Follow
Alexander Bastounis
Title
Cited by
Cited by
Year
On the absence of uniform recovery in many real-world applications of compressed sensing and the restricted isometry property and nullspace property in levels
A Bastounis, AC Hansen
SIAM Journal on Imaging Sciences 10 (1), 335-371, 2017
54*2017
The mathematics of adversarial attacks in AI--Why deep learning is unstable despite the existence of stable neural networks
A Bastounis, AC Hansen, V Vlačić
arXiv preprint arXiv:2109.06098, 2021
322021
The extended Smale's 9th problem--On computational barriers and paradoxes in estimation, regularisation, computer-assisted proofs and learning
A Bastounis, AC Hansen, V Vlačić
arXiv preprint arXiv:2110.15734, 2021
27*2021
The feasibility and inevitability of stealth attacks
IY Tyukin, DJ Higham, A Bastounis, E Woldegeorgis, AN Gorban
arXiv preprint arXiv:2106.13997, 2021
132021
On fundamentals of models and sampling in compressed sensing
B Roman, A Bastounis, B Adcock, AC Hansen
Preprint, 2015
112015
On random and deterministic compressed sensing and the restricted isometry property in levels
A Bastounis, AC Hansen
2015 International Conference on Sampling Theory and Applications (SampTA …, 2015
92015
From global to local: Getting more from compressed sensing
A Bastounis, B Adcock, AC Hansen
SIAM News 50 (8), 1-4, 2017
82017
The extended Smale’s 9th problem-On computational barriers and paradoxes in estimation, regularisation, learning and computer-assisted proofs
A Bastounis, AC Hansen, V Vlacic
arXiv preprint arxiv:2110.15734, 2021
52021
When can you trust feature selection?--II: On the effects of random data on condition in statistics and optimisation
A Bastounis, F Cucker, AC Hansen
arXiv preprint arXiv:2312.11429, 2023
12023
When can you trust feature selection?--I: A condition-based analysis of LASSO and generalised hardness of approximation
A Bastounis, F Cucker, AC Hansen
arXiv preprint arXiv:2312.11425, 2023
12023
The boundaries of verifiable accuracy, robustness, and generalisation in deep learning
A Bastounis, AN Gorban, AC Hansen, DJ Higham, D Prokhorov, O Sutton, ...
International Conference on Artificial Neural Networks, 530-541, 2023
12023
How adversarial attacks can disrupt seemingly stable accurate classifiers
OJ Sutton, Q Zhou, IY Tyukin, AN Gorban, A Bastounis, DJ Higham
arXiv preprint arXiv:2309.03665, 2023
2023
On fundamental computational barriers in the mathematics of information
AJ Bastounis
2018
The system can't perform the operation now. Try again later.
Articles 1–13