no code implementations • 12 Apr 2021 • Victor Berger, Michele Sebag
The paper focuses on the a posteriori tuning of a generative model in order to favor the generation of good instances in the sense of some external differentiable criterion.
no code implementations • 1 Jan 2021 • Victor Berger, Michele Sebag
The paper focuses on the a posteriori tuning of a generative model in order to favor the generation of good instances in the sense of some external differentiable criterion.
no code implementations • 12 Oct 2020 • Adrian Alan Pol, Victor Berger, Gianluca Cerminara, Cecile Germain, Maurizio Pierini
Exploiting the rapid advances in probabilistic inference, in particular variational Bayes and variational autoencoders (VAEs), for anomaly detection (AD) tasks remains an open research question.
no code implementations • 4 Mar 2020 • Michele Sebag, Victor Berger, Michèle Sebag
We claim that a source of severe failures for Variational Auto-Encoders is the choice of the distribution class used for the observation model. A first theoretical and experimental contribution of the paper is to establish that even in the large sample limit with arbitrarily powerful neural architectures and latent space, the VAE failsif the sharpness of the distribution class does not match the scale of the data. Our second claim is that the distribution sharpness must preferably be learned by the VAE (as opposed to, fixed and optimized offline): Autonomously adjusting this sharpness allows the VAE to dynamically control the trade-off between the optimization of the reconstruction loss and the latent compression.
no code implementations • 22 Jan 2020 • Victor Berger, Michèle Sebag
This paper focuses on their control.
no code implementations • 3 Jul 2018 • Victor Berger, Michèle Sebag
Generative Adversarial Networks (Goodfellow et al., 2014), a major breakthrough in the field of generative modeling, learn a discriminator to estimate some distance between the target and the candidate distributions.