Banach's fixed point theorem for contraction maps has been widely used to analyze the convergence of iterative methods in nonconvex problems. It is a common experience, however, that iterative maps fail to be globally contracting under the natural metric in their domain, making the applicability of Banach's theorem limited. We explore how generally we can apply Banach's fixed point theorem to establish the convergence of iterative methods when pairing it with carefully designed metrics. Our first result is a strong converse of Banach's theorem, showing that it is a universal analysis tool for establishing global convergence of iterative methods to unique fixed points, and for bounding their convergence rate. In other words, we show that, whenever an iterative map globally converges to a unique fixed point, there exists a metric under which the iterative map is contracting and which can be used to bound the number of iterations until convergence. We illustrate our approach in the widely used power method, providing a new way of bounding its convergence rate through contraction arguments. We next consider the computational complexity of Banach's fixed point theorem. Making the proof of our converse theorem constructive, we show that computing a fixed point whose existencemore »
A Converse to Banach's Fixed Point Theorem and its CLS Completeness
Banach's fixed point theorem for contraction maps has been widely used to analyze the convergence of iterative methods in nonconvex problems. It is a common experience, however, that iterative maps fail to be globally contracting under the natural metric in their domain, making the applicability of Banach's theorem limited. We explore how generally we can apply Banach's fixed point theorem to establish the convergence of iterative methods when pairing it with carefully designed metrics. Our first result is a strong converse of Banach's theorem, showing that it is a universal analysis tool for establishing global convergence of iterative methods to unique fixed points, and for bounding their convergence rate. In other words, we show that, whenever an iterative map globally converges to a unique fixed point, there exists a metric under which the iterative map is contracting and which can be used to bound the number of iterations until convergence. We illustrate our approach in the widely used power method, providing a new way of bounding its convergence rate through contraction arguments.
We next consider the computational complexity of Banach's fixed point theorem. Making the proof of our converse theorem constructive, we show that computing a fixed point whose existence is more »
 Publication Date:
 NSFPAR ID:
 10079724
 Journal Name:
 Proceedings of the annual ACM Symposium on Theory of Computing
 ISSN:
 07378017
 Sponsoring Org:
 National Science Foundation
More Like this


We consider the periodic review dynamic pricing and inventory control problem with fixed ordering cost. Demand is random and price dependent, and unsatisfied demand is backlogged. With complete demand information, the celebrated [Formula: see text] policy is proved to be optimal, where s and S are the reorder point and orderupto level for ordering strategy, and [Formula: see text], a function of onhand inventory level, characterizes the pricing strategy. In this paper, we consider incomplete demand information and develop online learning algorithms whose average profit approaches that of the optimal [Formula: see text] with a tight [Formula: see text] regret rate. A number of salient features differentiate our work from the existing online learning researches in the operations management (OM) literature. First, computing the optimal [Formula: see text] policy requires solving a dynamic programming (DP) over multiple periods involving unknown quantities, which is different from the majority of learning problems in OM that only require solving singleperiod optimization questions. It is hence challenging to establish stability results through DP recursions, which we accomplish by proving uniform convergence of the profittogo function. The necessity of analyzing actiondependent state transition over multiple periods resembles the reinforcement learning question, considerably more difficult thanmore »

Motivated by applications in Game Theory, Optimization, and Generative Adversarial Networks, recent work of Daskalakis et al~\cite{DISZ17} and followup work of Liang and Stokes~\cite{LiangS18} have established that a variant of the widely used Gradient Descent/Ascent procedure, called "Optimistic Gradient Descent/Ascent (OGDA)", exhibits lastiterate convergence to saddle points in {\em unconstrained} convexconcave minmax optimization problems. We show that the same holds true in the more general problem of {\em constrained} minmax optimization under a variant of the noregret MultiplicativeWeightsUpdate method called "Optimistic MultiplicativeWeights Update (OMWU)". This answers an open question of Syrgkanis et al~\cite{SALS15}. The proof of our result requires fundamentally different techniques from those that exist in noregret learning literature and the aforementioned papers. We show that OMWU monotonically improves the KullbackLeibler divergence of the current iterate to the (appropriately normalized) minmax solution until it enters a neighborhood of the solution. Inside that neighborhood we show that OMWU becomes a contracting map converging to the exact solution. We believe that our techniques will be useful in the analysis of the last iterate of other learning algorithms.

Embedding properties of network realizations of dissipative reduced order models Jörn Zimmerling, Mikhail Zaslavsky,Rob Remis, Shasri Moskow, Alexander Mamonov, Murthy Guddati, Vladimir Druskin, and Liliana Borcea Mathematical Sciences Department, Worcester Polytechnic Institute https://www.wpi.edu/people/vdruskin Abstract Realizations of reduced order models of passive SISO or MIMO LTI problems can be transformed to tridiagonal and blocktridiagonal forms, respectively, via dierent modications of the Lanczos algorithm. Generally, such realizations can be interpreted as ladder resistorcapacitorinductor (RCL) networks. They gave rise to network syntheses in the rst half of the 20th century that was at the base of modern electronics design and consecutively to MOR that tremendously impacted many areas of engineering (electrical, mechanical, aerospace, etc.) by enabling ecient compression of the underlining dynamical systems. In his seminal 1950s works Krein realized that in addition to their compressing properties, network realizations can be used to embed the data back into the state space of the underlying continuum problems. In more recent works of the authors Krein's ideas gave rise to socalled nitedierence Gaussian quadrature rules (FDGQR), allowing to approximately map the ROM statespace representation to its full order continuum counterpart on a judicially chosen grid. Thus, the state variables can be accessed directly from themore »

We leverage the connections between nonexpansive maps, monotone Lipschitz operators, and proximal mappings to obtain nearoptimal (i.e., optimal up to polylog factors in terms of iteration complexity) and parameterfree methods for solving monotone inclusion problems. These results immediately translate into nearoptimal guarantees for approximating strong solutions to variational inequality problems, approximating convexconcave minmax optimization problems, and minimizing the norm of the gradient in minmax optimization problems. Our analysis is based on a novel and simple potentialbased proof of convergence of Halpern iteration, a classical iteration for finding fixed points of nonexpansive maps. Additionally, we provide a series of algorithmic reductions that highlight connections between different problem classes and lead to lower bounds that certify nearoptimality of the studied methods.