5 papers
Expressivity of congruence-based architectures for DNNs on positive-definite matrices
Antonin Oswald, Estelle Massart
This work studies neural architectures for classifying symmetric positive-definite matrices, focusing on congruence-like layers, in which the input matrix is multiplied on the left…
The role of class encoding in neural collapse
Bastien Massion, Roy Makhlouf, Estelle Massart
Neural collapse is a structural property of the last-hidden-layer activations in neural network classification models, when trained beyond a zero classification error. In this work…
Efficient Techniques for Data Reconstruction, with Finite-Width Recovery Guarantees
Edward Tansley, Roy Makhlouf, Estelle Massart +1
Data reconstruction attacks on trained neural networks aim to recover the data on which the network has been trained and pose a significant threat to privacy, especially if the tra…
A Langevin sampler for quantum tomography
Tameem Adel, Abhishek Agarwal, Stéphane Chrétien +4
Quantum tomography involves obtaining a full classical description of a prepared quantum state from experimental results. We propose a Langevin sampler for quantum tomography, that…
On the Neural Feature Ansatz for Deep Neural Networks
Edward Tansley, Estelle Massart, Coralia Cartis
Understanding feature learning is an important open question in establishing a mathematical foundation for deep neural networks. The Neural Feature Ansatz (NFA) states that after t…