Lyapunov function for interacting reinforced stochastic processes via Hopfield’s energy function. (English) Zbl 1532.60222
Summary: In 1984, J. J. Hopfield [Proc. Natl. Acad. Sci. USA 81, 3088–3092 (1984; Zbl 1371.92015)] introduced an artificial neural network to understand the memory in living organisms. Under a condition of symmetry, he showed that there exists a Lyapunov function (known as energy function) for the network. In 2015, A. Budhiraja et al. [Electron. J. Probab. 20, Paper No. 80, 22 p. (2015; Zbl 1321.60202)] introduced an idea to construct Lyapunov functions for nonlinear Markov processes via relative entropy. In this article, we introduce an approach based on the energy function of Hopfield networks to obtain Lyapunov functions for a class of interacting reinforced stochastic processes. Our result is an alternative to Budhiraja, Dupuis and Fischer’s approach and it works for the case of processes with finitely many 2-dimensional probability measures. We also bring from the neural network framework results about the total stability of differential equations. Finally, we include an application of the results to the study of differential equations associated to \(n \geq 2\) vertex reinforced random walks on two-vertex graphs.
MSC:
| 60K35 | Interacting random processes; statistical mechanics type models; percolation theory |
| 92B20 | Neural networks for/in biological studies, artificial life and related topics |
| 60G50 | Sums of independent random variables; random walks |
| 60J10 | Markov chains (discrete-time Markov processes on discrete state spaces) |
References:
| [1] | Benaïm, Michel, Vertex-reinforced random walks and a conjecture of pemantle. Ann. Probab., 1, 361-392 (1997) · Zbl 0873.60044 |
| [2] | Benaïm, Michel, On gradient like properties of population games, learning models and self reinforced processes (2015) |
| [3] | Benaïm, Michel; Benjamini, Itai; Chen, Jun; Lima, Yuri, A generalized Pólya’s urn with graph based interactions. Random Struct. Algorithms, 4, 614-634 (2015) · Zbl 1317.05103 |
| [4] | Benaim, Michel; Raimond, Olivier; Schapira, Bruno, Strongly vertex-reinforced-random-walk on a complete graph. ALEA Lat. Am. J. Probab. Math. Stat., 2, 767-782 (2013) · Zbl 1277.60169 |
| [5] | Benaïm, Michel; Tarrès, Pierre, Dynamics of vertex-reinforced random walks. Ann. Probab., 6, 2178-2223 (2011) · Zbl 1242.60044 |
| [6] | Budhiraja, Amarjit; Dupuis, Paul; Fischer, Markus; Ramanan, Kavita, Limits of relative entropies associated with weakly interacting particle systems. Electron. J. Probab., 80, 22 (2015) · Zbl 1321.60202 |
| [7] | Budhiraja, Amarjit; Dupuis, Paul; Fischer, Markus; Ramanan, Kavita, Local stability of Kolmogorov forward equations for finite state nonlinear Markov processes. Electron. J. Probab., 81, 30 (2015) · Zbl 1337.60240 |
| [8] | Chen, Jun; Lucas, Cyrille, A generalized Pólya’s urn with graph based interactions: convergence at linearity. Electron. Commun. Probab., 67, 13 (2014) · Zbl 1326.60135 |
| [9] | Forti, M.; Manetti, S.; Marini, M., Necessary and sufficient condition for absolute stability of neural networks. IEEE Trans. Circuits Syst. I, 7, 491-494 (1994) · Zbl 0925.92014 |
| [10] | Hirsch, M. W., Convergence in neural nets. Proc. Int. Joint Conf. Neural Netw., 9, 115-125 (1987) |
| [11] | Hopfield, John J., Neurons with graded response have collective computational properties like those of 2-state neuros. Proc. Natl. Acad. Sci. USA, 10, 3088-3092 (1984) · Zbl 1371.92015 |
| [12] | Liang, Xue-Bin; Wu, Li-De, A simple proof of a necessary and sufficient condition for absolute stability of symmetric neural networks. IEEE Trans. Circuits Syst. I, 9, 1010-1011 (1998) · Zbl 1055.93548 |
| [13] | Lima, Yuri, Graph-based Pólya’s urn: completion of the linear case. Stoch. Dyn., 2 (2016), 13 · Zbl 1335.60185 |
| [14] | Pemantle, Robin, Vertex-reinforced random walk. Probab. Theory Related Fields, 1, 117-136 (1992) · Zbl 0741.60029 |
| [15] | Pemantle, Robin, A survey of random processes with reinforcement. Probab. Surv., 1-79 (2007) · Zbl 1189.60138 |
| [16] | Rosales, Rafael A.; Prado, Fernando P. A.; Pires, Benito, Vertex reinforced random walks with exponential interaction on complete graphs. Stochastic Process. Appl., 353-379 (2022) · Zbl 1492.60289 |
| [17] | Sandholm, William H., xiv+589 |
| [18] | Schapira, Bruno, Localization on 5 sites for vertex reinforced random walks: towards a characterization. Ann. Appl. Probab., 4, 1774-1786 (2021) · Zbl 1479.60202 |
| [19] | Vidyasagar, M., Location and stability of the high-gain equilibria of nonlinear neural networks. IEEE Trans. Neural Netw., 4, 660-672 (1993) |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
