Search Results for author: Vincent Le Guen

Found 6 papers, 5 papers with code

Deep Time Series Forecasting with Shape and Temporal Criteria

1 code implementation9 Apr 2021 Vincent Le Guen, Nicolas Thome

This paper addresses the problem of multi-step time series forecasting for non-stationary signals that can present sudden changes.

Dynamic Time Warping Time Series +1

Probabilistic Time Series Forecasting with Shape and Temporal Diversity

1 code implementation NeurIPS 2020 Vincent Le Guen, Nicolas Thome

We introduce the STRIPE model for representing structured diversity based on shape and time features, ensuring both probable predictions while being sharp and accurate.

Point Processes Probabilistic Time Series Forecasting +1

Probabilistic Time Series Forecasting with Structured Shape and Temporal Diversity

1 code implementation14 Oct 2020 Vincent Le Guen, Nicolas Thome

We introduce the STRIPE model for representing structured diversity based on shape and time features, ensuring both probable predictions while being sharp and accurate.

Point Processes Probabilistic Time Series Forecasting +1

Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting

no code implementations ICLR 2021 Vincent Le Guen, Yuan Yin, Jérémie Dona, Ibrahim Ayed, Emmanuel de Bézenac, Nicolas Thome, Patrick Gallinari

Forecasting complex dynamical phenomena in settings where only partial knowledge of their dynamics is available is a prevalent problem across various scientific fields.

Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction

1 code implementation CVPR 2020 Vincent Le Guen, Nicolas Thome

Leveraging physical knowledge described by partial differential equations (PDEs) is an appealing way to improve unsupervised video prediction methods.

Video Prediction

Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models

2 code implementations NeurIPS 2019 Vincent Le Guen, Nicolas Thome

We introduce a differentiable loss function suitable for training deep neural nets, and provide a custom back-prop implementation for speeding up optimization.

Dynamic Time Warping Time Series +2

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