Maximum Entropy Distributions on Graphs by Andre Yohannes Wibisono
نویسنده
چکیده
Maximum Entropy Distributions on Graphs by Andre Yohannes Wibisono Master of Arts in Statistics University of California, Berkeley Professor Michael I. Jordan, Chair We study the maximum entropy distribution on weighted graphs with a given expected degree sequence. This distribution on graphs is characterized by independent edge weights parameterized by vertex potentials at each node. Using the general theory of exponential family distributions, we prove the existence and uniqueness of the maximum likelihood estimator (MLE) of the vertex parameters. We also prove the consistency of the MLE from a single graph sample, extending the results of Chatterjee, Diaconis, and Sly for unweighted (binary) graphs. Interestingly, our extensions require an intricate study of the inverses of diagonally dominant positive matrices. Along the way, we derive analogues of the Erdős-Gallai criterion of graphical sequences for weighted graphs.
منابع مشابه
Maximum entropy distributions on graphs
Inspired by the problem of sensory coding in neuroscience, we study the maximum entropy distribution on weighted graphs with a given expected degree sequence. This distribution on graphs is characterized by independent edge weights parameterized by vertex potentials at each node. Using the general theory of exponential family distributions, we prove the existence and uniqueness of the maximum l...
متن کاملTight bounds on the infinity norm of inverses of symmetric diagonally dominant positive matrices
We prove tight bounds for the ∞-norm of the inverse of symmetric diagonally dominant positive matrices. Applications include numerical stability for linear systems, bounds on inverses of differentiable functions, and the consistency of maximum entropy graph distributions from single samples.
متن کاملVariational and Dynamical Perspectives On Learning and Optimization
Variational and Dynamical Perspectives On Learning and Optimization by Andre Yohannes Wibisono Doctor of Philosophy in Computer Science University of California, Berkeley Professor Michael Jordan, Chair The problem of learning from data is prevalent in the modern scientific age, and optimization provides a natural mathematical language for describing learning problems. We study some problems in...
متن کاملA Note on the Bivariate Maximum Entropy Modeling
Let X=(X1 ,X2 ) be a continuous random vector. Under the assumption that the marginal distributions of X1 and X2 are given, we develop models for vector X when there is partial information about the dependence structure between X1 and X2. The models which are obtained based on well-known Principle of Maximum Entropy are called the maximum entropy (ME) mo...
متن کاملInverses of symmetric, diagonally dominant positive matrices and applications
We prove tight bounds for the ∞-norm of the inverse of a symmetric, diagonally dominant positive matrix J ; in particular, we show that ‖J‖∞ is uniquely maximized among all such J . We also prove a new lower-bound form of Hadamard’s inequality for the determinant of diagonally dominant positive matrices and an improved upper bound for diagonally balanced positive matrices. Applications of our r...
متن کامل