Search Results for author: Pierre Marion

Found 6 papers, 4 papers with code

Implicit regularization of deep residual networks towards neural ODEs

1 code implementation3 Sep 2023 Pierre Marion, Yu-Han Wu, Michael E. Sander, Gérard Biau

Our results are valid for a finite training time, and also as the training time tends to infinity provided that the network satisfies a Polyak-Lojasiewicz condition.

valid

Leveraging the two timescale regime to demonstrate convergence of neural networks

1 code implementation19 Apr 2023 Pierre Marion, Raphaël Berthier

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer.

Vocal Bursts Valence Prediction

Scaling ResNets in the Large-depth Regime

1 code implementation14 Jun 2022 Pierre Marion, Adeline Fermanian, Gérard Biau, Jean-Philippe Vert

initializations, the only non-trivial dynamics is for $\alpha_L = 1/\sqrt{L}$ (other choices lead either to explosion or to identity mapping).

Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs

no code implementations EMNLP 2021 Pierre Marion, Paweł Krzysztof Nowak, Francesco Piccinno

On CSQA, our approach increases the coverage from $80\%$ to $96. 2\%$, and the LF execution accuracy from $70. 6\%$ to $75. 6\%$, with respect to previous state-of-the-art results.

Conversational Question Answering Knowledge Graphs +1

Framing RNN as a kernel method: A neural ODE approach

1 code implementation NeurIPS 2021 Adeline Fermanian, Pierre Marion, Jean-Philippe Vert, Gérard Biau

Building on the interpretation of a recurrent neural network (RNN) as a continuous-time neural differential equation, we show, under appropriate conditions, that the solution of a RNN can be viewed as a linear function of a specific feature set of the input sequence, known as the signature.

Cannot find the paper you are looking for? You can Submit a new open access paper.