3 citations · 3 across the 4 of their papers we have counts for
6 papers
Screening strongly correlated materials in solid oxide cells with quantum simulation
Ouns El Harzli, Jelle Bor, Linde Wester +9
We develop an end-to-end framework for assessing a quantum-computing application in industrial materials science: the screening of strongly correlated oxygen-electrode materials fo…
Autoregressive Differentiable Method for Integer Programming
Ouns El Harzli, Yudong Cao
We introduce an autoregressive differentiable method to solve 0-1 integer programs. We fix an arbitrary order of the binary variables and we train a transformer to predict the next…
Sufficient Conditions for Stability of Minimum-Norm Interpolating Deep ReLU Networks
Ouns El Harzli, Yoonsoo Nam, Ilja Kuzborskij +2
Algorithmic stability is a classical framework for analyzing the generalization error of learning algorithms. It predicts that an algorithm has small generalization error if it is…
Supervised sparse auto-encoders for interpretable and compositional representations
Ouns El Harzli, Hugo Wallner, Yoonsoo Nam +1
Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the penalt…
From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural Networks
Ouns El Harzli, Bernardo Cuenca Grau, Artur d'Avila Garcez +2
Fibring of modal logics is a well-established formalism for combining countable families of modal logics into a single fibred language with common semantics, characterized by fibre…
Cardinality-Minimal Explanations for Monotonic Neural Networks
Ouns El Harzli, Bernardo Cuenca Grau, Ian Horrocks
In recent years, there has been increasing interest in explanation methods for neural model predictions that offer precise formal guarantees. These include abductive (respectively,…