arXiv subjects

R. Zecchina

Publications and source records attributed to R. Zecchina.

46 records · Page 3Linked to original sources

arXiv2001

Learning to coordinate in a complex and non-stationary world

We study analytically and by computer simulations a complex system of adaptive agents with finite memory. Borrowing the framework of the Minority Game and using the replica formalism we show the existence of an equilibrium phase transition as a function of the ratio between the memory $λ$ and the learning rates $Γ$ of the agents. We show that, starting from a random configuration, a dynamic phase transition also exists, which prevents the system from reaching any Nash equilibria. Furthermore, in a non-stationary environment, we show by numerical simulations that agents with infinite memory play worst than others with less memory and that the dynamic transition naturally arises independently from the initial conditions.

cond-mat.stat-mech↗

arXiv2001

Statistical mechanics methods and phase transitions in optimization problems

Recently, it has been recognized that phase transitions play an important role in the probabilistic analysis of combinatorial optimization problems. However, there are in fact many other relations that lead to close ties between computer science and statistical physics. This review aims at presenting the tools and concepts designed by physicists to deal with optimization or decision problems in an accessible language for computer scientists and mathematicians, with no prerequisites in physics. We first introduce some elementary methods of statistical mechanics and then progressively cover the tools appropriate for disordered systems. In each case, we apply these methods to study the phase transitions or the statistical properties of the optimal solutions in various combinatorial problems. We cover in detail the Random Graph, the Satisfiability, and the Traveling Salesman problems. References to the physics literature on optimization are provided. We also give our perspective regarding the interdisciplinary contribution of physics to computer science.

cond-mat.stat-mech↗

arXiv2001

Phase coexistence and finite-size scaling in random combinatorial problems

We study an exactly solvable version of the famous random Boolean satisfiability problem, the so called random XOR-SAT problem. Rare events are shown to affect the combinatorial ``phase diagram'' leading to a coexistence of solvable and unsolvable instances of the combinatorial problem in a certain region of the parameters characterizing the model. Such instances differ by a non-extensive quantity in the ground state energy of the associated diluted spin-glass model. We also show that the critical exponent $ν$, controlling the size of the critical window where the probability of having solutions vanishes, depends on the model parameters, shedding light on the link between random hyper-graph topology and universality classes. In the case of random satisfiability, a similar behavior was conjectured to be connected to the onset of computational intractability.

cond-mat.dis-nn↗

arXiv2000

Simplest random K-satisfiability problem

We study a simple and exactly solvable model for the generation of random satisfiability problems. These consist of $γN$ random boolean constraints which are to be satisfied simultaneously by $N$ logical variables. In statistical-mechanics language, the considered model can be seen as a diluted p-spin model at zero temperature. While such problems become extraordinarily hard to solve by local search methods in a large region of the parameter space, still at least one solution may be superimposed by construction. The statistical properties of the model can be studied exactly by the replica method and each single instance can be analyzed in polynomial time by a simple global solution method. The geometrical/topological structures responsible for dynamic and static phase transitions as well as for the onset of computational complexity in local search method are thoroughly analyzed. Numerical analysis on very large samples allows for a precise characterization of the critical scaling behaviour.

cond-mat.dis-nn↗

arXiv2000

Comment on: Thermal model for Adaptive Competition in a Market

We show that the dynamical equations describing the collective behavior of the model introduced by Cavagna et al. i) are not their Eqs. (5,6) but rather ii) are the same as those of the minority game (MG). As a consequence the analytic solution of the MG presented in [PRL, 84, 1824 (2000)] holds also for this model. Finally we show that iii) the the large temperature behavior of the model is different, due to small simulation times, from that discussed by Cavagna et al.

cond-mat.stat-mech↗

arXiv1999

Statistical mechanics of systems with heterogeneous agents: Minority Games

We study analytically a simple game theoretical model of heterogeneous interacting agents. We show that the stationary state of the system is described by the ground state of a disordered spin model which is exactly solvable within the simple replica symmetric ansatz. Such a stationary state differs from the Nash equilibrium where each agent maximizes her own utility. The latter turns out to be characterized by a replica symmetry broken structure. Numerical results fully agree with our analytic findings.

cond-mat.stat-mech↗

arXiv1999

2+p-SAT: Relation of Typical-Case Complexity to the Nature of the Phase Transition

Heuristic methods for solution of problems in the NP-Complete class of decision problems often reach exact solutions, but fail badly at "phase boundaries", across which the decision to be reached changes from almost always having one value to almost having a different value. We report an analytic solution and experimental investigations of the phase transition that occurs in the limit of very large problems in K-SAT. The nature of its "random first-order" phase transition, seen at values of K large enough to make the computational cost of solving typical instances increase exponenitally with problem size, suggest a mechanism for the cost increase. There has been evidence for features like the "backbone" of frozen inputs which characterizes the UNSAT phase in K-SAT in the study of models of disordered materials, but this feature and this transition are uniquely accessible to analysis in K-SAT. The random first order transition combines properties of the 1st order (discontinuous onset of order) and 2nd order (with power law scaling, e.g. of the width of the the critical region in a finite system) transitions known in the physics of pure solids. Such transitions should occur in other combinatoric problems in the large N limit. Finally, improved search heuristics may be developed when a "backbone" is known to exist.

cond-mat.dis-nn↗

arXiv1998

Time scale separation and heterogeneous off-equilibrium dynamics in spin models over random graphs

We study analytically and numerically the statics and the off-equilibrium dynamics of spin models over finitely connected random graphs. We identify a threshold value for the connectivity beyond which the loop structure of the graph becomes thermodynamically relevant. Glauber dynamics simulations show that this loop structure is responsible for the onset of dynamical features of a local character (dynamical heterogeneities and spontaneous time scale separation), consistently with previous (experimental and numerical) studies of glasses and spin glasses in their approach to the low temperature phase.

cond-mat.dis-nn↗

arXiv1997

Statistical mechanics of the random K-SAT model

The Random K-Satisfiability Problem, consisting in verifying the existence of an assignment of N Boolean variables that satisfy a set of M=alpha N random logical clauses containing K variables each, is studied using the replica symmetric framework of diluted disordered systems. We present an exact iterative scheme for the replica symmetric functional order parameter together for the different cases of interest K=2, K>= 3 and K>>1. The calculation of the number of solutions, which allowed us [Phys. Rev. Lett. 76, 3881 (1996)] to predict a first order jump at the threshold where the Boolean expressions become unsatisfiable with probability one, is thoroughly displayed. In the case K=2, the (rigorously known) critical value (alpha=1) of the number of clauses per Boolean variable is recovered while for K>=3 we show that the system exhibits a replica symmetry breaking transition. The annealed approximation is proven to be exact for large K.

cond-mat.dis-nn↗

arXiv1995

Weight Space Structure and Internal Representations: a Direct Approach to Learning and Generalization in Multilayer Neural Network

We analytically derive the geometrical structure of the weight space in multilayer neural networks (MLN), in terms of the volumes of couplings associated to the internal representations of the training set. Focusing on the parity and committee machines, we deduce their learning and generalization capabilities both reinterpreting some known properties and finding new exact results. The relationship between our approach and information theory as well as the Mitchison--Durbin calculation is established. Our results are exact in the limit of a large number of hidden units, showing that MLN are a class of exactly solvable models with a simple interpretation of replica symmetry breaking.

cond-mat↗