doi: 10.3934/fods.2020011

Data-driven evolutions of critical points

1. 

Department of Mathematics, University of Vienna, Oskar-Morgenstern-Platz 1, 1090 Vienna, Austria

2. 

Department of Mathematics, Technical University of Munich, Boltzmannstrasse 3, 85748 Garching bei München, Germany

3. 

Institute of Mathematics and Scientific Computing, Karl-Franzens University of Graz, Heinrichstrasse 36/III, 8010 Graz, Austria

* Corresponding author

Published  August 2020

Fund Project: S.A. acknowledges the support of the DFG Transregio 109 "Discretization in Geometry and Dynamics". M.F. acknowledges the support of the DFG Project "Identification of Energies from Observation of Evolutions" and the DFG SPP 1962 "Non-smooth and Complementarity-based Distributed Parameter Systems: Simulation and Hierarchical Optimization". R.H. acknowledges the support of the DFG-FWF IGDK1754 "Optimization and Numerical Analysis for Partial Differential Equations with Nonsmooth Structures" and the hospitality of TUM during the preparation of this work

In this paper we are concerned with the learnability of energies from data obtained by observing time evolutions of their critical points starting at random initial equilibria. As a byproduct of our theoretical framework we introduce the novel concept of mean-field limit of critical point evolutions and of their energy balance as a new form of transport. We formulate the energy learning as a variational problem, minimizing the discrepancy of energy competitors from fulfilling the equilibrium condition along any trajectory of critical points originated at random initial equilibria. By $ \Gamma $-convergence arguments we prove the convergence of minimal solutions obtained from finite number of observations to the exact energy in a suitable sense. The abstract framework is actually fully constructive and numerically implementable. Hence, the approximation of the energy from a finite number of observations of past evolutions allows one to simulate further evolutions, which are fully data-driven. As we aim at a precise quantitative analysis, and to provide concrete examples of tractable solutions, we present analytic and numerical results on the reconstruction of an elastic energy for a one-dimensional model of thin nonlinear-elastic rod.

Citation: Stefano Almi, Massimo Fornasier, Richard Huber. Data-driven evolutions of critical points. Foundations of Data Science, doi: 10.3934/fods.2020011
References:
[1]

V. Agostiniani and R. Rossi, Singular vanishing-viscosity limits of gradient flows: The finite-dimensional case, J. Differential Equations, 263 (2017), 7815-7855.  doi: 10.1016/j.jde.2017.08.027.  Google Scholar

[2]

V. AgostinianiR. Rossi and G. Savaré, On the transversality conditions and their genericity, Rend. Circ. Mat. Palermo, 64 (2015), 101-116.  doi: 10.1007/s12215-014-0184-4.  Google Scholar

[3]

V. Agostiniani, R. Rossi, and G. Savaré, Singular vanishing-viscosity limits of gradient flows in Hilbert spaces, personal communication: in preparation, (2018). Google Scholar

[4]

V. AlbaniU. M. AscherX. Yang and J. P. Zubelli, Data driven recovery of local volatility surfaces, Inverse Probl. Imaging, 11 (2017), 799-823.  doi: 10.3934/ipi.2017038.  Google Scholar

[5]

L. Ambrosio, N. Fusco and D. Pallara, Functions of Bounded Variation and Free Discontinuity Problems, Oxford Mathematical Monographs. The Clarendon Press, Oxford University Press, New York, 2000.  Google Scholar

[6]

L. Ambrosio, N. Gigli and G. Savaré, Gradient flows in metric spaces and in the space of probability measures, Lectures in Mathematics ETH Zürich, Birkhäuser Verlag, Basel, second ed., 2008.  Google Scholar

[7]

M. BonginiM. FornasierM. Hansen and M. Maggioni, Inferring interaction rules from observations of evolutive systems Ⅰ: The variational approach, Math. Models Methods Appl. Sci., 27 (2017), 909-951.  doi: 10.1142/S0218202517500208.  Google Scholar

[8]

A. Braides, Γ-Convergence for Beginners, Oxford Lecture Series in Mathematics and its Applications, 22. Oxford University Press, Oxford, 2002. doi: 10.1093/acprof:oso/9780198507840.001.0001.  Google Scholar

[9]

T. Q. Chen, Y. Rubanova, J. Bettencourt and D. K. Duvenaud, Neural ordinary differential equations, Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi and R. Garnett, eds., Curran Associates, Inc., 31 (2018), 6571–6583. Google Scholar

[10]

S. ContiS. Müller and M. Ortiz, Data-driven problems in elasticity, Arch. Ration. Mech. Anal., 229 (2018), 79-123.  doi: 10.1007/s00205-017-1214-0.  Google Scholar

[11]

S. Crépey, Calibration of the local volatility in a generalized Black-Scholes model using Tikhonov regularization, SIAM J. Math. Anal., 34 (2003), 1183-1206.  doi: 10.1137/S0036141001400202.  Google Scholar

[12]

T. S. Cubitt, J. Eisert and M. M. Wolf, Extracting dynamical equations from experimental data is NP hard, Phys. Rev. Lett., 108 (2012), 120503. doi: 10.1103/PhysRevLett.108.120503.  Google Scholar

[13]

G. Dal Maso, An Introduction to $\Gamma$-Convergence, vol. 8 of Progress in Nonlinear Differential Equations and their Applications, Birkhäuser Boston, Inc., Boston, MA, 1993. doi: 10.1007/978-1-4612-0327-8.  Google Scholar

[14]

W. E, A proposal on machine learning via dynamical systems, Commun. Math. Stat., 5 (2017), 1-11.  doi: 10.1007/s40304-017-0103-z.  Google Scholar

[15]

W. E, J. Han and Q. Li, A mean-field optimal control formulation of deep learning, Res. Math. Sci., 6 (2019), No. 10, 41 pp. doi: 10.1007/s40687-018-0172-y.  Google Scholar

[16]

H. Egger and H. W. Engl, Tikhonov regularization applied to the inverse problem of option pricing: Convergence analysis and rates, Inverse Problems, 21 (2005), 1027-1045.  doi: 10.1088/0266-5611/21/3/014.  Google Scholar

[17]

R. Gerstberger and P. Rentrop, Feedforward neural nets as discretization schemes for ODES and DAES, 7th ICCAM 96 Congress., J. Comput. Appl. Math., 82 (1997), 117-128.  doi: 10.1016/S0377-0427(97)00085-X.  Google Scholar

[18]

M. C. Grant and S. P. Boyd, Graph implementations for nonsmooth convex programs, Recent Advances in Learning and Control, V. Blondel, S. Boyd, and H. Kimura, eds., Lecture Notes in Control and Information Sciences, Springer-Verlag Limited, 371 (2008), 95–110. doi: 10.1007/978-1-84800-155-8_7.  Google Scholar

[19]

M. Grant and S. Boyd, CVX: Matlab Software for Disciplined Convex Programming, version 2.1., http://cvxr.com/cvx, Mar. 2014. Google Scholar

[20]

J. Guckenheimer and P. Holmes, Nonlinear Oscillations, Dynamical Systems, and Bifurcations of Vector Fields, vol. 42 of Applied Mathematical Sciences, Springer-Verlag, New York, 1983. doi: 10.1007/978-1-4612-1140-2.  Google Scholar

[21]

T. Kirchdoerfer and M. Ortiz, Data-driven computational mechanics, Comput. Methods Appl. Mech. Engrg., 304 (2016), 81-101.  doi: 10.1016/j.cma.2016.02.001.  Google Scholar

[22]

F. Lu, M. Maggioni and S. Tang, Learning interaction kernels in heterogeneous systems of agents from multiple trajectories, arXiv: 1910.04832. Google Scholar

[23]

F. LuM. ZhongS. Tang and M. Maggioni, Nonparametric inference of interaction laws in systems of agents from trajectory data, Proc. Natl. Acad. Sci. USA, 116 (2019), 14424-14433.  doi: 10.1073/pnas.1822012116.  Google Scholar

[24]

E. Novak and H. Woźniakowski, Approximation of infinitely differentiable multivariate functions is intractable, J. Complexity, 25 (2009), 398-404.  doi: 10.1016/j.jco.2008.11.002.  Google Scholar

[25]

H. SchaefferG. Tran and R. Ward, Extracting sparse high-dimensional dynamics from limited data, SIAM J. Appl. Math., 78 (2018), 3279-3295.  doi: 10.1137/18M116798X.  Google Scholar

[26]

H. Schaeffer, G. Tran and R. Ward, Learning dynamical systems and bifurcation via group sparsity, arXiv: 1709.01558. Google Scholar

[27]

G. Scilla and F. Solombrino, Delayed loss of stability in singularly perturbed finite-dimensional gradient flows, Asymptot. Anal., 110 (2018), 1-19.  doi: 10.3233/ASY-181475.  Google Scholar

[28]

G. Scilla and F. Solombrino, Multiscale analysis of singularly perturbed finite dimensional gradient flows: The minimizing movement approach, Nonlinearity, 31 (2018), 5036-5074.  doi: 10.1088/1361-6544/aad6ac.  Google Scholar

[29]

G. Tran and R. Ward, Exact recovery of chaotic systems from highly corrupted data, Multiscale Model. Simul., 15 (2017), 1108-1129.  doi: 10.1137/16M1086637.  Google Scholar

[30]

C. Zanini, Singular perturbations of finite dimensional gradient flows, Discrete Contin. Dyn. Syst., 18 (2007), 657-675.  doi: 10.3934/dcds.2007.18.657.  Google Scholar

[31]

M. Zhong, J. Miller and M. Maggioni, Data-driven discovery of emergent behaviors in collective dynamics, Phys. D, 411 (2020), 132542, 25 pp. doi: 10.1016/j.physd.2020.132542.  Google Scholar

show all references

References:
[1]

V. Agostiniani and R. Rossi, Singular vanishing-viscosity limits of gradient flows: The finite-dimensional case, J. Differential Equations, 263 (2017), 7815-7855.  doi: 10.1016/j.jde.2017.08.027.  Google Scholar

[2]

V. AgostinianiR. Rossi and G. Savaré, On the transversality conditions and their genericity, Rend. Circ. Mat. Palermo, 64 (2015), 101-116.  doi: 10.1007/s12215-014-0184-4.  Google Scholar

[3]

V. Agostiniani, R. Rossi, and G. Savaré, Singular vanishing-viscosity limits of gradient flows in Hilbert spaces, personal communication: in preparation, (2018). Google Scholar

[4]

V. AlbaniU. M. AscherX. Yang and J. P. Zubelli, Data driven recovery of local volatility surfaces, Inverse Probl. Imaging, 11 (2017), 799-823.  doi: 10.3934/ipi.2017038.  Google Scholar

[5]

L. Ambrosio, N. Fusco and D. Pallara, Functions of Bounded Variation and Free Discontinuity Problems, Oxford Mathematical Monographs. The Clarendon Press, Oxford University Press, New York, 2000.  Google Scholar

[6]

L. Ambrosio, N. Gigli and G. Savaré, Gradient flows in metric spaces and in the space of probability measures, Lectures in Mathematics ETH Zürich, Birkhäuser Verlag, Basel, second ed., 2008.  Google Scholar

[7]

M. BonginiM. FornasierM. Hansen and M. Maggioni, Inferring interaction rules from observations of evolutive systems Ⅰ: The variational approach, Math. Models Methods Appl. Sci., 27 (2017), 909-951.  doi: 10.1142/S0218202517500208.  Google Scholar

[8]

A. Braides, Γ-Convergence for Beginners, Oxford Lecture Series in Mathematics and its Applications, 22. Oxford University Press, Oxford, 2002. doi: 10.1093/acprof:oso/9780198507840.001.0001.  Google Scholar

[9]

T. Q. Chen, Y. Rubanova, J. Bettencourt and D. K. Duvenaud, Neural ordinary differential equations, Advances in Neural Information Processing Systems, S. Bengio, H. Wallach, H. Larochelle, K. Grauman, N. Cesa-Bianchi and R. Garnett, eds., Curran Associates, Inc., 31 (2018), 6571–6583. Google Scholar

[10]

S. ContiS. Müller and M. Ortiz, Data-driven problems in elasticity, Arch. Ration. Mech. Anal., 229 (2018), 79-123.  doi: 10.1007/s00205-017-1214-0.  Google Scholar

[11]

S. Crépey, Calibration of the local volatility in a generalized Black-Scholes model using Tikhonov regularization, SIAM J. Math. Anal., 34 (2003), 1183-1206.  doi: 10.1137/S0036141001400202.  Google Scholar

[12]

T. S. Cubitt, J. Eisert and M. M. Wolf, Extracting dynamical equations from experimental data is NP hard, Phys. Rev. Lett., 108 (2012), 120503. doi: 10.1103/PhysRevLett.108.120503.  Google Scholar

[13]

G. Dal Maso, An Introduction to $\Gamma$-Convergence, vol. 8 of Progress in Nonlinear Differential Equations and their Applications, Birkhäuser Boston, Inc., Boston, MA, 1993. doi: 10.1007/978-1-4612-0327-8.  Google Scholar

[14]

W. E, A proposal on machine learning via dynamical systems, Commun. Math. Stat., 5 (2017), 1-11.  doi: 10.1007/s40304-017-0103-z.  Google Scholar

[15]

W. E, J. Han and Q. Li, A mean-field optimal control formulation of deep learning, Res. Math. Sci., 6 (2019), No. 10, 41 pp. doi: 10.1007/s40687-018-0172-y.  Google Scholar

[16]

H. Egger and H. W. Engl, Tikhonov regularization applied to the inverse problem of option pricing: Convergence analysis and rates, Inverse Problems, 21 (2005), 1027-1045.  doi: 10.1088/0266-5611/21/3/014.  Google Scholar

[17]

R. Gerstberger and P. Rentrop, Feedforward neural nets as discretization schemes for ODES and DAES, 7th ICCAM 96 Congress., J. Comput. Appl. Math., 82 (1997), 117-128.  doi: 10.1016/S0377-0427(97)00085-X.  Google Scholar

[18]

M. C. Grant and S. P. Boyd, Graph implementations for nonsmooth convex programs, Recent Advances in Learning and Control, V. Blondel, S. Boyd, and H. Kimura, eds., Lecture Notes in Control and Information Sciences, Springer-Verlag Limited, 371 (2008), 95–110. doi: 10.1007/978-1-84800-155-8_7.  Google Scholar

[19]

M. Grant and S. Boyd, CVX: Matlab Software for Disciplined Convex Programming, version 2.1., http://cvxr.com/cvx, Mar. 2014. Google Scholar

[20]

J. Guckenheimer and P. Holmes, Nonlinear Oscillations, Dynamical Systems, and Bifurcations of Vector Fields, vol. 42 of Applied Mathematical Sciences, Springer-Verlag, New York, 1983. doi: 10.1007/978-1-4612-1140-2.  Google Scholar

[21]

T. Kirchdoerfer and M. Ortiz, Data-driven computational mechanics, Comput. Methods Appl. Mech. Engrg., 304 (2016), 81-101.  doi: 10.1016/j.cma.2016.02.001.  Google Scholar

[22]

F. Lu, M. Maggioni and S. Tang, Learning interaction kernels in heterogeneous systems of agents from multiple trajectories, arXiv: 1910.04832. Google Scholar

[23]

F. LuM. ZhongS. Tang and M. Maggioni, Nonparametric inference of interaction laws in systems of agents from trajectory data, Proc. Natl. Acad. Sci. USA, 116 (2019), 14424-14433.  doi: 10.1073/pnas.1822012116.  Google Scholar

[24]

E. Novak and H. Woźniakowski, Approximation of infinitely differentiable multivariate functions is intractable, J. Complexity, 25 (2009), 398-404.  doi: 10.1016/j.jco.2008.11.002.  Google Scholar

[25]

H. SchaefferG. Tran and R. Ward, Extracting sparse high-dimensional dynamics from limited data, SIAM J. Appl. Math., 78 (2018), 3279-3295.  doi: 10.1137/18M116798X.  Google Scholar

[26]

H. Schaeffer, G. Tran and R. Ward, Learning dynamical systems and bifurcation via group sparsity, arXiv: 1709.01558. Google Scholar

[27]

G. Scilla and F. Solombrino, Delayed loss of stability in singularly perturbed finite-dimensional gradient flows, Asymptot. Anal., 110 (2018), 1-19.  doi: 10.3233/ASY-181475.  Google Scholar

[28]

G. Scilla and F. Solombrino, Multiscale analysis of singularly perturbed finite dimensional gradient flows: The minimizing movement approach, Nonlinearity, 31 (2018), 5036-5074.  doi: 10.1088/1361-6544/aad6ac.  Google Scholar

[29]

G. Tran and R. Ward, Exact recovery of chaotic systems from highly corrupted data, Multiscale Model. Simul., 15 (2017), 1108-1129.  doi: 10.1137/16M1086637.  Google Scholar

[30]

C. Zanini, Singular perturbations of finite dimensional gradient flows, Discrete Contin. Dyn. Syst., 18 (2007), 657-675.  doi: 10.3934/dcds.2007.18.657.  Google Scholar

[31]

M. Zhong, J. Miller and M. Maggioni, Data-driven discovery of emergent behaviors in collective dynamics, Phys. D, 411 (2020), 132542, 25 pp. doi: 10.1016/j.physd.2020.132542.  Google Scholar

Figure 1.  Reconstructions $ \hat a $ (left) and $ \hat a' $ (right) in dotted red and true $ a $ and $ a' $ in blue. The underlying red circles depict the (adaptive) nodes in $ \Lambda $. Below you see the distribution $ \tilde \eta $ of available data
Figure 2.  Reconstruction of $ a' $ with increasing number $ {N_e} $ of measurements. The true $ a' $ is depicted by the blue curve while the red line depicts the reconstruction $ \hat a' $ following (5.23). The red circles at the bottom of the figures depict the position of nodes of the underlying mesh $ \Lambda_N $. The histogram below describes the density of the available information encoded by the probability measure $ \tilde{\eta} $ for the case $ N_e = 60 $
Figure 3.  Reconstruction of $ a' $ for varying $ N $ and $ D(N) = 4N $ and distribution $ \tilde \eta $ for $ N = 60 $. Graphic as described in Figure 2
Figure 4.  Reconstruction of $ a' $ for varying $ N $ and fixed $ D(N) = 300 $ and distribution $ \tilde \eta $. Graphics as described in Figure 2
Figure 5.  Impact of different constants $ M_2 $ for constraints on $ a'' $ with $ \|a''\| \leq [2,5;20,1000] $ on reconstructs are depicted, showing improved approximations for increasing $ M_2 $. Graphics as in Figure 2
Figure 6.  Impact of changing constraint $ M_1 $ bounding the values of $ a' $, showing a projection-like behaviour of the reconstruction for small $ M_1 $. Graphics as in Figure 2
Figure 7.  Left showing $ \hat x_\varepsilon(t) $ (dark dashed) and $ x_\varepsilon(t) $ (line bright) with data from Section 5.2.2 at times $ t = [0.2 $, $ 0.4 $, $ 0.6 $, $ 0.8 $, $ 1.0] $, right with data from Section 5.2.3
[1]

Patrick Gerard, Christophe Pallard. A mean-field toy model for resonant transport. Kinetic & Related Models, 2010, 3 (2) : 299-309. doi: 10.3934/krm.2010.3.299

[2]

Alice Fiaschi. Young-measure quasi-static damage evolution: The nonconvex and the brittle cases. Discrete & Continuous Dynamical Systems - S, 2013, 6 (1) : 17-42. doi: 10.3934/dcdss.2013.6.17

[3]

Roman VodiČka, Vladislav MantiČ. An energy based formulation of a quasi-static interface damage model with a multilinear cohesive law. Discrete & Continuous Dynamical Systems - S, 2017, 10 (6) : 1539-1561. doi: 10.3934/dcdss.2017079

[4]

Dorothee Knees, Andreas Schröder. Computational aspects of quasi-static crack propagation. Discrete & Continuous Dynamical Systems - S, 2013, 6 (1) : 63-99. doi: 10.3934/dcdss.2013.6.63

[5]

Przemysław Górka. Quasi-static evolution of polyhedral crystals. Discrete & Continuous Dynamical Systems - B, 2008, 9 (2) : 309-320. doi: 10.3934/dcdsb.2008.9.309

[6]

Gerasimenko Viktor. Heisenberg picture of quantum kinetic evolution in mean-field limit. Kinetic & Related Models, 2011, 4 (1) : 385-399. doi: 10.3934/krm.2011.4.385

[7]

Seung-Yeal Ha, Jeongho Kim, Jinyeong Park, Xiongtao Zhang. Uniform stability and mean-field limit for the augmented Kuramoto model. Networks & Heterogeneous Media, 2018, 13 (2) : 297-322. doi: 10.3934/nhm.2018013

[8]

Michael Herty, Mattia Zanella. Performance bounds for the mean-field limit of constrained dynamics. Discrete & Continuous Dynamical Systems - A, 2017, 37 (4) : 2023-2043. doi: 10.3934/dcds.2017086

[9]

Irina F. Sivergina, Michael P. Polis. About global null controllability of a quasi-static thermoelastic contact system. Conference Publications, 2005, 2005 (Special) : 816-823. doi: 10.3934/proc.2005.2005.816

[10]

Christopher J. Larsen. Local minimality and crack prediction in quasi-static Griffith fracture evolution. Discrete & Continuous Dynamical Systems - S, 2013, 6 (1) : 121-129. doi: 10.3934/dcdss.2013.6.121

[11]

Xianping Wu, Xun Li, Zhongfei Li. A mean-field formulation for multi-period asset-liability mean-variance portfolio selection with probability constraints. Journal of Industrial & Management Optimization, 2018, 14 (1) : 249-265. doi: 10.3934/jimo.2017045

[12]

Seung-Yeal Ha, Jeongho Kim, Peter Pickl, Xiongtao Zhang. A probabilistic approach for the mean-field limit to the Cucker-Smale model with a singular communication. Kinetic & Related Models, 2019, 12 (5) : 1045-1067. doi: 10.3934/krm.2019039

[13]

Young-Pil Choi, Samir Salem. Cucker-Smale flocking particles with multiplicative noises: Stochastic mean-field limit and phase transition. Kinetic & Related Models, 2019, 12 (3) : 573-592. doi: 10.3934/krm.2019023

[14]

Seung-Yeal Ha, Jeongho Kim, Xiongtao Zhang. Uniform stability of the Cucker-Smale model and its application to the Mean-Field limit. Kinetic & Related Models, 2018, 11 (5) : 1157-1181. doi: 10.3934/krm.2018045

[15]

Joachim Crevat. Mean-field limit of a spatially-extended FitzHugh-Nagumo neural network. Kinetic & Related Models, 2019, 12 (6) : 1329-1358. doi: 10.3934/krm.2019052

[16]

Rong Yang, Li Chen. Mean-field limit for a collision-avoiding flocking system and the time-asymptotic flocking dynamics for the kinetic equation. Kinetic & Related Models, 2014, 7 (2) : 381-400. doi: 10.3934/krm.2014.7.381

[17]

Franco Flandoli, Matti Leimbach. Mean field limit with proliferation. Discrete & Continuous Dynamical Systems - B, 2016, 21 (9) : 3029-3052. doi: 10.3934/dcdsb.2016086

[18]

Thierry Paul, Mario Pulvirenti. Asymptotic expansion of the mean-field approximation. Discrete & Continuous Dynamical Systems - A, 2019, 39 (4) : 1891-1921. doi: 10.3934/dcds.2019080

[19]

Marc Bocquet, Julien Brajard, Alberto Carrassi, Laurent Bertino. Bayesian inference of chaotic dynamics by merging data assimilation, machine learning and expectation-maximization. Foundations of Data Science, 2020, 2 (1) : 55-80. doi: 10.3934/fods.2020004

[20]

Diogo A. Gomes, Gabriel E. Pires, Héctor Sánchez-Morgado. A-priori estimates for stationary mean-field games. Networks & Heterogeneous Media, 2012, 7 (2) : 303-314. doi: 10.3934/nhm.2012.7.303

 Impact Factor: 

Article outline

Figures and Tables

[Back to Top]