Mendizábal, Valentina Zelaya Boullé, Marc Rossi, Fabrice
G-Enum histograms are a new fast and fully automated method for irregular histogram construction. By framing histogram construction as a density estimation problem and its automation as a model selection task, these histograms leverage the Minimum Description Length principle (MDL) to derive two different model selection criteria. Several proven th...
Fouillen, Erwan Boyer, Claire Sangnier, Maxime
Gradient boosting is a prediction method that iteratively combines weak learners to produce a complex and accurate model. From an optimization point of view, the learning procedure of gradient boosting mimics a gradient descent on a functional variable. This paper proposes to build upon the proximal point algorithm when the empirical risk to minimi...
Sebia, Hana Guyet, Thomas Audureau, Etienne
La décomposition tensorielle a récemment fait l'objet d'une attention croissante dans la communauté de l'apprentissage automatique en raison de sa polyvalence dans le traitement des données à grande échelle. Cependant, cette tâche devient plus difficile lorsqu'il s'agit de prendre en comte la dimension temporelle. Dans cet article, nous étendons la...
Richa, Majdi Prévotet, Jean-Christophe Dardaillon, Mickaël Mroué, Mohamad Abed Ellatif, Samhat
Nowadays, power optimization has become a major interest for most digital hardware designers. Some, traditionally, might stick to offline power estimation especially in early design phases; some others resort to the modern and very promising runtime power management. Therefore, the Online Power Monitoring (OPM) is considered as an important feature...
Singh, Premjeet Sahidullah, Md Saha, Goutam
This work explores the use of constant-Q transform based modulation spectral features (CQT-MSF) for speech emotion recognition (SER). The human perception and analysis of sound comprise of two important cognitive parts: early auditory analysis and cortex-based processing. The early auditory analysis considers spectrogram-based representation wherea...
Pauwels, Edouard
Minibatch decomposition methods for empirical risk minimization are commonly analysed in a stochastic approximation setting, also known as sampling with replacement. On the other hands modern implementations of such techniques are incremental: they rely on sampling without replacement, for which available analysis are much scarcer. We provide conve...
Guo, Wen Du, Yuming Shen, Xi Lepetit, Vincent Alameda-Pineda, Xavier Moreno-Noguer, Francesc
This paper tackles the problem of human motion prediction, consisting in forecasting future body poses from historically observed sequences. State-of-the-art approaches provide good results, however, they rely on deep learning architectures of arbitrary complexity, such as Recurrent Neural Networks(RNN), Transformers or Graph Convolutional Networks...
Bergner, Yoav Halpin, Peter Vie, Jill-Jênn
Published in
Psychometrika
This paper presents a machine learning approach to multidimensional item response theory (MIRT), a class of latent factor models that can be used to model and predict student performance from observed assessment data. Inspired by collaborative filtering, we define a general class of models that includes many MIRT models. We discuss the use of penal...
Sajadmanesh, Sina Shamsabadi, Ali Shahin Bellet, Aurélien Gatica-Perez, Daniel
In this paper, we study the problem of learning Graph Neural Networks (GNNs) with Differential Privacy (DP). We propose a novel differentially private GNN based on Aggregation Perturbation (GAP), which adds stochastic noise to the GNN's aggregation function to statistically obfuscate the presence of a single edge (edge-level privacy) or a single no...
Cífka, Ondřej Liutkus, Antoine
The increasingly widespread adoption of large language models has highlighted the need for improving their explainability. We present context length probing, a novel explanation technique for causal language models, based on tracking the predictions of a model as a function of the length of available context, and allowing to assign differential imp...