6 papers
Parallelized Computation and Backpropagation Under Angle-Parametrized Orthogonal Matrices
Firas Hamze
We present a methodology for parallel acceleration of learning in the presence of matrix orthogonality and unitarity constraints of interest in several branches of machine learning…
Chook -- A comprehensive suite for generating binary optimization problems with planted solutions
Dilina Perera, Inimfon Akpabio, Firas Hamze +4
We present Chook, an open-source Python-based tool to generate discrete optimization problems of tunable complexity with a priori known solutions. Chook provides a cross-platform u…
Computational hardness of spin-glass problems with tile-planted solutions
Dilina Perera, Firas Hamze, Jack Raymond +2
We investigate the computational hardness of spin-glass instances on a square lattice, generated via a recently introduced tunable and scalable approach for planting solutions. The…
The Wishart planted ensemble: A tunably-rugged pairwise Ising model with a first-order phase transition
Firas Hamze, Jack Raymond, Christopher A. Pattison +2
We propose the Wishart planted ensemble, a class of zero-field Ising models with tunable algorithmic hardness and specifiable (or planted) ground state. The problem class arises fr…
Learning to find order in disorder
Humberto Munoz-Bauza, Firas Hamze, Helmut G. Katzgraber
We introduce the use of neural networks as classifiers on classical disordered systems with no spatial ordering. In this study, we implement a convolutional neural network trained…
From Fields to Trees
Firas Hamze, Nando de Freitas
We present new MCMC algorithms for computing the posterior distributions and expectations of the unknown variables in undirected graphical models with regular structure. For demons…