We prove identifiability of a broad class of deep latent variable models that (a) have
universal approximation capabilities and (b) are the decoders of variational autoencoders …

Understanding the geometric properties of gradient descent dynamics is a key ingredient in
deciphering the recent success of very large machine learning models. A striking …

The possibility for one to recover the parameters—weights and biases—of a neural network
thanks to the knowledge of its function on a subset of the input space can be, depending on …

Given a training set, a loss function, and a neural network architecture, it is often taken for
granted that optimal network parameters exist, and a common practice is to apply available …

Is a sample rich enough to determine, at least locally, the parameters of a neural network?
To answer this question, we introduce a new local parameterization of a given deep ReLU …

This work introduces the first toolkit around path-norms that is fully able to encompass
general DAG ReLU networks with biases, skip connections and any operation based on the …

Understanding the learning process of artificial neural networks requires clarifying the
structure of the parameter space within which learning takes place. A neural network …

Building segmentation has extensive research value and application prospects in high-
resolution remote sensing image (HRSI) processing. However, complex architectural …

In this paper, we investigate the complexity of feed-forward neural networks by examining
the concept of functional equivalence, which suggests that different network …

It is well known that neural networks with many more parameters than training examples do
not overfit. Implicit regularization phenomena, which are still not well understood, occur …