{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:52:31Z","timestamp":1776837151363,"version":"3.51.2"},"reference-count":79,"publisher":"American Mathematical Society (AMS)","issue":"344","license":[{"start":{"date-parts":[[2024,6,14]],"date-time":"2024-06-14T00:00:00Z","timestamp":1718323200000},"content-version":"am","delay-in-days":366,"URL":"https:\/\/www.ams.org\/publications\/copyright-and-permissions"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1811012"],"award-info":[{"award-number":["1811012"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2145900"],"award-info":[{"award-number":["2145900"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2204722"],"award-info":[{"award-number":["2204722"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1907221"],"award-info":[{"award-number":["1907221"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010336","name":"Hellman Foundation","doi-asserted-by":"publisher","award":["1811012"],"award-info":[{"award-number":["1811012"]}],"id":[{"id":"10.13039\/100010336","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010336","name":"Hellman Foundation","doi-asserted-by":"publisher","award":["2145900"],"award-info":[{"award-number":["2145900"]}],"id":[{"id":"10.13039\/100010336","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010336","name":"Hellman Foundation","doi-asserted-by":"publisher","award":["2204722"],"award-info":[{"award-number":["2204722"]}],"id":[{"id":"10.13039\/100010336","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010336","name":"Hellman Foundation","doi-asserted-by":"publisher","award":["1907221"],"award-info":[{"award-number":["1907221"]}],"id":[{"id":"10.13039\/100010336","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1811012"],"award-info":[{"award-number":["1811012"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2145900"],"award-info":[{"award-number":["2145900"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2204722"],"award-info":[{"award-number":["2204722"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1907221"],"award-info":[{"award-number":["1907221"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Math. Comp."],"abstract":"<p>As a counterpoint to classical stochastic particle methods for linear diffusion equations, such as Langevin dynamics for the Fokker-Planck equation, we develop a deterministic particle method for the weighted porous medium equation and prove its convergence on bounded time intervals. This generalizes related work on blob methods for unweighted porous medium equations. From a numerical analysis perspective, our method has several advantages: it is meshfree, preserves the gradient flow structure of the underlying PDE, converges in arbitrary dimension, and captures the correct asymptotic behavior in simulations.<\/p>\n                  <p>\n                    The fact that our method succeeds in capturing the long time behavior of the weighted porous medium equation is significant from the perspective of related problems in quantization. Just as the Fokker-Planck equation provides a way to quantize a probability measure\n                    <inline-formula content-type=\"math\/mathml\">\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" alttext=\"rho overbar\">\n                        <mml:semantics>\n                          <mml:mrow class=\"MJX-TeXAtom-ORD\">\n                            <mml:mover>\n                              <mml:mi>\n                                \u03c1\n                                \n                              <\/mml:mi>\n                              <mml:mo stretchy=\"false\">\n                                \u00af\n                                \n                              <\/mml:mo>\n                            <\/mml:mover>\n                          <\/mml:mrow>\n                          <mml:annotation encoding=\"application\/x-tex\">\\bar {\\rho }<\/mml:annotation>\n                        <\/mml:semantics>\n                      <\/mml:math>\n                    <\/inline-formula>\n                    by evolving an empirical measure\n                    <inline-formula content-type=\"math\/mathml\">\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" alttext=\"rho Superscript upper N Baseline left-parenthesis t right-parenthesis equals StartFraction 1 Over upper N EndFraction sigma-summation Underscript i equals 1 Overscript upper N Endscripts delta Subscript upper X Sub Superscript i Subscript left-parenthesis t right-parenthesis\">\n                        <mml:semantics>\n                          <mml:mrow>\n                            <mml:msup>\n                              <mml:mi>\n                                \u03c1\n                                \n                              <\/mml:mi>\n                              <mml:mi>N<\/mml:mi>\n                            <\/mml:msup>\n                            <mml:mo stretchy=\"false\">(<\/mml:mo>\n                            <mml:mi>t<\/mml:mi>\n                            <mml:mo stretchy=\"false\">)<\/mml:mo>\n                            <mml:mo>=<\/mml:mo>\n                            <mml:mfrac>\n                              <mml:mn>1<\/mml:mn>\n                              <mml:mi>N<\/mml:mi>\n                            <\/mml:mfrac>\n                            <mml:munderover>\n                              <mml:mo>\n                                \u2211\n                                \n                              <\/mml:mo>\n                              <mml:mrow class=\"MJX-TeXAtom-ORD\">\n                                <mml:mi>i<\/mml:mi>\n                                <mml:mo>=<\/mml:mo>\n                                <mml:mn>1<\/mml:mn>\n                              <\/mml:mrow>\n                              <mml:mi>N<\/mml:mi>\n                            <\/mml:munderover>\n                            <mml:msub>\n                              <mml:mi>\n                                \u03b4\n                                \n                              <\/mml:mi>\n                              <mml:mrow class=\"MJX-TeXAtom-ORD\">\n                                <mml:msup>\n                                  <mml:mi>X<\/mml:mi>\n                                  <mml:mi>i<\/mml:mi>\n                                <\/mml:msup>\n                                <mml:mo stretchy=\"false\">(<\/mml:mo>\n                                <mml:mi>t<\/mml:mi>\n                                <mml:mo stretchy=\"false\">)<\/mml:mo>\n                              <\/mml:mrow>\n                            <\/mml:msub>\n                          <\/mml:mrow>\n                          <mml:annotation encoding=\"application\/x-tex\">\\rho ^N(t) = \\frac {1}{N} \\sum _{i=1}^N \\delta _{X^i(t)}<\/mml:annotation>\n                        <\/mml:semantics>\n                      <\/mml:math>\n                    <\/inline-formula>\n                    according to stochastic Langevin dynamics so that\n                    <inline-formula content-type=\"math\/mathml\">\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" alttext=\"rho Superscript upper N Baseline left-parenthesis t right-parenthesis\">\n                        <mml:semantics>\n                          <mml:mrow>\n                            <mml:msup>\n                              <mml:mi>\n                                \u03c1\n                                \n                              <\/mml:mi>\n                              <mml:mi>N<\/mml:mi>\n                            <\/mml:msup>\n                            <mml:mo stretchy=\"false\">(<\/mml:mo>\n                            <mml:mi>t<\/mml:mi>\n                            <mml:mo stretchy=\"false\">)<\/mml:mo>\n                          <\/mml:mrow>\n                          <mml:annotation encoding=\"application\/x-tex\">\\rho ^N(t)<\/mml:annotation>\n                        <\/mml:semantics>\n                      <\/mml:math>\n                    <\/inline-formula>\n                    flows toward\n                    <inline-formula content-type=\"math\/mathml\">\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" alttext=\"rho overbar\">\n                        <mml:semantics>\n                          <mml:mrow class=\"MJX-TeXAtom-ORD\">\n                            <mml:mover>\n                              <mml:mi>\n                                \u03c1\n                                \n                              <\/mml:mi>\n                              <mml:mo stretchy=\"false\">\n                                \u00af\n                                \n                              <\/mml:mo>\n                            <\/mml:mover>\n                          <\/mml:mrow>\n                          <mml:annotation encoding=\"application\/x-tex\">\\bar {\\rho }<\/mml:annotation>\n                        <\/mml:semantics>\n                      <\/mml:math>\n                    <\/inline-formula>\n                    , our particle method provides a way to quantize\n                    <inline-formula content-type=\"math\/mathml\">\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" alttext=\"rho overbar\">\n                        <mml:semantics>\n                          <mml:mrow class=\"MJX-TeXAtom-ORD\">\n                            <mml:mover>\n                              <mml:mi>\n                                \u03c1\n                                \n                              <\/mml:mi>\n                              <mml:mo stretchy=\"false\">\n                                \u00af\n                                \n                              <\/mml:mo>\n                            <\/mml:mover>\n                          <\/mml:mrow>\n                          <mml:annotation encoding=\"application\/x-tex\">\\bar {\\rho }<\/mml:annotation>\n                        <\/mml:semantics>\n                      <\/mml:math>\n                    <\/inline-formula>\n                    according to deterministic particle dynamics approximating the weighted porous medium equation. In this way, our method has natural applications to multi-agent coverage algorithms and sampling probability measures.\n                  <\/p>\n                  <p>\n                    A specific case of our method corresponds to\n                    <italic>confined<\/italic>\n                    mean-field dynamics of training a two-layer neural network for a radial basis activation function. From this perspective, our convergence result shows that, in the overparametrized regime and as the variance of the radial basis functions goes to zero, the continuum limit is given by the weighted porous medium equation. This generalizes previous results, which considered the case of a uniform data distribution, to the more general inhomogeneous setting. As a consequence of our convergence result, we identify conditions on the target function and data distribution for which convexity of the energy landscape emerges in the continuum limit.\n                  <\/p>","DOI":"10.1090\/mcom\/3841","type":"journal-article","created":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T15:21:00Z","timestamp":1686756060000},"page":"2575-2654","source":"Crossref","is-referenced-by-count":6,"title":["A blob method for inhomogeneous diffusion with applications to multi-agent control and sampling"],"prefix":"10.1090","volume":"92","author":[{"given":"Katy","family":"Craig","sequence":"first","affiliation":[]},{"given":"Karthik","family":"Elamvazhuthi","sequence":"additional","affiliation":[]},{"given":"Matt","family":"Haberland","sequence":"additional","affiliation":[]},{"given":"Olga","family":"Turanova","sequence":"additional","affiliation":[]}],"member":"14","published-online":{"date-parts":[[2023,6,14]]},"reference":[{"key":"1","doi-asserted-by":"publisher","first-page":"111480","DOI":"10.1016\/j.na.2019.03.003","article-title":"The role of a strong confining potential in a nonlinear Fokker-Planck equation","volume":"193","author":"Alasio, Luca","year":"2020","journal-title":"Nonlinear Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0362-546X","issn-type":"print"},{"key":"2","series-title":"Unitext","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-72162-6","volume-title":"Lectures on optimal transport","volume":"130","author":"Ambrosio, Luigi","year":"[2021] \\copyright2021","ISBN":"https:\/\/id.crossref.org\/isbn\/9783030721619"},{"key":"3","series-title":"Lectures in Mathematics ETH Z\\\"{u}rich","isbn-type":"print","volume-title":"Gradient flows in metric spaces and in the space of probability measures","author":"Ambrosio, Luigi","year":"2008","ISBN":"https:\/\/id.crossref.org\/isbn\/9783764387211","edition":"2"},{"key":"4","doi-asserted-by":"crossref","unstructured":"B. Anderson, E. Loeser, M. Gee, F. Ren, S. Biswas, O. Turanova, M. Haberland, and A. L. Bertozzi, Quantitative assessment of robotic swarm coverage, Proceedings of the 15th International Conference on Informatics in Control, Automation, and Robotics, vol. 2, 2018, pp. 91\u2013101.","DOI":"10.5220\/0006844600910101"},{"key":"5","isbn-type":"print","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1007\/978-3-030-31993-9_13","article-title":"Quantifying robotic swarm coverage","author":"Anderson, Brendon G.","year":"[2020] \\copyright2020","ISBN":"https:\/\/id.crossref.org\/isbn\/9783030319922"},{"issue":"3","key":"6","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/s00211-015-0781-y","article-title":"Discretization of functionals involving the Monge-Amp\u00e8re operator","volume":"134","author":"Benamou, Jean-David","year":"2016","journal-title":"Numer. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/0029-599X","issn-type":"print"},{"issue":"5","key":"7","doi-asserted-by":"publisher","first-page":"B559--B583","DOI":"10.1137\/110853807","article-title":"A finite volume scheme for nonlinear degenerate parabolic equations","volume":"34","author":"Bessemoulin-Chatard, Marianne","year":"2012","journal-title":"SIAM J. Sci. Comput.","ISSN":"https:\/\/id.crossref.org\/issn\/1064-8275","issn-type":"print"},{"key":"8","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-34514-5","volume-title":"Measure theory. Vol. I, II","author":"Bogachev, V. I.","year":"2007","ISBN":"https:\/\/id.crossref.org\/isbn\/9783540345138"},{"key":"9","unstructured":"N. Bou-Rabee and A. Eberle, Markov chain Monte Carlo methods, Lecture notes, 2020 \\url{https:\/\/uni-bonn.sciebo.de\/s\/kzTUFff5FrWGAay}."},{"issue":"3","key":"10","doi-asserted-by":"publisher","first-page":"1549","DOI":"10.1007\/s00220-021-04216-6","article-title":"Asymptotic optimality of the triangular lattice for a class of optimal location problems","volume":"387","author":"Bourne, David P.","year":"2021","journal-title":"Comm. Math. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0010-3616","issn-type":"print"},{"issue":"6","key":"11","doi-asserted-by":"publisher","first-page":"2545","DOI":"10.1137\/141000993","article-title":"Centroidal power diagrams, Lloyd\u2019s algorithm, and applications to optimal location problems","volume":"53","author":"Bourne, D. P.","year":"2015","journal-title":"SIAM J. Numer. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1429","issn-type":"print"},{"key":"12","series-title":"Princeton Series in Applied Mathematics","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1515\/9781400831470","volume-title":"Distributed control of robotic networks","author":"Bullo, Francesco","year":"2009","ISBN":"https:\/\/id.crossref.org\/isbn\/9780691141954"},{"issue":"1","key":"13","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3934\/krm.2010.3.59","article-title":"A mixed finite element method for nonlinear diffusion equations","volume":"3","author":"Burger, Martin","year":"2010","journal-title":"Kinet. Relat. Models","ISSN":"https:\/\/id.crossref.org\/issn\/1937-5093","issn-type":"print"},{"key":"14","unstructured":"M. Burger and A. Esposito, Porous medium equation as limit of nonlocal interaction, Preprint,  arXiv:2202.05030, 2022."},{"key":"15","series-title":"Pitman Research Notes in Mathematics Series","isbn-type":"print","volume-title":"Semicontinuity, relaxation and integral representation in the calculus of variations","volume":"207","author":"Buttazzo, Giuseppe","year":"1989","ISBN":"https:\/\/id.crossref.org\/isbn\/0582018595"},{"issue":"10","key":"16","doi-asserted-by":"publisher","first-page":"1845","DOI":"10.1142\/S0218202515500475","article-title":"A gradient flow approach to quantization of measures","volume":"25","author":"Caglioti, Emanuele","year":"2015","journal-title":"Math. Models Methods Appl. Sci.","ISSN":"https:\/\/id.crossref.org\/issn\/0218-2025","issn-type":"print"},{"issue":"3","key":"17","doi-asserted-by":"publisher","first-page":"613","DOI":"10.3934\/krm.2017025","article-title":"Numerical study of a particle method for gradient flows","volume":"10","author":"Carrillo, Jos\u00e9 Antonio","year":"2017","journal-title":"Kinet. Relat. Models","ISSN":"https:\/\/id.crossref.org\/issn\/1937-5093","issn-type":"print"},{"issue":"1","key":"18","doi-asserted-by":"publisher","first-page":"233","DOI":"10.4208\/cicp.160214.010814a","article-title":"A finite-volume method for nonlinear nonlocal equations with a gradient flow structure","volume":"17","author":"Carrillo, Jos\u00e9 A.","year":"2015","journal-title":"Commun. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/1815-2406","issn-type":"print"},{"issue":"2","key":"19","doi-asserted-by":"publisher","first-page":"Paper No. 53, 53","DOI":"10.1007\/s00526-019-1486-3","article-title":"A blob method for diffusion","volume":"58","author":"Carrillo, Jos\u00e9 Antonio","year":"2019","journal-title":"Calc. Var. Partial Differential Equations","ISSN":"https:\/\/id.crossref.org\/issn\/0944-2669","issn-type":"print"},{"issue":"2","key":"20","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/s10208-021-09503-1","article-title":"Primal dual methods for Wasserstein gradient flows","volume":"22","author":"Carrillo, Jos\u00e9 A.","year":"2022","journal-title":"Found. Comput. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/1615-3375","issn-type":"print"},{"key":"21","isbn-type":"print","first-page":"65","article-title":"Aggregation-diffusion equations: dynamics, asymptotics, and singular limits","author":"Carrillo, Jos\u00e9 A.","year":"2019","ISBN":"https:\/\/id.crossref.org\/isbn\/9783030202965"},{"issue":"6","key":"22","doi-asserted-by":"publisher","first-page":"4305","DOI":"10.1137\/080739574","article-title":"Numerical simulation of diffusive and aggregation phenomena in nonlinear continuity equations by evolving diffeomorphisms","volume":"31","author":"Carrillo, J. A.","year":"2009","journal-title":"SIAM J. Sci. Comput.","ISSN":"https:\/\/id.crossref.org\/issn\/1064-8275","issn-type":"print"},{"issue":"6","key":"23","doi-asserted-by":"publisher","first-page":"3708","DOI":"10.1137\/16M1077210","article-title":"Convergence of a particle method for diffusive gradient flows in one dimension","volume":"48","author":"Carrillo, J. A.","year":"2016","journal-title":"SIAM J. Math. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1410","issn-type":"print"},{"key":"24","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1016\/j.jcp.2016.09.040","article-title":"Numerical simulation of nonlinear continuity equations by evolving diffeomorphisms","volume":"327","author":"Carrillo, Jos\u00e9 A.","year":"2016","journal-title":"J. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0021-9991","issn-type":"print"},{"key":"25","unstructured":"S. Chewi, T. L. Gouic, C. Lu, T. Maunu, and P. Rigollet, SVGD as a kernelized Wasserstein gradient flow of the chi-squared divergence, Preprint,  arXiv:2006.02509, 2020."},{"key":"26","unstructured":"L. Chizat and F. Bach, On the global convergence of gradient descent for over-parameterized models using optimal transport, Preprint,  arXiv:1805.09545, 2018."},{"key":"27","doi-asserted-by":"crossref","unstructured":"J. Cortes, S. Martinez, T. Karatas, and F. Bullo, Coverage control for mobile sensing networks, IEEE Trans. Robot. Autom. 20 (2004), no. 2, 243\u2013255.","DOI":"10.1109\/TRA.2004.824698"},{"issue":"1","key":"28","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1112\/plms.12005","article-title":"Nonconvex gradient flow in the Wasserstein metric and applications to constrained nonlocal interactions","volume":"114","author":"Craig, Katy","year":"2017","journal-title":"Proc. Lond. Math. Soc. (3)","ISSN":"https:\/\/id.crossref.org\/issn\/0024-6115","issn-type":"print"},{"issue":"300","key":"29","doi-asserted-by":"publisher","first-page":"1681","DOI":"10.1090\/mcom3033","article-title":"A blob method for the aggregation equation","volume":"85","author":"Craig, Katy","year":"2016","journal-title":"Math. Comp.","ISSN":"https:\/\/id.crossref.org\/issn\/0025-5718","issn-type":"print"},{"key":"30","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/j.jde.2021.12.019","article-title":"Deterministic particle approximation of aggregation-diffusion equations on unbounded domains","volume":"312","author":"Daneri, Sara","year":"2022","journal-title":"J. Differential Equations","ISSN":"https:\/\/id.crossref.org\/issn\/0022-0396","issn-type":"print"},{"issue":"3","key":"31","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/s00205-015-0843-4","article-title":"Rigorous derivation of nonlinear scalar conservation laws from follow-the-leader type models via many particle limit","volume":"217","author":"Di Francesco, M.","year":"2015","journal-title":"Arch. Ration. Mech. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0003-9527","issn-type":"print"},{"issue":"1","key":"32","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/BF02213456","article-title":"Asymptotics for transportation cost in high dimensions","volume":"8","author":"Dobri\u0107, V.","year":"1995","journal-title":"J. Theoret. Probab.","ISSN":"https:\/\/id.crossref.org\/issn\/0894-9840","issn-type":"print"},{"issue":"1","key":"33","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1007\/s11118-007-9066-0","article-title":"\ud835\udc3f^{\ud835\udc5e}-functional inequalities and weighted porous media equations","volume":"28","author":"Dolbeault, Jean","year":"2008","journal-title":"Potential Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0926-2601","issn-type":"print"},{"key":"34","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1214\/aoms\/1177697802","article-title":"The speed of mean Glivenko-Cantelli convergence","volume":"40","author":"Dudley, R. M.","year":"1968","journal-title":"Ann. Math. Statist.","ISSN":"https:\/\/id.crossref.org\/issn\/0003-4851","issn-type":"print"},{"key":"35","doi-asserted-by":"crossref","unstructured":"K. Elamvazhuthi, C. Adams, and S. Berman, Coverage and field estimation on bounded domains by diffusive swarms, 2016 IEEE 55th Conference on Decision and Control (CDC), IEEE, 2016, pp. 2867\u20132874.","DOI":"10.1109\/CDC.2016.7798696"},{"key":"36","doi-asserted-by":"crossref","unstructured":"K. Elamvazhuthi and S. Berman, Nonlinear generalizations of diffusion-based coverage by robotic swarms, 2018 IEEE Conference on Decision and Control (CDC), IEEE, 2018, pp. 1341\u20131346.","DOI":"10.1109\/CDC.2018.8618889"},{"key":"37","doi-asserted-by":"crossref","unstructured":"U. Eren and B. A\u00e7\u0131kme\u015fe, Velocity field generation for density control of swarms using heat equation and smoothing kernels, IFAC-PapersOnLine 50 (2017), no. 1, 9405\u20139411.","DOI":"10.1016\/j.ifacol.2017.08.1454"},{"issue":"3","key":"38","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1137\/04061386X","article-title":"Diffeomorphisms and nonlinear heat flows","volume":"37","author":"Evans, L. C.","year":"2005","journal-title":"SIAM J. Math. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1410","issn-type":"print"},{"key":"39","series-title":"EMS Textbooks in Mathematics","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.4171\/ETB\/22","volume-title":"An invitation to optimal transport, Wasserstein distances, and gradient flows","author":"Figalli, Alessio","year":"[2021] \\copyright2021","ISBN":"https:\/\/id.crossref.org\/isbn\/9783985470105"},{"issue":"3","key":"40","doi-asserted-by":"publisher","first-page":"2990","DOI":"10.1137\/21M1422756","article-title":"Convergence of a Lagrangian discretization for barotropic fluids and porous media flow","volume":"54","author":"Gallou\u00ebt, Thomas O.","year":"2022","journal-title":"SIAM J. Math. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1410","issn-type":"print"},{"key":"41","series-title":"Lecture Notes in Mathematics","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0103945","volume-title":"Foundations of quantization for probability distributions","volume":"1730","author":"Graf, Siegfried","year":"2000","ISBN":"https:\/\/id.crossref.org\/isbn\/3540673946"},{"issue":"8","key":"42","doi-asserted-by":"publisher","first-page":"3599","DOI":"10.3934\/dcds.2013.33.3599","article-title":"Porous media equations with two weights: smoothing and decay properties of energy solutions via Poincar\u00e9 inequalities","volume":"33","author":"Grillo, Gabriele","year":"2013","journal-title":"Discrete Contin. Dyn. Syst.","ISSN":"https:\/\/id.crossref.org\/issn\/1078-0947","issn-type":"print"},{"key":"43","doi-asserted-by":"crossref","unstructured":"J. D. Hunter, Matplotlib: a 2D graphics environment, Comput. Sci. Eng. 9 (2007), no. 3, 90\u201395.","DOI":"10.1109\/MCSE.2007.55"},{"key":"44","isbn-type":"print","first-page":"145","article-title":"A gradient flow perspective on the quantization problem","author":"Iacobelli, Mikaela","year":"2018","ISBN":"https:\/\/id.crossref.org\/isbn\/9783030019464"},{"issue":"9","key":"45","doi-asserted-by":"publisher","first-page":"4929","DOI":"10.3934\/dcds.2019201","article-title":"Asymptotic analysis for a very fast diffusion equation arising from the 1D quantization problem","volume":"39","author":"Iacobelli, Mikaela","year":"2019","journal-title":"Discrete Contin. Dyn. Syst.","ISSN":"https:\/\/id.crossref.org\/issn\/1078-0947","issn-type":"print"},{"issue":"6","key":"46","doi-asserted-by":"publisher","first-page":"3619","DOI":"10.1214\/20-AOS1945","article-title":"Analysis of a two-layer neural network via displacement convexity","volume":"48","author":"Javanmard, Adel","year":"2020","journal-title":"Ann. Statist.","ISSN":"https:\/\/id.crossref.org\/issn\/0090-5364","issn-type":"print"},{"issue":"1","key":"47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1137\/S0036141096303359","article-title":"The variational formulation of the Fokker-Planck equation","volume":"29","author":"Jordan, Richard","year":"1998","journal-title":"SIAM J. Math. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1410","issn-type":"print"},{"key":"48","unstructured":"A. Korba, A. Salim, M. Arbel, G. Luise, and A. Gretton, A non-asymptotic analysis for Stein variational gradient descent, Adv. Neural Inf. Process. Syst. 33 (2020), 4672\u20134682."},{"key":"49","doi-asserted-by":"crossref","unstructured":"V. Krishnan and S. Mart\u00ednez, Distributed optimal transport for the deployment of swarms, 2018 IEEE Conference on Decision and Control (CDC), IEEE, 2018, pp. 4583\u20134588.","DOI":"10.1109\/CDC.2018.8619816"},{"issue":"4","key":"50","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1016\/S0764-4442(00)01795-X","article-title":"Une m\u00e9thode particulaire d\u00e9terministe pour des \u00e9quations diffusives non lin\u00e9aires","volume":"332","author":"Lions, Pierre-Louis","year":"2001","journal-title":"C. R. Acad. Sci. Paris S\\'{e}r. I Math.","ISSN":"https:\/\/id.crossref.org\/issn\/0764-4442","issn-type":"print"},{"key":"51","unstructured":"Q. Liu, Stein variational gradient descent as gradient flow, Adv. Neural Inf. Process. Syst. 30 (2017)."},{"key":"52","unstructured":"Q. Liu and D. Wang, Stein variational gradient descent: a general purpose Bayesian inference algorithm, Adv. Neural Inf. Process. Syst. 29 (2016)."},{"issue":"2","key":"53","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1137\/18M1187611","article-title":"Scaling limit of the Stein variational gradient descent: the mean field regime","volume":"51","author":"Lu, Jianfeng","year":"2019","journal-title":"SIAM J. Math. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1410","issn-type":"print"},{"issue":"10-12","key":"54","doi-asserted-by":"publisher","first-page":"1352","DOI":"10.1080\/03605300903296256","article-title":"A family of nonlinear fourth order equations of gradient flow type","volume":"34","author":"Matthes, Daniel","year":"2009","journal-title":"Comm. Partial Differential Equations","ISSN":"https:\/\/id.crossref.org\/issn\/0360-5302","issn-type":"print"},{"issue":"3","key":"55","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1051\/m2an\/2013126","article-title":"Convergence of a variational Lagrangian scheme for a nonlinear drift diffusion equation","volume":"48","author":"Matthes, Daniel","year":"2014","journal-title":"ESAIM Math. Model. Numer. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/2822-7840","issn-type":"print"},{"key":"56","isbn-type":"print","first-page":"313","article-title":"Convergent Lagrangian discretization for drift-diffusion with nonlocal aggregation","author":"Matthes, Daniel","year":"2017","ISBN":"https:\/\/id.crossref.org\/isbn\/9783319492612"},{"issue":"33","key":"57","doi-asserted-by":"publisher","first-page":"E7665--E7671","DOI":"10.1073\/pnas.1806579115","article-title":"A mean field view of the landscape of two-layer neural networks","volume":"115","author":"Mei, Song","year":"2018","journal-title":"Proc. Natl. Acad. Sci. USA","ISSN":"https:\/\/id.crossref.org\/issn\/0027-8424","issn-type":"print"},{"key":"58","doi-asserted-by":"crossref","unstructured":"Q. M\u00e9rigot, A multiscale approach to optimal transport, Comput. Graph. Forum 30 (2011), 1583\u20131592. Wiley Online Library.","DOI":"10.1111\/j.1467-8659.2011.02032.x"},{"key":"59","isbn-type":"print","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1007\/978-3-540-78929-1_26","article-title":"Optimotaxis: a stochastic multi-agent optimization procedure with point measurements","author":"Mesquita, Alexandre R.","year":"2008","ISBN":"https:\/\/id.crossref.org\/isbn\/9783540789284"},{"issue":"2","key":"60","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/0022-0396(90)90101-T","article-title":"Large systems of interacting particles and the porous medium equation","volume":"88","author":"Oelschl\u00e4ger, Karl","year":"1990","journal-title":"J. Differential Equations","ISSN":"https:\/\/id.crossref.org\/issn\/0022-0396","issn-type":"print"},{"key":"61","unstructured":"R. Okuta, Y. Unno, D. Nishino, S. Hido, and C. Loomis, CuPy: a NumPy-Compatible Library for NVIDIA GPU Calculations, 31st Conference on Neural Information Processing Systems, 2017."},{"issue":"1-2","key":"62","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1081\/PDE-100002243","article-title":"The geometry of dissipative evolution equations: the porous medium equation","volume":"26","author":"Otto, Felix","year":"2001","journal-title":"Comm. Partial Differential Equations","ISSN":"https:\/\/id.crossref.org\/issn\/0360-5302","issn-type":"print"},{"issue":"2","key":"63","doi-asserted-by":"publisher","first-page":"903","DOI":"10.3934\/dcds.2021142","article-title":"The nonlocal-interaction equation near attracting manifolds","volume":"42","author":"Patacchini, Francesco S.","year":"2022","journal-title":"Discrete Contin. Dyn. Syst.","ISSN":"https:\/\/id.crossref.org\/issn\/1078-0947","issn-type":"print"},{"issue":"9","key":"64","doi-asserted-by":"publisher","first-page":"1889","DOI":"10.1002\/cpa.22074","article-title":"Trainability and accuracy of artificial neural networks: an interacting particle system approach","volume":"75","author":"Rotskoff, G. M.","year":"2022","journal-title":"Comm. Pure Appl. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/0010-3640","issn-type":"print"},{"key":"65","volume-title":"Real analysis","author":"Royden, H. L.","year":"1963"},{"key":"66","series-title":"Progress in Nonlinear Differential Equations and their Applications","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20828-2","volume-title":"Optimal transport for applied mathematicians","volume":"87","author":"Santambrogio, Filippo","year":"2015","ISBN":"https:\/\/id.crossref.org\/isbn\/9783319208275"},{"issue":"4","key":"67","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.3934\/dcds.2011.31.1427","article-title":"Gamma-convergence of gradient flows on Hilbert and metric spaces and applications","volume":"31","author":"Serfaty, Sylvia","year":"2011","journal-title":"Discrete Contin. Dyn. Syst.","ISSN":"https:\/\/id.crossref.org\/issn\/1078-0947","issn-type":"print"},{"issue":"2","key":"68","doi-asserted-by":"publisher","first-page":"725","DOI":"10.1137\/18M1192184","article-title":"Mean field analysis of neural networks: a law of large numbers","volume":"80","author":"Sirignano, Justin","year":"2020","journal-title":"SIAM J. Appl. Math.","ISSN":"https:\/\/id.crossref.org\/issn\/0036-1399","issn-type":"print"},{"key":"69","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.jcp.2017.09.050","article-title":"A discontinuous Galerkin method for nonlinear parabolic equations and gradient flow problems with interaction potentials","volume":"352","author":"Sun, Zheng","year":"2018","journal-title":"J. Comput. Phys.","ISSN":"https:\/\/id.crossref.org\/issn\/0021-9991","issn-type":"print"},{"key":"70","series-title":"Springer Series in Statistics","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1007\/b13794","volume-title":"Introduction to nonparametric estimation","author":"Tsybakov, Alexandre B.","year":"2009","ISBN":"https:\/\/id.crossref.org\/isbn\/9780387790510"},{"key":"71","doi-asserted-by":"crossref","unstructured":"S. Van Der Walt, S. C. Colbert, and G. Varoquaux, The NumPy array: a structure for efficient numerical computation, Comput. Sci. Eng. 13 (2011), no. 2, 22\u201330.","DOI":"10.1109\/MCSE.2011.37"},{"key":"72","isbn-type":"print","first-page":"205","article-title":"The mathematical theories of diffusion: nonlinear and fractional diffusion","author":"V\u00e1zquez, Juan Luis","year":"2017","ISBN":"https:\/\/id.crossref.org\/isbn\/9783319614939"},{"key":"73","series-title":"Graduate Studies in Mathematics","isbn-type":"print","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/058","volume-title":"Topics in optimal transportation","volume":"58","author":"Villani, C\u00e9dric","year":"2003","ISBN":"https:\/\/id.crossref.org\/isbn\/082183312X"},{"key":"74","doi-asserted-by":"crossref","unstructured":"P. Virtanen, R. Gommers, T. E. Oliphant, M. Haberland, T. Reddy, D. Cournapeau, E. Burovski, P. Peterson, W. Weckesser, J. Bright, et al., SciPy 1.0: fundamental algorithms for scientific computing in Python, Nat. Methods 17 (2020), no. 3, 261\u2013272.","DOI":"10.1038\/s41592-020-0772-5"},{"key":"75","unstructured":"N. K. Vishnoi, An introduction to Hamiltonian Monte Carlo method for sampling, Preprint,  arXiv:2108.12107, 2021."},{"issue":"4","key":"76","doi-asserted-by":"publisher","first-page":"2620","DOI":"10.3150\/18-BEJ1065","article-title":"Sharp asymptotic and finite-sample rates of convergence of empirical measures in Wasserstein distance","volume":"25","author":"Weed, Jonathan","year":"2019","journal-title":"Bernoulli","ISSN":"https:\/\/id.crossref.org\/issn\/1350-7265","issn-type":"print"},{"issue":"11","key":"77","doi-asserted-by":"publisher","first-page":"2233","DOI":"10.1007\/s11425-020-1773-8","article-title":"Machine learning from a continuous viewpoint, I","volume":"63","author":"E, Weinan","year":"2020","journal-title":"Sci. China Math.","ISSN":"https:\/\/id.crossref.org\/issn\/1674-7283","issn-type":"print"},{"issue":"1","key":"78","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1051\/m2an\/2009043","article-title":"Variational particle schemes for the porous medium equation and for the system of isentropic Euler equations","volume":"44","author":"Westdickenberg, Michael","year":"2010","journal-title":"M2AN Math. Model. Numer. Anal.","ISSN":"https:\/\/id.crossref.org\/issn\/0764-583X","issn-type":"print"},{"key":"79","unstructured":"S. Wojtowytsch, On the convergence of gradient descent training for two-layer ReLU-networks in the mean field regime, Preprint,  arXiv:2005.13530, 2020."}],"container-title":["Mathematics of Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ams.org\/mcom\/2023-92-344\/S0025-5718-2023-03841-8\/S0025-5718-2023-03841-8.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T05:04:24Z","timestamp":1776834264000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ams.org\/mcom\/2023-92-344\/S0025-5718-2023-03841-8\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,14]]},"references-count":79,"journal-issue":{"issue":"344","published-print":{"date-parts":[[2023,11]]}},"alternative-id":["S0025-5718-2023-03841-8"],"URL":"https:\/\/doi.org\/10.1090\/mcom\/3841","archive":["CLOCKSS","Portico"],"relation":{},"ISSN":["1088-6842","0025-5718"],"issn-type":[{"value":"1088-6842","type":"electronic"},{"value":"0025-5718","type":"print"}],"subject":[],"published":{"date-parts":[[2023,6,14]]}}}