Statistical Physics of Inference problems
نویسندگان
چکیده
1 Lecture 1 3 1.1 Bayesian Inference and Estimators . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.1.1 The Bayes formula . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.1.2 Estimators . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.2 A toy example in denoising . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.2.1 Phase transition in an easy example . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.2.2 The connection with Random Energy Model . . . . . . . . . . . . . . . . . . . . . . . 6 1.3 Taking averages: quenched, annealed and planted ensembles . . . . . . . . . . . . . . . . . . . 7 1.3.1 The Quenched ensemble . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.3.2 The Annealed ensemble . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.3.3 The Planted ensemble . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 1.4 The fundamental properties of planted problems . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.4.1 The two golden rules . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.4.2 The planted ensemble is the annealed ensemble, but the planted free energy is not the annealed free energy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.4.3 Equivalence between the planted and the Nishimori ensemble . . . . . . . . . . . . . . 10 1.5 The quenched ensemble and Large deviations . . . . . . . . . . . . . . . . . . . . . . . . . . . 11 1.5.1 The magic of quiet planting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
منابع مشابه
Replication-based inference algorithms for hard computational problems.
Inference algorithms based on evolving interactions between replicated solutions are introduced and analyzed on a prototypical NP-hard problem: the capacity of the binary Ising perceptron. The efficiency of the algorithm is examined numerically against that of the parallel tempering algorithm, showing improved performance in terms of the results obtained, computing requirements and simplicity o...
متن کاملStatistical physics of inference: Thresholds and algorithms
Many questions of fundamental interest in today’s science can be formulated as inference problems: Some partial, or noisy, observations are performed over a set of variables and the goal is to recover, or infer, the values of the variables based on the indirect information contained in the measurements. For such problems, the central scientific questions are: Under what conditions is the inform...
متن کاملVariational mean-field algorithm for efficient inference in large systems of stochastic differential equations.
This work introduces a Gaussian variational mean-field approximation for inference in dynamical systems which can be modeled by ordinary stochastic differential equations. This new approach allows one to express the variational free energy as a functional of the marginal moments of the approximating Gaussian process. A restriction of the moment equations to piecewise polynomial functions, over ...
متن کاملDirectionality of coupling from bivariate time series: how to avoid false causalities and missed connections.
We discuss some problems encountered in inference of directionality of coupling, or, in the case of two interacting systems, in inference of causality from bivariate time series. We identify factors and influences that can lead to either decreased test sensitivity or false detections and propose ways to cope with them in order to perform tests with high sensitivity and a low rate of false posit...
متن کاملConstraint satisfaction problems and neural networks: A statistical physics perspective.
A new field of research is rapidly expanding at the crossroad between statistical physics, information theory and combinatorial optimization. In particular, the use of cutting edge statistical physics concepts and methods allow one to solve very large constraint satisfaction problems like random satisfiability, coloring, or error correction. Several aspects of these developments should be relev...
متن کاملSurvey Propagation: Iterative Solutions to Constraint Satisfaction Problems
Iterative algorithms, such as the well known Belief Propagation algorithm, have had much success in solving problems in statistical inference and coding and information theory. Survey Propagation attempts to apply iterative message passing algorithms to solve difficult combinatorial problems, in particular constraint satisfaction problems such as k-sat and coloring problems. Intuition from stat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2014