90 citations · 142 across the 7 of their papers we have counts for
7 papers
BINAS: Bilinear Interpretable Neural Architecture Search
Niv Nayman, Yonathan Aflalo, Asaf Noy +2
Practical use of neural networks often involves requirements on latency, energy and memory among others. A popular approach to find networks under such requirements is through cons…
HardCoRe-NAS: Hard Constrained diffeRentiable Neural Architecture Search
Niv Nayman, Yonathan Aflalo, Asaf Noy +1
Realistic use of neural networks often requires adhering to multiple constraints on latency, energy and memory among others. A popular approach to find fitting networks is through…
A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks
Asaf Noy, Yi Xu, Yonathan Aflalo +2
Deep neural networks' remarkable ability to correctly fit training data when optimized by gradient-based algorithms is yet to be fully understood. Recent theoretical results explai…
Knapsack Pruning with Inner Distillation
Yonathan Aflalo, Asaf Noy, Ming Lin +2
Neural network pruning reduces the computational cost of an over-parameterized network to improve its efficiency. Popular methods vary from -norm sparsification to Neural A…
On the optimality of shape and data representation in the spectral domain
Yonathan Aflalo, Haim Brezis, Ron Kimmel
A proof of the optimality of the eigenfunctions of the Laplace-Beltrami operator (LBO) in representing smooth functions on surfaces is provided and adapted to the field of applied…
Graph matching: relax or not?
Yonathan Aflalo, Alex Bronstein, Ron Kimmel
We consider the problem of exact and inexact matching of weighted undirected graphs, in which a bijective correspondence is sought to minimize a quadratic weight disagreement. This…
Spectral Generalized Multi-Dimensional Scaling
Yonathan Aflalo, Anastasia Dubrovina, Ron Kimmel
Multidimensional scaling (MDS) is a family of methods that embed a given set of points into a simple, usually flat, domain. The points are assumed to be sampled from some metric sp…