Machine Learning
Browse by
Recent Submissions

DoubleWeighting for Covariate Shift Adaptation
(202307)Supervised learning is often affected by a covariate shift in which the marginal distributions of instances (covariates $x$) of training and testing samples $p_\text{tr}(x)$ and $p_\text{te}(x)$ are different but the label ... 
On the Use of Second Order Neighbors to Escape from Local Optima
(20230712)Designing efficient local search based algorithms requires to consider the specific properties of the problems. We introduce a simple and effi cient strategy, the Extended Reach, that escapes from local optima ob tained ... 
MinimumFuel LowThrust Trajectory Optimization Via a Direct Adaptive Evolutionary Approach
(20231128)Space missions with lowthrust propulsion systems are of appreciable interest to space agencies because of their practicality due to higher specific impulses. This research proposes a technique to the solution of minimumfuel ... 
Adaptive Estimation of Distribution Algorithms for LowThrust Trajectory Optimization
(20230802)A direct adaptive scheme is presented as an alternative approach for minimumfuel lowthrust trajectory design in noncoplanar orbit transfers, utilizing fitness landscape analysis (FLA). Spacecraft dynamics is modeled ... 
Robust Estimation of Distribution Algorithms via Fitness Landscape Analysis for Optimal LowThrust Orbital Maneuvers
(202309)One particular kind of evolutionary algorithms known as Estimation of Distribution Algorithms (EDAs) has gained the attention of the aerospace industry for its ability to solve nonlinear and complicated problems, particularly ... 
Learning a logistic regression with the help of unknown features at prediction stage
(2023)The use of features available at training time, but not at prediction time, as additional information for training models is known as learning using privileged information paradigm. In this paper, the handling of ... 
Female Models in AI and the Fight Against COVID19
(20221101)Gender imbalance has persisted over time and is well documented in science, technology, engineering and mathematics (STEM) and singularly in artificial intelligence (AI). In this article we emphasize the importance of ... 
Efficient Learning of Minimax Risk Classifiers in High Dimensions
(20230801)Highdimensional data is common in multiple areas, such as health care and genomics, where the number of features can be tens of thousands. In such scenarios, the large number of features often leads to inefficient ... 
LASSO for streaming data with adaptative filtering
(2022)Streaming data is ubiquitous in modern machine learning, and so the development of scalable algorithms to analyze this sort of information is a topic of current interest. On the other hand, the problem of l1penalized ... 
Are the statistical tests the best way to deal with the biomarker selection problem?
(2022)Statistical tests are a powerful set of tools when applied correctly, but unfortunately the extended misuse of them has caused great concern. Among many other applications, they are used in the detection of biomarkers so ... 
On the use of the descriptive variable for enhancing the aggregation of crowdsourced labels
(2022)The use of crowdsourcing for annotating data has become a popular and cheap alternative to expert labelling. As a consequence, an aggregation task is required to combine the different labels provided and agree on a single ... 
On the relative value of weak information of supervision for learning generative models: An empirical study
(2022)Weakly supervised learning is aimed to learn predictive models from partially supervised data, an easytocollect alternative to the costly standard full supervision. During the last decade, the research community has ... 
Comparing Two Samples Through Stochastic Dominance: A Graphical Approach
(2022)Nondeterministic measurements are common in realworld scenarios: the performance of a stochastic optimization algorithm or the total reward of a reinforcement learning agent in a chaotic environment are just two examples ... 
Nonparametric discretization for probabilistic labeled data
(2022)Probabilistic label learning is a challenging task that arises from recent realworld problems within the weakly supervised classification framework. In this task algorithms have to deal with datasets where each instance ... 
Dirichlet process mixture models for nonstationary data streams
(2022)In recent years, we have seen a handful of work on inference algorithms over nonstationary data streams. Given their flexibility, Bayesian nonparametric models are a good candidate for these scenarios. However, reliable ... 
Machine learning from crowds using candidate setbased labelling
(2022)Crowdsourcing is a popular cheap alternative in machine learning for gathering information from a set of annotators. Learning from crowdlabelled data involves dealing with its inherent uncertainty and inconsistencies. In ... 
New Knowledge about the Elementary Landscape Decomposition for Solving the Quadratic Assignment Problem
(20230715)Previous works have shown that studying the characteristics of the Quadratic Assignment Problem (QAP) is a crucial step in gaining knowledge that can be used to design tailored metaheuristic algorithms. One way to analyze ... 
Minimax Risk Classifiers with 01 Loss
(20230701)Supervised classification techniques use training samples to learn a classification rule with small expected 0 1 loss (error probability). Conventional methods enable tractable learning and provide outofsample ... 
Transitions from P to NPhardness: the case of the Linear Ordering Problem
(2022)In this paper we evaluate how constructive heuristics degrade when a problem transits from P to NPhard. This is done by means of the linear ordering problem. More specifically, for this problem we prove that the objective ...