Journée Statistique et Informatique pour la Science des Données à Paris Saclay

Résumés

1. Supervised Learning with Missing Values

Gaël Varoquaux (INRIA Parietal)

2/5/21, 10:30 AM

Some data come with missing values. For instance, a survey’s participant may ignore some questions. There is an abundant statistical literature on this topic, establishing for instance how to fit model without biases due to the missingness, and imputation strategies to provide practical solutions to the analyst. In machine learning, to build models that minimize a prediction risk, most work...

2. Analysis of Gradient Descent on Wide Two-Layer Neural Networks

Lenaïc Chizat (LMO)

2/5/21, 11:20 AM

Artificial neural networks are a class of "prediction" functions parameterized by a large number of parameters -- called weights -- that are used in various machine learning tasks (classification, regression, etc). Given a learning task, the weights are adjusted via a gradient-based algorithm so that the corresponding predictor achieves a good performance on a given training set. In this talk,...

4. Deep Unfolding of a Proximal Interior Point Method for Image Restoration

Emilie Chouzenoux (CVN)

2/5/21, 12:00 PM

Variational methods have started to be widely applied to ill-posed inverse problems since they have the ability to embed prior knowledge about the solution. However, the level of performance of these methods significantly depends on a set of parameters, which can be estimated through computationally expensive and time-consuming processes. In contrast, deep learning offers very generic and...

3. Maximum Entropy Distributions for Image Synthesis under Statistical Constraints

Agnès Desolneux (Centre Borelli)

2/5/21, 2:00 PM

The question of texture synthesis in image processing is a very challenging problem that can be stated as followed: given an exemplar image, sample a new image that has the same statistical features (empirical mean, empirical covariance, filter responses, neural network responses, etc.). Exponential models then naturally arise as distributions satisfying these constraints in expectation while...

5. Input Similarity from the Neural Network Perspective

Guillaume Charpiat (LRI)

2/5/21, 2:50 PM

Given a trained neural network, we aim at understanding how similar it considers any two samples. For this, we express a proper definition of similarity from the neural network perspective (i.e. we quantify how undissociable two inputs A and B are), by taking a machine learning viewpoint: how much a parameter variation designed to change the output for A would impact the output for B as...

6. Deep Neural Network for Audio and Music Transformations

Gaël Richard (Télécom Paris)

2/5/21, 3:30 PM

We will first discuss how deep learning techniques can be used for audio signals. To that aim, we will recall some of the important characteristics of an audio signal and review some of the main deep learning architectures and concepts used in audio signal analysis. We will then illustrate some of these concepts in more details with two applications, namely informed singing voice source...