Asymptotic stability of saddle points under the saddle-point dynamics

This paper considers continuously differentiable functions of two vector variables that have (possibly a continuum of) min-max saddle points. We study the asymptotic convergence properties of the associated saddle-point dynamics (gradient-descent in the first variable and gradient-ascent in the second one). We identify a suite of complementary conditions under which the set of saddle points is asymptotically stable under the saddle-point dynamics. Our first set of results is based on the convexity-concavity of the function defining the saddle-point dynamics to establish the convergence guarantees. For functions that do not enjoy this feature, our second set of results relies on properties of the linearization of the dynamics and the function along the proximal normals to the saddle set. We also provide global versions of the asymptotic convergence results. Various examples illustrate our discussion.

[1]  W. Marsden I and J , 2012 .

[2]  Xuan Zhang,et al.  A real-time control framework for smart power networks with star topology , 2013, 2013 American Control Conference.

[3]  B. V. Dean,et al.  Studies in Linear and Non-Linear Programming. , 1959 .

[4]  B. V. Dean,et al.  Studies in Linear and Non-Linear Programming. , 1959 .

[5]  T. Kose Solutions of Saddle Value Problems by Differential Equations , 1956 .

[6]  Yu. S. Ledyaev,et al.  Nonsmooth analysis and control theory , 1998 .

[7]  Fernando Paganini,et al.  Stability of primal-dual gradient dynamics and applications to network optimization , 2010, Autom..

[8]  Hans-Bernd Dürr,et al.  A smooth vector field for saddle point problems , 2011, IEEE Conference on Decision and Control and European Control Conference.

[9]  Magnus Egerstedt,et al.  Proportional integral distributed optimization for dynamic network topologies , 2014, 2014 American Control Conference.

[10]  J. Hofbauer,et al.  BEST RESPONSE DYNAMICS FOR CONTINUOUS ZERO{SUM GAMES , 2005 .

[11]  Pierre-Antoine Absil,et al.  On the stable equilibrium points of gradient systems , 2006, Syst. Control. Lett..

[12]  Enrique Mallada,et al.  Asymptotic convergence of constrained primal-dual dynamics , 2015, Syst. Control. Lett..

[13]  E. Barron,et al.  Best response dynamics for continuous games , 2010 .

[14]  T. Başar,et al.  Dynamic Noncooperative Game Theory , 1982 .

[15]  Nicola Elia,et al.  A distributed continuous-time gradient dynamics approach for the active power loss minimizations , 2013, 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[16]  Angelia Nedic,et al.  Subgradient Methods for Saddle-Point Problems , 2009, J. Optimization Theory and Applications.

[17]  Jing Wang,et al.  A control perspective for centralized and distributed convex optimization , 2011, IEEE Conference on Decision and Control and European Control Conference.

[18]  Jorge Cortés,et al.  Robust Distributed Linear Programming , 2014, IEEE Transactions on Automatic Control.

[19]  Ufuk Topcu,et al.  Design and Stability of Load-Side Primary Frequency Control in Power Systems , 2013, IEEE Transactions on Automatic Control.

[20]  Ioannis Lestas,et al.  On the convergence to saddle points of concave-convex functions, the gradient method and emergence of oscillations , 2014, 53rd IEEE Conference on Decision and Control.

[21]  S. Shankar Sastry,et al.  Characterization and computation of local Nash equilibria in continuous games , 2013, 2013 51st Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[22]  Bahman Gharesifard,et al.  Distributed Continuous-Time Convex Optimization on Weight-Balanced Digraphs , 2012, IEEE Transactions on Automatic Control.

[23]  M. Hirsch,et al.  Differential Equations, Dynamical Systems, and Linear Algebra , 1974 .

[24]  R. Bellman,et al.  Linear Programming and Economic Analysis. , 1958 .

[25]  Jorge Cortés,et al.  Distributed Bargaining in Dyadic-Exchange Networks , 2014, IEEE Transactions on Control of Network Systems.