Fast and Provably Accurate Bilateral Filtering

Provably Fast and Accurate Recovery

Fast and Accurate Arc Filtering for Dependency Parsing

We propose a series of learned arc filters to speed up graph-based dependency parsing. A cascade of filters identify implausible head-modifier pairs, with time complexity that is first linear, and then quadratic in the length of the sentence. The linear filters reliably predict, in context, words that are roots or leaves of dependency trees, and words that are likely to have heads on their left...

Provably Accurate Double-Sparse Coding

Sparse coding is a crucial subroutine in algorithms for various signal processing, deep learning, and other machine learning applications. The central goal is to learn an overcomplete dictionary that can sparsely represent a given dataset. However, storage, transmission, and processing of the learned dictionary can be untenably high if the data dimension is high. In this paper, we consider the ...

Fast O(1) bilateral filtering using trigonometric range kernels

It is well known that spatial averaging can be realized (in space or frequency domain) using algorithms whose complexity does not scale with the size or shape of the filter. These fast algorithms are generally referred to as constant-time or O(1) algorithms in the image-processing literature. Along with the spatial filter, the edge-preserving bilateral filter involves an additional range kernel...

Provably Fast and Accurate Recovery of Evolutionary Trees through Harmonic Greedy Triplets

We give a greedy learning algorithm for reconstructing an evolutionary tree based on a certain harmonic average on triplets of terminal taxa. After the pairwise distances between terminal taxa are estimated from sequence data, the algorithm runs in O(n2) time using O(n) work space, where n is the number of terminal taxa. These time and space complexities are optimal in the sense that the size o...