17 citations · 78 across the 17 of their papers we have counts for
21 papers
Contrastive Linearized Laplace: Loss Geometry, Valid Repairs, and Reliable Cores
Francisco J. Sáez-Maldonado, Luis A. Ortega, Andrés R. Masegosa +1
While contrastive learning is widely used to learn deterministic representations, it does not inherently provide estimates of uncertainty. Post-hoc uncertainty estimation methods,…
Generalized Matheron Variational Implicit Processes
Luis A. Ortega, Andrés R. Masegosa, Thomas D. Nielsen
Implicit-process priors specify distributions over functions through sample-forward mechanisms such as Bayesian neural networks and stochastic simulators, but their function-space…
Sequence-Informed Geometric Evaluation of RNA 3D Structures
Andrea Zerio, Yighua Yao, Alessandro Micheli +5
Computational RNA structure pipelines generate many candidate conformations for the same sequence. Reliable evaluation therefore requires more than recognising plausible geometry,…
Flow-Transformed Implicit Processes for Function-Space Variational Inference
Luis A. Ortega, Andrés R. Masegosa, Thomas D. Nielsen
Implicit-process priors define distributions over functions through flexible generative mechanisms, making them attractive for Bayesian function-space modelling. However, performin…
UncertainGen: Uncertainty-Aware Representations of DNA Sequences for Metagenomic Binning
Abdulkadir Celikkanat, Andres R. Masegosa, Mads Albertsen +1
Metagenomic binning aims to cluster DNA fragments from mixed microbial samples into their respective genomes, a critical step for downstream analyses of microbial communities. Exis…
Deep Actor-Critics with Tight Risk Certificates
Bahareh Tasdighi, Manuel Haussmann, Yi-Shan Wu +2
Deep actor-critic algorithms have reached a level where they influence everyday life. They are a driving force behind continual improvement of large language models through user fe…
Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning
Abdulkadir Celikkanat, Andres R. Masegosa, Thomas D. Nielsen
Obtaining effective representations of DNA sequences is crucial for genome analysis. Metagenomic binning, for instance, relies on genome representations to cluster complex mixtures…
PAC-Bayes-Chernoff bounds for unbounded losses
Ioar Casado, Luis A. Ortega, Aritz Pérez +1
We introduce a new PAC-Bayes oracle bound for unbounded losses that extends Cramér-Chernoff bounds to the PAC-Bayesian setting. The proof technique relies on controlling the tails…
If there is no underfitting, there is no Cold Posterior Effect
Yijie Zhang, Yi-Shan Wu, Luis A. Ortega +1
The cold posterior effect (CPE) (Wenzel et al., 2020) in Bayesian deep learning shows that, for posteriors with a temperature , the resulting posterior predictive could have b…
PAC-Chernoff Bounds: Understanding Generalization in the Interpolation Regime
Andrés R. Masegosa, Luis A. Ortega
This paper introduces a distribution-dependent PAC-Chernoff bound that exhibits perfect tightness for interpolators, even within over-parameterized model classes. This bound, which…
From Anecdote to Evidence: The Relationship Between Personality and Need for Cognition of Developers
Daniel Russo, Andres R. Masegosa, Klaas-Jan Stol
There is considerable anecdotal evidence suggesting that software engineers enjoy engaging in solving puzzles and other cognitive efforts. A tendency to engage in and enjoy effortf…
Diversity and Generalization in Neural Network Ensembles
Luis A. Ortega, Rafael Cabañas, Andrés R. Masegosa
Ensembles are widely used in machine learning and, usually, provide state-of-the-art performance in many prediction tasks. From the very beginning, the diversity of an ensemble has…
Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
Yi-Shan Wu, Andrés R. Masegosa, Stephan S. Lorenzen +2
We present a new second-order oracle bound for the expected risk of a weighted majority vote. The bound is based on a novel parametric form of the Chebyshev- Cantelli inequality (a…
Second Order PAC-Bayesian Bounds for the Weighted Majority Vote
Andrés R. Masegosa, Stephan S. Lorenzen, Christian Igel +1
We present a novel analysis of the expected risk of weighted majority vote in multiclass classification. The analysis takes correlation of predictions by ensemble members into acco…
Learning under Model Misspecification: Applications to Variational and Ensemble methods
Andres R. Masegosa
Virtually any model we use in machine learning to make predictions does not perfectly represent reality. So, most of the learning happens under model misspecification. In this work…
Probabilistic Models with Deep Neural Networks
Andrés R. Masegosa, Rafael Cabañas, Helge Langseth +2
Recent advances in statistical inference have significantly expanded the toolbox of probabilistic modeling. Historically, probabilistic modeling has been constrained to (i) very re…
InferPy: Probabilistic Modeling with Deep Neural Networks Made Easy
Javier Cózar, Rafael Cabañas, Antonio Salmerón +1
InferPy is a Python package for probabilistic modeling with deep neural networks. It defines a user-friendly API that trades-off model complexity with ease of use, unlike other lib…
Bayesian Models of Data Streams with Hierarchical Power Priors
Andres Masegosa, Thomas D. Nielsen, Helge Langseth +3
Making inferences from data streams is a pervasive problem in many modern data analysis applications. But it requires to address the problem of continuous model updating and adapt…
AMIDST: a Java Toolbox for Scalable Probabilistic Machine Learning
Andrés R. Masegosa, Ana M. Martínez, Darío Ramos-López +5
The AMIDST Toolbox is a software for scalable probabilistic machine learning with a spe- cial focus on (massive) streaming data. The toolbox supports a flexible modeling language b…
Probabilistic Graphical Models on Multi-Core CPUs using Java 8
Andres R. Masegosa, Ana M. Martinez, Hanen Borchani
In this paper, we discuss software design issues related to the development of parallel computational intelligence algorithms on multi-core CPUs, using the new Java 8 functional pr…
Stochastic Discriminative EM
Andres R. Masegosa
Stochastic discriminative EM (sdEM) is an online-EM-type algorithm for discriminative training of probabilistic generative models belonging to the exponential family. In this work,…