1 code implementation • 15 Feb 2024 • Romain Ilbert, Ambroise Odonnat, Vasilii Feofanov, Aladin Virmaux, Giuseppe Paolo, Themis Palpanas, Ievgen Redko
Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting.
no code implementations • 20 Oct 2023 • Vasilii Feofanov, Malik Tiomoko, Aladin Virmaux
As an application, we derive a hyperparameter selection policy that finds the best balance between the supervised and the unsupervised terms of our learning criterion.
no code implementations • 6 Oct 2021 • Aladin Virmaux, Illyyne Saffar, Jianfeng Zhang, Balázs Kégl
Knothe-Rosenblatt Domain Adaptation (KRDA) is based on the Knothe-Rosenblatt transport: we exploit autoregressive density estimation algorithms to accurately model the different sources by an autoregressive model using a mixture of Gaussians.
no code implementations • 29 Sep 2021 • Paul Daoudi, Merwan Barlier, Ludovic Dos Santos, Aladin Virmaux
We hence introduce Density Conservative Q-Learning (D-CQL), a batch-RL algorithm with strong theoretical guarantees that carefully penalizes the value function based on the amount of information collected in the state-action space.
1 code implementation • 8 Mar 2021 • George Dasoulas, Kevin Scaman, Aladin Virmaux
To address this issue, we derive a theoretical analysis of the Lipschitz continuity of attention modules and introduce LipschitzNorm, a simple and parameter-free normalization for self-attention mechanisms that enforces the model to be Lipschitz continuous.
no code implementations • 17 Feb 2021 • George Dasoulas, Giannis Nikolentzos, Kevin Scaman, Aladin Virmaux, Michalis Vazirgiannis
Machine learning on graph-structured data has attracted high research interest due to the emergence of Graph Neural Networks (GNNs).
no code implementations • 17 Feb 2021 • Avery Ma, Aladin Virmaux, Kevin Scaman, Juwei Lu
Do all adversarial examples have the same consequences?
no code implementations • 1 Jan 2021 • Jianfeng Zhang, Illyyne Saffar, Aladin Virmaux, Balázs Kégl
We propose an unsupervised domain adaptation approach based on generative models.
no code implementations • 1 Mar 2020 • George Dasoulas, Giannis Nikolentzos, Kevin Scaman, Aladin Virmaux, Michalis Vazirgiannis
Moreover, on graph classification tasks, we suggest the utilization of the generated structural embeddings for the transformation of an attributed graph structure into a set of augmented node attributes.
no code implementations • 12 Dec 2019 • George Dasoulas, Ludovic Dos Santos, Kevin Scaman, Aladin Virmaux
In this paper, we show that a simple coloring scheme can improve, both theoretically and empirically, the expressive power of Message Passing Neural Networks(MPNNs).
1 code implementation • NeurIPS 2018 • Kevin Scaman, Aladin Virmaux
First, we show that, even for two layer neural networks, the exact computation of this quantity is NP-hard and state-of-art methods may significantly overestimate it.