Conditional Random Fields, Planted Constraint Satisfaction and Entropy Concentration
نویسندگان
چکیده
This paper studies a class of probabilistic models on graphs, where edge variables depend on incident node variables through a fixed probability kernel. The class includes planted constraint satisfaction problems (CSPs), as well as more general structures motivated by coding and community clustering problems. It is shown that under mild assumptions on the kernel and for sparse random graphs, the conditional entropy of the node variables given the edge variables concentrates around a deterministic threshold. This implies in particular the concentration of the number of solutions in a broad class of planted CSPs, the existence of a threshold function for the disassortative stochastic block model, and the proof of a conjecture on parity check codes. It also establishes new connections among coding, clustering and satisfiability. ∗ Department of Electrical Engineering and Program in Applied and Computational Mathematics, Princeton University, Email: [email protected] † Departments of Electrical Engineering and Statistics, Stanford University, Email: [email protected]
منابع مشابه
Conditional Random Fields, Planted Satisfaction, and Entropy Concentration
This paper studies a class of probabilistic models on graphs, where edge variables depend on incident node variables through a fixed probability kernel. The class includes planted constraint satisfaction problems (CSPs), as well as more general structures motivated by coding and community clustering problems. It is shown that under mild assumptions on the kernel, the conditional entropy of the ...
متن کاملHiding Quiet Solutions in Random Constraint Satisfaction Problems
We study constraint satisfaction problems on the so-called planted random ensemble. We show that for a certain class of problems, e.g., graph coloring, many of the properties of the usual random ensemble are quantitatively identical in the planted random ensemble. We study the structural phase transitions and the easy-hard-easy pattern in the average computational complexity. We also discuss th...
متن کاملQuiet Planting in the Locked Constraint Satisfaction Problems
We study the planted ensemble of locked constraint satisfaction problems. We describe the connection between the random and planted ensembles. The use of the cavity method is combined with arguments from reconstruction on trees and first and second moment considerations; in particular the connection with the reconstruction on trees appears to be crucial. Our main result is the location of the h...
متن کاملSpecial Section on Constraint Satisfaction Problems and Message Passing Algorithms
Recent years have seen the emergence of a fascinating cross-disciplinary area at the interface of statistical physics, combinatorial optimization, information theory, and computer science. Many important questions in various branches of science can be formulated as problems of optimization or inference, and the framework of graphical models provides a common language. Topics range from constrai...
متن کاملSubsampled Power Iteration: a Unified Algorithm for Block Models and Planted CSP's
We present an algorithm for recovering planted solutions in two well-known models, the stochastic block model and planted constraint satisfaction problems (CSP), via a common generalization in terms of random bipartite graphs. Our algorithm matches up to a constant factor the best-known bounds for the number of edges (or constraints) needed for perfect recovery and its running time is linear in...
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:
- Theory of Computing
دوره 11 شماره
صفحات -
تاریخ انتشار 2013