Alexander Bastounis
Orcid: 0000-0002-2867-4635
  According to our database1,
  Alexander Bastounis
  authored at least 9 papers
  between 2014 and 2024.
  
  
Collaborative distances:
Collaborative distances:
Timeline
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
  2024
    Neural Networks, 2024
    
  
On the consistent reasoning paradox of intelligence and optimal trust in AI: The power of 'I don't know'.
    
  
    CoRR, 2024
    
  
    Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024
    
  
  2023
When can you trust feature selection? - I: A condition-based analysis of LASSO and generalised hardness of approximation.
    
  
    CoRR, 2023
    
  
The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning.
    
  
    Proceedings of the Artificial Neural Networks and Machine Learning, 2023
    
  
  2021
The mathematics of adversarial attacks in AI - Why deep learning is unstable despite the existence of stable neural networks.
    
  
    CoRR, 2021
    
  
  2017
On the Absence of Uniform Recovery in Many Real-World Applications of Compressed Sensing and the Restricted Isometry Property and Nullspace Property in Levels.
    
  
    SIAM J. Imaging Sci., 2017
    
  
  2014
On the absence of the RIP in real-world applications of compressed sensing and the RIP in levels.
    
  
    CoRR, 2014