11 citations · 34 across the 13 of their papers we have counts for
13 papers
ECUAS: A family of metrics for principled evaluation of uncertainty-augmented systems
Lautaro Estienne, Erik Ernst, Matías Vera +2
In high-stakes automated decision-making, access to predictive uncertainty is essential for enabling users -- human or downstream systems -- to accept or reject predictions based o…
Using Spatial Diffusions for Optoacoustic Tomography Image Reconstruction
Martin G. Gonzalez, Matias Vera, Leonardo Rey Vega
Optoacoustic tomography image reconstruction has been a problem of interest in recent years. By exploiting the exceptional generative power of the recently proposed diffusion model…
On the Stability of a non-hyperbolic nonlinear map with non-bounded set of non-isolated fixed points with applications to Machine Learning
Roberta Hansen, Matias Vera, Lautaro Estienne +2
This paper deals with the convergence analysis of the SUCPA (Semi Unsupervised Calibration through Prior Adaptation) algorithm, defined from a first-order non-linear difference equ…
Unsupervised Calibration through Prior Adaptation for Text Classification using Large Language Models
Lautaro Estienne, Luciana Ferrer, Matías Vera +1
A wide variety of natural language tasks are currently being addressed with large-scale language models (LLMs). These models are usually trained with a very large amount of unsuper…
Invariant Representations in Deep Learning for Optoacoustic Imaging
Matias Vera, Martin G. Gonzalez, Leonardo Rey Vega
Image reconstruction in optoacoustic tomography (OAT) is a trending learning task highly dependent on measured physical magnitudes present at sensing time. The large number of diff…
Cross-domain Sentiment Classification in Spanish
Lautaro Estienne, Matias Vera, Leonardo Rey Vega
Sentiment Classification is a fundamental task in the field of Natural Language Processing, and has very important academic and commercial applications. It aims to automatically pr…
Combining band-frequency separation and deep neural networks for optoacoustic imaging
Martin G. Gonzalez, Matias Vera, Leonardo Rey Vega
In this paper we consider the problem of image reconstruction in optoacoustic tomography. In particular, we devise a deep neural architecture that can explicitly take into account…
PACMAN: PAC-style bounds accounting for the Mismatch between Accuracy and Negative log-loss
Matias Vera, Leonardo Rey Vega, Pablo Piantanida
The ultimate performance of machine learning algorithms for classification tasks is usually measured in terms of the empirical error probability (or accuracy) based on a testing da…
The Role of Mutual Information in Variational Classifiers
Matias Vera, Leonardo Rey Vega, Pablo Piantanida
Overfitting data is a well-known phenomenon related with the generation of a model that mimics too closely (or exactly) a particular instance of data, and may therefore fail to pre…
Understanding the Behaviour of the Empirical Cross-Entropy Beyond the Training Distribution
Matias Vera, Pablo Piantanida, Leonardo Rey Vega
Machine learning theory has mostly focused on generalization to samples from the same distribution as the training data. Whereas a better understanding of generalization beyond the…
The Role of Information Complexity and Randomization in Representation Learning
Matías Vera, Pablo Piantanida, Leonardo Rey Vega
A grand challenge in representation learning is to learn the different explanatory factors of variation behind the high dimen- sional data. Encoder models are often determined to o…
Compression-Based Regularization with an Application to Multi-Task Learning
Matías Vera, Leonardo Rey Vega, Pablo Piantanida
This paper investigates, from information theoretic grounds, a learning problem based on the principle that any regularity in a given dataset can be exploited to extract compact fe…
Collaborative Information Bottleneck
Matías Vera, Leonardo Rey Vega, Pablo Piantanida
This paper investigates a multi-terminal source coding problem under a logarithmic loss fidelity which does not necessarily lead to an additive distortion measure. The problem is m…