4 papers
ArrowFlow: Hierarchical Machine Learning in the Space of Permutations
Ozgur Yilmaz
We introduce ArrowFlow, a machine learning architecture that operates entirely in the space of permutations. Its computational units are ranking filters, learned orderings that com…
Partially deterministic sampling for compressed sensing with denoising guarantees
Yaniv Plan, Matthew S. Scott, Ozgur Yilmaz
We study compressed sensing when the sampling vectors are chosen from the rows of a unitary matrix. In the literature, these sampling vectors are typically chosen randomly; the use…
Denoising guarantees for optimized sampling schemes in compressed sensing
Yaniv Plan, Matthew S. Scott, Xia Sheng +1
Compressed sensing with subsampled unitary matrices benefits from \emph{optimized} sampling schemes, which feature improved theoretical guarantees and empirical performance relativ…
Near-optimal sample complexity for convex tensor completion
Navid Ghadermarzy, Yaniv Plan, Özgür Yılmaz
We analyze low rank tensor completion (TC) using noisy measurements of a subset of the tensor. Assuming a rank-, order-, tensor where $r=O…