Kissing to find a match: efficient low-rank permutation representation

H Dröge, Z Lähner, Y Bahat… - Advances in …, 2024 - proceedings.neurips.cc
Permutation matrices play a key role in matching and assignment problems across the
fields, especially in computer vision and robotics. However, memory for explicitly …

Symmetric Matrix Completion with ReLU Sampling

H Liu, P Wang, L Huang, Q Qu, L Balzano - arXiv preprint arXiv …, 2024 - arxiv.org
We study the problem of symmetric positive semi-definite low-rank matrix completion (MC)
with deterministic entry-dependent sampling. In particular, we consider rectified linear unit …

A Momentum Accelerated Algorithm for ReLU-based Nonlinear Matrix Decomposition

Q Wang, C Cui, D Han - arXiv preprint arXiv:2402.02442, 2024 - arxiv.org
Recently, there has been a growing interest in the exploration of Nonlinear Matrix
Decomposition (NMD) due to its close ties with neural networks. NMD aims to find a low …

Coordinate Descent Algorithm for Nonlinear Matrix Decomposition with the ReLU function

A Awari, H Nguyen, S Wertz… - 2024 32nd European …, 2024 - ieeexplore.ieee.org
Nonlinear Matrix Decompositions (NMD) solve the following problem: Given a matrix X, find
low-rank factors W and H such that X≈f(WH), where f is an element-wise nonlinear function …

On the confluence of machine learning and model-based energy minimization methods for computer vision

H Dröge - 2024 - dspace.ub.uni-siegen.de
Deep learning has achieved great success in the field of computer vision across a wide
range of applications. However, learning-based methods still have several limitations …

[PDF][PDF] LOW-RANK MATRIX FACTORIZATION: FROM LINEAR TO NONLINEAR MODELS

M PORCELLI, G SERAGHITI, N GILLIS - amslaurea.unibo.it
Il presente elaborato è la rielaborazione del lavoro condotto durante un tirocinio della durata
di tre mesi che ha avuto luogo presso la Facultè Polytechnique di Mons in Belgio. In …