arXiv subjects

Alessio Benavoli

Publications and source records attributed to Alessio Benavoli.

40 records · Page 3Linked to original sources

arXiv2016

State Space representation of non-stationary Gaussian Processes

The state space (SS) representation of Gaussian processes (GP) has recently gained a lot of interest. The main reason is that it allows to compute GPs based inferences in O(n), where $n$ is the number of observations. This implementation makes GPs suitable for Big Data. For this reason, it is important to provide a SS representation of the most important kernels used in machine learning. The aim of this paper is to show how to exploit the transient behaviour of SS models to map non-stationary kernels to SS models.

cs.LG↗

arXiv2015

Should we really use post-hoc tests based on mean-ranks?

The statistical comparison of multiple algorithms over multiple data sets is fundamental in machine learning. This is typically carried out by the Friedman test. When the Friedman test rejects the null hypothesis, multiple comparisons are carried out to establish which are the significant differences among algorithms. The multiple comparisons are usually performed using the mean-ranks test. The aim of this technical note is to discuss the inconsistencies of the mean-ranks post-hoc test with the goal of discouraging its use in machine learning as well as in medicine, psychology, etc.. We show that the outcome of the mean-ranks test depends on the pool of algorithms originally included in the experiment. In other words, the outcome of the comparison between algorithms A and B depends also on the performance of the other algorithms included in the original experiment. This can lead to paradoxical situations. For instance the difference between A and B could be declared significant if the pool comprises algorithms C, D, E and not significant if the pool comprises algorithms F, G, H. To overcome these issues, we suggest instead to perform the multiple comparison using a test whose outcome only depends on the two algorithms being compared, such as the sign-test or the Wilcoxon signed-rank test.

cs.LG↗

arXiv2014

Imprecise Dirichlet Process with application to the hypothesis test on the probability that X< Y

The Dirichlet process (DP) is one of the most popular Bayesian nonparametric models. An open problem with the DP is how to choose its infinite dimensional parameter (base measure) in case of lack of prior information. In this work we present the Imprecise DP (IDP) -- a prior near-ignorance DP-based model that does not require any choice of this probability measure. It consists of a class of DPs obtained by letting the normalized base measure of the DP vary in the set of all probability measures. We discuss the tight connections of this approach with Bayesian robustness and in particular prior near-ignorance modeling via sets of probabilities. We use this model to perform a Bayesian hypothesis test on the probability P(X<Y). We study the theoretical properties of the IDP test (e.g., asymptotic consistency), and compare it with the frequentist Mann-Whitney-Wilcoxon rank test that is commonly employed as a test on P(X< Y). In particular we will show that our method is more robust, in the sense that it is able to isolate instances in which the aforementioned test is virtually guessing at random.

math.ST↗

arXiv2013

On the Complexity of Strong and Epistemic Credal Networks

Credal networks are graph-based statistical models whose parameters take values in a set, instead of being sharply specified as in traditional statistical models (e.g., Bayesian networks). The computational complexity of inferences on such models depends on the irrelevance/independence concept adopted. In this paper, we study inferential complexity under the concepts of epistemic irrelevance and strong independence. We show that inferences under strong independence are NP-hard even in trees with ternary variables. We prove that under epistemic irrelevance the polynomial time complexity of inferences in credal trees is not likely to extend to more general models (e.g. singly connected networks). These results clearly distinguish networks that admit efficient inferences and those where inferences are most likely hard, and settle several open questions regarding computational complexity.

cs.AI↗