pith. sign in

arxiv: 2606.27626 · v1 · pith:RFPV2IR2new · submitted 2026-06-26 · ⚛️ physics.bio-ph · cond-mat.stat-mech· nlin.AO

Self-organized robustness in mean-field interacting systems

Emmy Blumenthal , Gautam Reddy This is my paper

Pith reviewed 2026-06-29 00:53 UTC · model grok-4.3

classification ⚛️ physics.bio-ph cond-mat.stat-mechnlin.AO
keywords self-organized robustnessmean-field modelseascapeWasserstein gradient flowcollective dynamicsreservoir statesassociative memoryperturbation response
0
0 comments X

The pith

Mean-field systems self-organize interactions into a seascape that accelerates relaxation to equilibrium.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces a tractable mean-field model of self-organized robustness formulated as meta-optimization over the system's response to perturbations. The resulting interaction structure appears as a dynamically modulated landscape, or seascape, whose shape is set self-consistently to speed relaxation back to equilibrium. Collective dynamics follows an optimized Wasserstein gradient flow toward an attractor in the space of collective states. When communication is limited, interactions preferentially encode slowly relaxing modes and modes that are frequently perturbed. The model further associates robust collective states with flatter equilibrium landscapes and predicts a continuum of intermediate reservoir states.

Core claim

In mean-field interacting systems, self-organized robustness emerges when the interaction structure is determined self-consistently through meta-optimization over responses to perturbations. This produces a seascape whose shape accelerates return to equilibrium, with collective dynamics described by an optimized Wasserstein gradient flow to an attractor. Limited communication causes the interactions to encode slowly relaxing modes and frequently perturbed modes preferentially. Robust states sit on flatter equilibrium landscapes, and the framework predicts a continuum of intermediate reservoir states, framing self-organization as hierarchical associative memory operating across collective uni

What carries the argument

The seascape, a dynamically modulated landscape whose shape is determined self-consistently by meta-optimization to accelerate relaxation back to equilibrium.

If this is right

  • When communication is limited, interactions preferentially encode slowly relaxing modes and modes that are frequently perturbed.
  • Robust collective states are associated with flatter equilibrium landscapes.
  • The model predicts a continuum of intermediate reservoir states.
  • Self-organization functions as a hierarchical associative memory operating on the scale of a collective of interacting units.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The seascape view implies that external control of perturbation statistics could reshape the effective landscape and steer collective attractors.
  • The Wasserstein flow description links the model to gradient-based optimization methods used in other collective systems.
  • A direct test would involve imposing controlled perturbation spectra on an experimental collective and checking whether encoded modes match the predicted slow and frequent ones.

Load-bearing premise

That self-organized robustness can be usefully formulated as meta-optimization over the system's response to perturbations, allowing the interaction structure to be determined self-consistently.

What would settle it

Simulations or measurements of interaction strengths in a collective with limited communication would need to show stronger couplings precisely for modes with longer relaxation times and higher perturbation rates.

Figures

Figures reproduced from arXiv: 2606.27626 by Emmy Blumenthal, Gautam Reddy.

Figure 1
Figure 1. Figure 1: FIG. 1. Signaling-modulated landscape accelerates self [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: FIG. 2. The geometry of signaling-mediated inference of [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: FIG. 3. A signaling-modulated landscape accelerates convergence to the desired state. Top row: the KL divergence from the [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: FIG. 4. Optimal signaling modes for example distributions experiencing perturbations along the passive modes ( [PITH_FULL_IMAGE:figures/full_fig_p007_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: FIG. 5. Optimal signaling trades off between signaling the [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: FIG. 6. Preconditioning introduces reservoir states that accelerate convergence at short times at the cost of long-time [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: FIG. 7. Self-organized robustness can be conceived of as an [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗
read the original abstract

Self-organization is a defining feature of living systems, with order often maintained through interactions between constituent units rather than centralized feedback. We introduce a tractable mean-field model of self-organized robustness, formulated as meta-optimization over the system's response to perturbations. The resulting interaction structure has an intuitive picture as a dynamically modulated landscape (``seascape'') whose shape is determined self-consistently to accelerate relaxation back to equilibrium. The collective dynamics follows an optimized Wasserstein gradient flow toward an attractor in the space of collective states. When communication is limited, interactions preferentially encode slowly relaxing modes and modes that are frequently perturbed. The model further shows that robust collective states are associated with flatter equilibrium landscapes and predicts a continuum of intermediate ``reservoir states'' in such systems. The model offers a perspective of self-organization as a hierarchical associative memory that operates on the scale of a collective of interacting computational units.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The paper introduces a tractable mean-field model of self-organized robustness formulated as meta-optimization over the system's response to perturbations. The resulting interaction structure is pictured as a dynamically modulated 'seascape' determined self-consistently to accelerate relaxation back to equilibrium. Collective dynamics are described as an optimized Wasserstein gradient flow toward an attractor in collective state space. With limited communication, interactions preferentially encode slowly relaxing and frequently perturbed modes. The model associates robust collective states with flatter equilibrium landscapes, predicts a continuum of intermediate 'reservoir states,' and frames self-organization as hierarchical associative memory operating on interacting computational units.

Significance. If the meta-optimization construction and self-consistency can be shown to be internally consistent and free of circularity, the framework could supply a useful modeling lens for robustness in biological collectives, linking mean-field limits, Wasserstein geometry, and associative-memory ideas. The absence of any equations, derivations, or validation in the abstract, however, leaves the technical content and predictive power unassessable from the provided material.

major comments (1)
  1. [Abstract] Abstract: the central construction is described only at the level of a modeling perspective with no equations, no explicit definition of the meta-optimization functional, and no statement of the mean-field limit or Wasserstein flow. Without these, it is impossible to verify whether the self-consistent seascape avoids the circularity risk noted in the reader's report (i.e., whether the optimization target is independent of the relaxation dynamics it is intended to produce).
minor comments (1)
  1. [Abstract] The abstract introduces several novel terms ('seascape', 'reservoir states') without immediate definitions or references; a short glossary or forward reference to their first mathematical appearance would improve readability.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their review and for highlighting the need for clarity on the abstract's technical content. We address the single major comment below. The full manuscript contains the requested equations, definitions, and derivations; the abstract is written at a conceptual level for accessibility.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central construction is described only at the level of a modeling perspective with no equations, no explicit definition of the meta-optimization functional, and no statement of the mean-field limit or Wasserstein flow. Without these, it is impossible to verify whether the self-consistent seascape avoids the circularity risk noted in the reader's report (i.e., whether the optimization target is independent of the relaxation dynamics it is intended to produce).

    Authors: The abstract is intentionally non-technical to summarize the modeling perspective for a broad readership, which is standard practice. The full manuscript provides the explicit meta-optimization functional (defined over expected relaxation times to perturbations), the mean-field limit derivation, and the formulation of dynamics as an optimized Wasserstein gradient flow, all with equations and proofs. On circularity: the optimization target (minimizing integrated relaxation time under a perturbation measure) is specified independently of the flow; the seascape is obtained as the self-consistent solution to this optimization problem, after which the gradient flow is derived from the resulting landscape. This separation is shown to be non-circular in the derivations, with the fixed-point iteration converging to a consistent equilibrium without feedback from the dynamics into the target. revision: no

Circularity Check

0 steps flagged

No significant circularity; model is self-contained by definition

full rationale

The paper introduces a tractable mean-field model explicitly formulated as meta-optimization over perturbation response, with the seascape and Wasserstein flow presented as direct consequences of that modeling choice. No derivation chain, equations, or self-citations are exhibited that reduce a claimed prediction or first-principles result back to the inputs by construction. The construction is definitional to the model rather than an independent theorem that loops on itself, satisfying the criterion for a self-contained modeling perspective.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 1 invented entities

Only the abstract is available, so no concrete free parameters, axioms, or invented entities can be extracted or verified. The 'seascape' is mentioned as a conceptual device but its mathematical status is unspecified.

invented entities (1)
  • seascape no independent evidence
    purpose: Dynamically modulated landscape whose shape is set self-consistently to accelerate relaxation
    Introduced in the abstract as the central intuitive picture of the interaction structure; no independent evidence or falsifiable handle is supplied.

pith-pipeline@v0.9.1-grok · 5679 in / 1213 out tokens · 45743 ms · 2026-06-29T00:53:23.251717+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

148 extracted references · 15 canonical work pages · 2 internal anchors

  1. [1]

    Self-Organization in Pattern Formation , journal =

    Schweisguth, Fran. Self-Organization in Pattern Formation , journal =. 2019 , doi =

    2019

  2. [2]

    and Guo, Yipei and Brenner, Michael P

    Pelc, Guy and McKeithan, Wesley L. and Guo, Yipei and Brenner, Michael P. and Lim, Wendell A. and Nitzan, Mor , title =. 2025 , doi =

    2025

  3. [3]

    Collective Is Different: Information Exchange and Speed-Accuracy Trade-Offs in Self-Organized Patterning , year =

    Tripathi, Ashutosh and Dunkel, J. Collective Is Different: Information Exchange and Speed-Accuracy Trade-Offs in Self-Organized Patterning , year =. 2510.01397 , archivePrefix =

    work page arXiv

  4. [4]

    Information Content and Optimization of Self-Organized Developmental Systems , journal =

    Br. Information Content and Optimization of Self-Organized Developmental Systems , journal =. 2024 , doi =

    2024

  5. [5]

    and Scandolo, Mattia and Fruchart, Michel and Munro, Edwin M

    Romeo, Nicolas and Martin, David G. and Scandolo, Mattia and Fruchart, Michel and Munro, Edwin M. and Vitelli, Vincenzo , title =. 2026 , eprint =

    2026

  6. [6]

    and Grason, Gregory M

    Hagan, Michael F. and Grason, Gregory M. , title =. Reviews of Modern Physics , volume =. 2021 , doi =

    2021

  7. [7]

    Cell Reports Physical Science , volume =

    Smart, Matthew and Zilman, Anton , title =. Cell Reports Physical Science , volume =. 2023 , doi =

    2023

  8. [8]

    and Lemaire, Patrick and Mani, Madhav , title =

    Skinner, Dominic J. and Lemaire, Patrick and Mani, Madhav , title =. PRX Life , volume =. 2025 , doi =

    2025

  9. [9]

    Physical Review X , volume =

    Howe, Addison and Mani, Madhav , title =. Physical Review X , volume =. 2025 , doi =

    2025

  10. [10]

    Cislo, Dillon J. and Del. Reconstructing. Proceedings of the National Academy of Sciences , volume =. 2025 , doi =

    2025

  11. [11]

    and Dal Co, Alma , title =

    Deshpande, Ramya and Mottes, Francesco and Vlad, Ariana-Dalia and Brenner, Michael P. and Dal Co, Alma , title =. Nature Computational Science , volume =. 2025 , doi =

    2025

  12. [12]

    2024 , eprint =

    Reddy, Gautam , title =. 2024 , eprint =

    2024

  13. [13]

    and Simons, Benjamin D

    Klein, Allon M. and Simons, Benjamin D. , title =. Development , volume =. 2011 , doi =

    2011

  14. [14]

    and Swaminathan, Aishwarya and Winward, Ashley and Lalonde, Logan and Hwang, Yung and Littman, Noah and Socolovsky, Merav and Klein, Allon M

    Wu, Qiu C. and Swaminathan, Aishwarya and Winward, Ashley and Lalonde, Logan and Hwang, Yung and Littman, Noah and Socolovsky, Merav and Klein, Allon M. , title =. 2024 , doi =

    2024

  15. [15]

    Gradient Flows in Metric Spaces and in the Space of Probability Measures , edition =

    Ambrosio, Luigi and Gigli, Nicola and Savar. Gradient Flows in Metric Spaces and in the Space of Probability Measures , edition =. 2008 , doi =

    2008

  16. [16]

    2015 , doi =

    Santambrogio, Filippo , title =. 2015 , doi =

    2015

  17. [17]

    2024 , eprint =

    Chewi, Sinho and Niles-Weed, Jonathan and Rigollet, Philippe , title =. 2024 , eprint =. doi:10.48550/arXiv.2407.18163 , url =

    work page doi:10.48550/arxiv.2407.18163 2024

  18. [18]

    Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Damped Sinkhorn Iterations , year =

    Chizat, L. Computational Guarantees for Doubly Entropic Wasserstein Barycenters via Damped Sinkhorn Iterations , year =. 2307.13370 , archivePrefix =

    work page arXiv

  19. [19]

    On the relation between optimal transport and Schr\"odinger bridges: A stochastic control viewpoint

    Chen, Yongxin and Georgiou, Tryphon T. and Pavon, Michele , title =. 2014 , eprint =. doi:10.48550/arXiv.1412.4430 , url =

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1412.4430 2014

  20. [20]

    and Pavon, Michele , title =

    Chen, Yongxin and Georgiou, Tryphon T. and Pavon, Michele , title =. SIAM Review , volume =. 2021 , doi =

    2021

  21. [21]

    2016 , doi =

    Amari, Shun-ichi , title =. 2016 , doi =

    2016

  22. [22]

    and Mahony, Robert and Sepulchre, Rodolphe , title =

    Absil, P.-A. and Mahony, Robert and Sepulchre, Rodolphe , title =

  23. [23]

    , title =

    Bendokat, Thomas and Zimmermann, Ralf and Absil, P.-A. , title =. Advances in Computational Mathematics , volume =. 2024 , doi =

    2024

  24. [24]

    Bensoussan, Alain , title =

  25. [25]

    , title =

    Sinha, Sumit and Krishnan, Vishaal and Mahadevan, L. , title =. 2023 , eprint =

    2023

  26. [26]

    Advances in Neural Information Processing Systems , volume =

    Liu, Qiang and Wang, Dilin , title =. Advances in Neural Information Processing Systems , volume =

  27. [27]

    Lipman, Yaron and Havasi, Marton and Holderrieth, Peter and Shaul, Neta and Le, Matt and Karrer, Brian and Chen, Ricky T. Q. and Lopez-Paz, David and Ben-Hamu, Heli and Gat, Itai , title =. 2024 , eprint =

    2024

  28. [28]

    2024 , eprint =

    Haviv, Doron and Pooladian, Aram-Alexandre and Pe'er, Dana and Amos, Brandon , title =. 2024 , eprint =

    2024

  29. [29]

    2025 , eprint =

    Ollivier, Yann , title =. 2025 , eprint =

    2025

  30. [30]

    2025 , eprint =

    Nimonkar, Chirayu and Shah, Shlok and Ji, Catherine and Eysenbach, Benjamin , title =. 2025 , eprint =

    2025

  31. [31]

    , title =

    Krishnan, Vishaal and Sinha, Sumit and Mahadevan, L. , title =. Newton , volume =. 2026 , doi =

    2026

  32. [32]

    , title =

    Sethian, James A. , title =. Proceedings of the National Academy of Sciences , volume =. 1996 , doi =

    1996

  33. [33]

    and Vladimirsky, Alexander , title =

    Sethian, James A. and Vladimirsky, Alexander , title =. Proceedings of the National Academy of Sciences , volume =. 2001 , doi =

    2001

  34. [34]

    Mathematics of Computation , volume =

    Zhao, Hongkai , title =. Mathematics of Computation , volume =. 2005 , doi =

    2005

  35. [35]

    and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and van der Walt, St

    Virtanen, Pauli and Gommers, Ralf and Oliphant, Travis E. and Haberland, Matt and Reddy, Tyler and Cournapeau, David and Burovski, Evgeni and Peterson, Pearu and Weckesser, Warren and Bright, Jonathan and van der Walt, St. Nature Methods , volume =. 2020 , doi =

    2020

  36. [36]

    Chen, Ricky T. Q. and Rubanova, Yulia and Bettencourt, Jesse and Duvenaud, David K. , title =. Advances in Neural Information Processing Systems , volume =. 2018 , url =

    2018

  37. [37]

    SIAM Journal on Scientific Computing , volume =

    Wang, Qiqi and Moin, Parviz and Iaccarino, Gianluca , title =. SIAM Journal on Scientific Computing , volume =. 2009 , doi =

    2009

  38. [38]

    SIAM Journal on Scientific Computing , volume =

    Stumm, Philipp and Walther, Andrea , title =. SIAM Journal on Scientific Computing , volume =. 2010 , doi =

    2010

  39. [39]

    2018 , url =

    Bradbury, James and Frostig, Roy and Hawkins, Peter and Johnson, Matthew James and Leary, Chris and Maclaurin, Dougal and Necula, George and Paszke, Adam and VanderPlas, Jake and Wanderman-Milne, Skye and Zhang, Qiao , title =. 2018 , url =

    2018

  40. [40]

    2021 , url =

    Kidger, Patrick , title =. 2021 , url =

    2021

  41. [41]

    iScience , volume=

    The inherent fragility of collective proliferative control , author=. iScience , volume=. 2025 , publisher=

    2025

  42. [42]

    Annual Review of Condensed Matter Physics , volume=

    Stem cell populations as self-renewing many-particle systems , author=. Annual Review of Condensed Matter Physics , volume=. 2021 , publisher=

    2021

  43. [43]

    Nature , volume=

    Intestinal crypt homeostasis revealed at single-stem-cell level by in vivo live imaging , author=. Nature , volume=. 2014 , publisher=

    2014

  44. [44]

    Cell stem cell , volume=

    Homeostatic epidermal stem cell self-renewal is driven by local differentiation , author=. Cell stem cell , volume=. 2018 , publisher=

    2018

  45. [45]

    Cell Stem Cell , volume=

    Competition for mitogens regulates spermatogenic stem cell homeostasis in an open niche , author=. Cell Stem Cell , volume=. 2019 , publisher=

    2019

  46. [46]

    Cell , volume=

    Strategies for homeostatic stem cell self-renewal in adult tissues , author=. Cell , volume=. 2011 , publisher=

    2011

  47. [47]

    Development , volume=

    Communication codes in developmental signaling pathways , author=. Development , volume=. 2019 , publisher=

    2019

  48. [48]

    International Conference on Learning Representations , volume=

    Meta flow matching: Integrating vector fields on the wasserstein manifold , author=. International Conference on Learning Representations , volume=

  49. [49]

    arXiv preprint arXiv:2206.05262 , year=

    Meta optimal transport , author=. arXiv preprint arXiv:2206.05262 , year=

    work page arXiv

  50. [50]

    Physical Review X , volume=

    Speed-accuracy relations for diffusion models: Wisdom from nonequilibrium thermodynamics and optimal transport , author=. Physical Review X , volume=. 2025 , publisher=

    2025

  51. [51]

    Physical Review E , volume=

    Universal energy-speed-accuracy trade-offs in driven nonequilibrium systems , author=. Physical Review E , volume=. 2025 , publisher=

    2025

  52. [52]

    Orland, Henri , journal=. Schr. 2025 , publisher=

    2025

  53. [53]

    2014 , publisher=

    The strategy of the genes , author=. 2014 , publisher=

    2014

  54. [54]

    Proceedings of the National Academy of Sciences , volume=

    Geometry of gene regulatory dynamics , author=. Proceedings of the National Academy of Sciences , volume=. 2021 , publisher=

    2021

  55. [55]

    Development, Growth & Differentiation , volume=

    A geometrical perspective on development , author=. Development, Growth & Differentiation , volume=. 2023 , publisher=

    2023

  56. [56]

    Cell systems , volume=

    Statistically derived geometrical landscapes capture principles of decision-making dynamics during cell fate transitions , author=. Cell systems , volume=. 2022 , publisher=

    2022

  57. [57]

    Interface focus , volume=

    Dynamical landscapes of cell fate decisions , author=. Interface focus , volume=. 2022 , publisher=

    2022

  58. [58]

    PLoS computational biology , volume=

    Epigenetic landscapes explain partially reprogrammed cells and identify key reprogramming genes , author=. PLoS computational biology , volume=. 2014 , publisher=

    2014

  59. [59]

    Development , volume=

    scTOP: physics-inspired order parameters for cellular identification and visualization , author=. Development , volume=. 2023 , publisher=

    2023

  60. [60]

    Physical Review Research , volume=

    Waddington landscape for prototype learning in generalized Hopfield networks , author=. Physical Review Research , volume=. 2024 , publisher=

    2024

  61. [61]

    Nature Reviews Methods Primers , volume=

    Optimal transport for single-cell and spatial omics , author=. Nature Reviews Methods Primers , volume=. 2024 , publisher=

    2024

  62. [62]

    Nature methods , volume=

    Learning single-cell perturbation responses using neural optimal transport , author=. Nature methods , volume=. 2023 , publisher=

    2023

  63. [63]

    Cell , volume=

    Optimal-transport analysis of single-cell gene expression identifies developmental trajectories in reprogramming , author=. Cell , volume=. 2019 , publisher=

    2019

  64. [64]

    2009 , publisher=

    Optimal transport: old and new , author=. 2009 , publisher=

    2009

  65. [65]

    Numerische Mathematik , volume=

    A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem , author=. Numerische Mathematik , volume=. 2000 , publisher=

    2000

  66. [66]

    Physical review letters , volume=

    Optimal protocols and optimal transport in stochastic thermodynamics , author=. Physical review letters , volume=. 2011 , publisher=

    2011

  67. [67]

    Physical Review X , volume=

    Thermodynamic unification of optimal transport: Thermodynamic uncertainty relation, minimum dissipation, and thermodynamic speed limits , author=. Physical Review X , volume=. 2023 , publisher=

    2023

  68. [68]

    Journal of statistical physics , volume=

    Refined second law of thermodynamics for fast random processes , author=. Journal of statistical physics , volume=. 2012 , publisher=

    2012

  69. [69]

    Journal of Optimization Theory and Applications , volume=

    On the relation between optimal transport and Schrödinger bridges: A stochastic control viewpoint , author=. Journal of Optimization Theory and Applications , volume=. 2016 , publisher=

    2016

  70. [70]

    Siam Review , volume=

    Stochastic control liaisons: Richard sinkhorn meets gaspard monge on a schrodinger bridge , author=. Siam Review , volume=. 2021 , publisher=

    2021

  71. [71]

    Journal of statistical mechanics: theory and experiment , volume=

    Path integrals and symmetry breaking for optimal control theory , author=. Journal of statistical mechanics: theory and experiment , volume=. 2005 , publisher=

    2005

  72. [72]

    Proceedings of the national academy of sciences , volume=

    Efficient computation of optimal actions , author=. Proceedings of the national academy of sciences , volume=. 2009 , publisher=

    2009

  73. [73]

    Journal of Functional Analysis , volume=

    Unbalanced optimal transport: Dynamic and Kantorovich formulations , author=. Journal of Functional Analysis , volume=. 2018 , publisher=

    2018

  74. [74]

    Handbook of Numerical Analysis , volume=

    Unbalanced optimal transport, from theory to numerics , author=. Handbook of Numerical Analysis , volume=. 2023 , publisher=

    2023

  75. [75]

    Foundations and Trends

    Computational optimal transport: With applications to data science , author=. Foundations and Trends. 2019 , publisher=

    2019

  76. [76]

    Advances in neural information processing systems , volume=

    Sinkhorn distances: Lightspeed computation of optimal transport , author=. Advances in neural information processing systems , volume=

  77. [77]

    1931 , publisher=

    Schr. 1931 , publisher=

    1931

  78. [78]

    Sur la th

    Schr. Sur la th. Annales de l'institut Henri Poincar

  79. [79]

    Pacific Journal of Mathematics , volume=

    Concerning nonnegative matrices and doubly stochastic matrices , author=. Pacific Journal of Mathematics , volume=. 1967 , publisher=

    1967

  80. [80]

    The annals of mathematical statistics , volume=

    A relationship between arbitrary positive matrices and doubly stochastic matrices , author=. The annals of mathematical statistics , volume=. 1964 , publisher=

    1964

Showing first 80 references.