Morteza Ibrahimi

Robust max-product belief propagation

We study the problem of optimizing a graph-structured objective function under adversarial uncertainty. This problem can be modeled as a two-persons zero-sum game between an Engineer and Nature. The Engineer controls a subset of the variables (nodes in the graph), and tries to assign their values to maximize an objective function. Nature controls the complementary subset of variables and tries to minimize the same objective. This setting encompasses estimation and optimization problems under model uncertainty, and strategic problems with a graph structure. Von Neumanns minimax theorem guarantees the existence of a (minimax) pair of randomized strategies that provide optimal robustness for each player against its adversary. We prove several structural properties of this strategy pair in the case of graph-structured payoff function. In particular, the randomized minimax strategies (distributions over variable assignments) can be chosen in such a way to satisfy the Markov property with respect to the graph. This significantly reduces the problem dimensionality. Finally we introduce a message passing algorithm to solve this minimax problem. The algorithm generalizes max-product belief propagation to this new domain.

The set of solutions of random XORSAT formulae

The XOR-satisfiability (XORSAT) problem requires finding an assignment of

A renewable, modular, and time-responsive DNA circuit

n

Renewable, Time-Responsive DNA Logic Gates for Scalable Digital Circuits

Boolean variables that satisfy

Information theoretic limits on learning stochastic differential equations

m

Accelerated Time-of-Flight Mass Spectrometry

exclusive OR (XOR) clauses, whereby each clause constrains a subset of the variables. We consider random XORSAT instances, drawn uniformly at random from the ensemble of formulae containing

Support Recovery for the Drift Coefficient of High-Dimensional Diffusions

n

Accelerated time-of-flight mass spectrometry

variables and

Learning Networks of Stochastic Differential Equations

m

Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems

clauses of size