriented-based Barycenter models

  • Encoder Barycenter

ρenc∈arg⁡min⁡ρ∈P2(Rd)[Benc(ρ):=∑i=1NλiSBB⁡(μi,ρ)].(3)\rho_{\mathrm{enc}} \in\underset{\rho\in\mathcal{P}_2(\mathbb{R}^{d})}{\arg\min}\left[\mathcal{B}_{\mathrm{enc}}(\rho) := \sum_{i=1}^{N}\lambda_i\operatorname{SBB}(\mu_i,\rho)\right]. \tag*{(3)}
  • Decoder Barycenter

ρdec∈arg⁡min⁡ρ∈P2(Rd)[Bdec(ρ):=∑i=1NλiSBB⁡(ρ,μi)].(4)\rho_{\mathrm{dec}} \in\underset{\rho\in\mathcal{P}_2(\mathbb{R}^{d})}{\arg\min}\left[\mathcal{B}_{\mathrm{dec}}(\rho) := \sum_{i=1}^{N}\lambda_i\operatorname{SBB}(\rho,\mu_i)\right]. \tag*{(4)}
  • Symmetric Barycenter

ρsym∈arg⁡min⁡ρ∈P2(Rd)[Bsym(ρ):=12[Benc(ρ)+Bdec(ρ)]].(5)\rho_{\mathrm{sym}} \in\underset{\rho\in\mathcal{P}_2(\mathbb{R}^{d})}{\arg\min}\left[\mathcal{B}_{\mathrm{sym}}(\rho) := \frac{1}{2}\left[\mathcal{B}_{\mathrm{enc}}(\rho)+\mathcal{B}_{\mathrm{dec}}(\rho)\right]\right]. \tag*{(5)}

An encoder barycenter is a common terminal law reached from all input domains. A decoder barycenter learns a common source from which the inputs are generated by domain-specific bridges. The symmetric barycenter uses both directions and consequently avoids asymmetry. Also, when there are only two marginals, one for the initial and the other for the final time point, we can interpolate the marginal at an intermediate time point as the barycenter of the initial and final marginals (see our application in § 8.3 about single-cell RNA intermediate-state reconstruction). This motivates us to propose the following interpolation-variant of the barycenter:

  • SBB Markovian Barycenter

ρMar∈arg⁡min⁡ρ∈P2(Rd)[BMar(ρ):=λ1SBB⁡(μ1,ρ)+λ2SBB⁡(ρ,μ2)],(6)\rho_{\mathrm{Mar}} \in\arg\min_{\rho\in\mathcal{P}_2(\mathbb{R}^d)} \left[\mathcal{B}_{\mathrm{Mar}}(\rho) := \lambda_1 \operatorname{SBB}(\mu_1,\rho) + \lambda_2 \operatorname{SBB}(\rho,\mu_2)\right], \tag*{(6)}

where μ1\mu_1 and μ2\mu_2 are the initial and final marginals and λ1,λ2\lambda_1,\lambda_2 are non-negative weights.

Existence. We establish that these SBB barycenter formulations are well posed by proving the existence of minimizers. In particular, we have the following result

Theorem 4.1 (Existence). Let μ1,…,μN∈P2(Rd)\mu_1,\ldots,\mu_N \in\mathcal{P}_2(\mathbb{R}^d). Then the decoder barycenter problem 4 admits at least one minimizer in P2(Rd)\mathcal{P}_2(\mathbb{R}^d). The same conclusion holds for the encoder 3, symmetric 5 and Markovian 6 barycenter problem.

The full proof is provided in Appendix § 12.§ 1. We present the decoder case in detail, as it is technically more challenging. The encoder, symmetric and Markovian case follows essentially the same argument, as explained in the remark after the proof. The key ingredient is based on this inequality characterizing the bound of SBB using W2W_2

SBB⁡(ρ,μi)≥W22(ρ,μi)−4εdT4T+8/β.\operatorname{SBB}(\rho,\mu_i) \ge\frac{W_2^2(\rho,\mu_i)-4\varepsilon dT}{4T+8/\beta}.

We leave the question of uniqueness to future work.

A HYBRID WASSERSTEIN GRADIENT PARTICLE DESCENT SCHEME

The main goal of this section is to design an efficient numerical algorithm to solve for the SBB-Barycenter. Since the optimization problem is posed over probability measures, a natural direction is to employ a particle-based gradient scheme. We represent the current barycenter by ρk=M−1∑m=1MδXmk\rho^k = M^{-1}\sum_{m=1}^M \delta_{X_m^k} and update the particles XmkX_m^k instead. The update is done on manifold using Wasserstein gradient descent (WGD) (for the background, see Yang et al. [ [44]). Our key step is to compute the Wasserstein gradient of either SBB(μ,ρ)SBB(\mu,\rho) or SBB(ρ,μ)SBB(\rho,\mu) with respect to the variable measure ρ\rho. We show that for the SBB functional, its first variation may be expressible in terms of a suitable dual potential. If this dual potential can be computed for each term in the objective, then we can use its gradient to update the particles, yielding a practical particle-based scheme for approximating the barycenter.

First Variation of SBB and Update Rules

Alouadi et al. [ [2] proved the following dual variational characterization of the pairwise SBB

SBB⁡(μ0,μT)=sup⁡(ψ,v){∫ψ(x) μT(dx)−∫v(0,x) μ0(dx)}.(7)\operatorname{SBB}(\mu_0,\mu_T) = \sup_{(\psi,v)} \left\{\int\psi(x)\,\mu_T(\mathrm{d}x) - \int v(0,x)\,\mu_0(\mathrm{d}x)\right\}. \tag*{(7)}

The function vv solves the associated backward Hamilton–Jacobi–Bellman (HJB) equation with v(T,⋅)=ψv(T,\cdot)=\psi and curvature constraint D2v≺βIdD^2v \prec\beta I_d. The reduced SBB system introduces heat potentials ht∗h_t^* and maps YtY_t through

References

  1. [1]Martial Agueh and Guillaume Carlier. Barycenters in the wasserstein space. SIAM Journal on Mathematical Analysis, 43(2):904–924, 2011.DOI
  2. [2]Alexandre Alouadi, Pierre Henry-Labordère, Grégoire Looper, Othmane Mazhar, Huyền Pham, and Nizar Touzi. LightSBB: Bridging Schrödinger and Bass for generative diffusion modeling, 2026a. URL https://arxiv.org/abs/2601.19312v2. Version 2, May 5, 2026.
  3. [3]Alexandre Alouadi, Pierre Henry-Labordère, Grégoire Looper, Othmane Mazhar, Huyền Pham, and Nizar Touzi. A PDE derivation of the Schrödinger–Bass bridge, 2026b. URL https://arxiv.org/abs/2601.17863v1.
  4. [4]Jason M. Altschuler, Sinho Chewi, Patrik R. Gerber, and Austin J. Stromme. Averaging on the Bures–Wasserstein manifold: Dimension-free convergence of gradient descent. In Advances in Neural Information Processing Systems, volume 34, pages 22132–22145, 2021. URL https://proceedings.neurips.cc/paper_files/paper/2021/hash/b9acb4ae6121c941324b2b1d3fac5c30-Abstract.html.arxiv.org/abs/2106.08502
  5. [5]Pedro C. Álvarez-Esteban, Eustasio del Barrio, J. A. Cuesta-Albertos, and Carlos Matrán. A fixed-point approach to barycenters in Wasserstein space. Journal of Mathematical Analysis and Applications, 441(2):744–762, 2016. doi: 10.1016/j.jmaa.2016.04.045.
  6. [6]Julio Backhoff-Veraguas, Mathias Beiglböck, and Gudmund Pammer. Existence, duality, and cyclical monotonicity for weak transport costs. Calculus of Variations and Partial Differential Equations, 58(6):203, 2019. doi: 10.1007/s00526-019-1624-y.
  7. [7]Julio Backhoff-Veraguas, Mathias Beiglböck, Martin Huesmann, and Sigrid Källblad. Martingale Benamou–Brenier: A probabilistic perspective. The Annals of Probability, 48(5):2258–2289, 2020. doi: 10.1214/20-AOP1422.
  8. [8]Yikun Bai, Ivan Vladimir Medri, Rocio Diaz Martin, Rana Shahroz, and Soheil Kolouri. Linear optimal partial transport embedding. In International Conference on Machine Learning, pages 1492–1520. PMLR, 2023.arxiv.org/abs/2302.03232
  9. [9]Richard F. Bass. Skorokhod embedding via stochastic integrals. Séminaire de Probabilités, 17:221–224, 1983. URL https://www.numdam.org/item/SPS_1983__17__221_0/.DOI
  10. [10]Jean-David Benamou and Yann Brenier. A computational fluid mechanics solution to the Monge–Kantorovich mass transfer problem. Numerische Mathematik, 84:375–393, 2000. doi: 10.1007/s002110050002.
  11. [13]Charlotte Bunne, Ya-Ping Hsieh, Marco Cuturi, and Andreas Krause. The Schrödinger bridge between Gaussian measures has a closed form. In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics, volume 206 of Proceedings of Machine Learning Research, pages 5802–5833, 2023. URL https://proceedings.mlr.press/v206/bunne23a.html.
  12. [14]Kevin Cheng, Shuchin Aeron, Michael C Hughes, and Eric L Miller. Dynamical wasserstein barycenters for time-series modeling. Advances in Neural Information Processing Systems, 34:27991–28003, 2021.
  13. [15]Lénaïc Chizat. Doubly regularized entropic Wasserstein barycenters, 2023. URL https://arxiv.org/abs/2303.11844.
  14. [17]Marco Cuturi and Arnaud Doucet. Fast computation of Wasserstein barycenters. In Proceedings of the 31st International Conference on Machine Learning, volume 32 of Proceedings of Machine Learning Research, pages 685–693, 2014. URL https://proceedings.mlr.press/v32/cuturi14.html.arxiv.org/abs/1310.4375
  15. [18]Paolo Dai Pra. A stochastic control approach to reciprocal diffusion processes. Applied Mathematics and Optimization, 23:313–329, 1991. doi: 10.1007/BF01442404.
  16. [19]Eustasio del Barrio and Jean-Michel Loubes. The statistical effect of entropic regularization in optimal transportation. arXiv preprint arXiv:2006.05199, 2020.
  17. [20]Nathaël Gozlan, Cyril Roberto, Paul-Marie Samson, and Prasad Tetali. Kantorovich duality for general transport costs and applications. Journal of Functional Analysis, 273(11):3327–3405, 2017. doi: 10.1016/j.jfa.2017.08.015.
  18. [21]Florian Gunsilius, Meng Hsuan Hsieh, and Myung Jin Lee. Tangential wasserstein projections. Journal of Machine Learning Research, 25(69):1–41, 2024. URL http://jmlr.org/papers/v25/23-0708.html.
  19. [23]Manuel Hasenbichler, Gudmund Pammer, and Stefan Thonhauser. A weak transport approach to the Schrödinger–Bass bridge, 2026. URL https://arxiv.org/abs/2604.02312v2. Version 2, June 30, 2026.
  20. [24]Pierre Henry-Labordère, Grégoire Loeper, Othmane Mazhar, Huyền Pham, and Nizar Touzi. Bridging Schrödinger and Bass: A semimartingale optimal transport problem with diffusion control, 2026. URL https://arxiv.org/abs/2603.27712v2. Version 2, May 29, 2026.
  21. [26]Hicham Janati, Marco Cuturi, and Alexandre Gramfort. Debiased Sinkhorn barycenters. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 4692–4701, 2020a. URL https://proceedings.mlr.press/v119/janati20a.html.
  22. [27]Hicham Janati, Boris Muzellec, Gabriel Peyré, and Marco Cuturi. Entropic optimal transport between unbalanced Gaussian measures has a closed form. In Advances in Neural Information Processing Systems, volume 33, 2020b. URL https://proceedings.neurips.cc/paper/2020/hash/766e428d1e232bbdd58664b41346196c-Abstract.html.
  23. [29]Christian Léonard. A survey of the Schrödinger problem and some of its connections with optimal transport. Discrete and Continuous Dynamical Systems, 34(4):1533–1574, 2014. doi: 10.3934/dcds.2014.34.1533.DOI
  24. [30]Anton Mallasto, Augusto Gerolin, and Hà Quang Minh. Entropy-regularized 2-Wasserstein distance between Gaussian measures. Information Geometry, 5:289–323, 2022. doi: 10.1007/s41884-021-00052-8.DOI
  25. [31]Brendan Mallery, James M Murphy, and Shuchin Aeron. Synthesis and analysis of data as probability measures with entropy-regularized optimal transport. arXiv preprint arXiv:2501.07446, 2025.arxiv.org/abs/2501.07446
  26. [32]Ngoc-Hai Nguyen, Hoang-Phi Nguyen, Tung Pham, Nhat Ho, et al. On barycenter computation: Analyzing semi-unbalanced optimal transport-based method on bures-wasserstein manifold. In The 29th International Conference on Artificial Intelligence and Statistics, 2025.
  27. [36]Morgan A Schmitz, Matthieu Heitz, Nicolas Bonneel, Fred Ngole, David Coeurjolly, Marco Cuturi, Gabriel Peyré, and Jean-Luc Starck. Wasserstein dictionary learning: Optimal transport-based unsupervised nonlinear dictionary learning. SIAM Journal on Imaging Sciences, 11(1):643–678, 2018.
  28. [39]Xiaolu Tan and Nizar Touzi. Optimal transportation under controlled stochastic dynamics. The Annals of Probability, 41(5):3201–3240, 2013. doi: 10.1214/12-AOP797.DOI
  29. [40]Alexander Tong, Jessie Huang, Guy Wolf, David Van Dijk, and Smita Krishnaswamy. Trajectorynet: A dynamic optimal transport network for modeling cellular dynamics. In International conference on machine learning, pages 9526–9536. PMLR, 2020.arxiv.org/abs/2002.04461
  30. [41]Matthew Werenski, Ruijie Jiang, Abiy Tasissa, Shuchin Aeron, and James M Murphy. Measure estimation in the barycentric coding model. In International Conference on Machine Learning, pages 23781–23803. PMLR, 2022.arxiv.org/abs/2201.12195
  31. [42]Matthew Werenski, Brendan Mallery, Shuchin Aeron, and James M. Murphy. Linearized wasserstein barycenters: Synthesis, analysis, representational capacity, and applications. In The 28th International Conference on Artificial Intelligence and Statistics, 2025. URL https://openreview.net/forum?id=MWCHed0m2L.arxiv.org/abs/2410.23602
  32. [43]Hongteng Xu, Wenlin Wang, Wei Liu, and Lawrence Carin. Distilled wasserstein learning for word embedding and topic modeling. Advances in Neural Information Processing Systems, 31, 2018.arxiv.org/abs/1809.04705
  33. [44]Yibo Yang, Stephan Eckstein, Marcel Nutz, and Stephan Mandt. Estimating the rate-distortion function by Wasserstein gradient descent. In Advances in Neural Information Processing Systems, volume 36, pages 2768–2794, 2023. URL https://arxiv.org/abs/2310.18908.

Paper details

vlnc:W_43c2pswn
Version
v1 · latest
Published
Fresh — added to the Hub within the last 30 days
Added
License
CC BY 4.0
Usage

views · 0

downloads · 0

A view counts once per browser per day, a download each time the PDF is requested.

  • Mathematics

Not recorded for this paper

View statement
Looking for related papers…
Contents