Search Results for author:
Found 5 papers, 0 papers with code
When can you trust feature selection? -- I: A condition-based analysis of LASSO and generalised hardness of approximation
However, we define a LASSO condition number and design an efficient algorithm for computing these support sets provided the input data is well-posed (has finite condition number) in time polynomial in the dimensions and logarithm of the condition number.
The Boundaries of Verifiable Accuracy, Robustness, and Generalisation in Deep Learning
We consider classical distribution-agnostic framework and algorithms minimising empirical risks and potentially subjected to some weights regularisation.
How adversarial attacks can disrupt seemingly stable accurate classifiers
We introduce a simple generic and generalisable framework for which key behaviours observed in practical systems arise with high probability -- notably the simultaneous susceptibility of the (otherwise accurate) model to easily constructed adversarial attacks, and robustness to random perturbations of the input data.
The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks
Our paper addresses why there has been no solution to the problem, as we prove the following mathematical paradox: any training procedure based on training neural networks for classification problems with a fixed architecture will yield neural networks that are either inaccurate or unstable (if accurate) -- despite the provable existence of both accurate and stable neural networks for the same classification problems.
The Feasibility and Inevitability of Stealth Attacks
Such a stealth attack could be conducted by a mischievous, corrupt or disgruntled member of a software development team.
