arXiv subjects

Yann Guermeur

Publications and source records attributed to Yann Guermeur.

6 recordsLinked to original sources

arXiv2022

Generalization Bounds for Inductive Matrix Completion in Low-noise Settings

We study inductive matrix completion (matrix completion with side information) under an i.i.d. subgaussian noise assumption at a low noise regime, with uniform sampling of the entries. We obtain for the first time generalization bounds with the following three properties: (1) they scale like the standard deviation of the noise and in particular approach zero in the exact recovery case; (2) even in the presence of noise, they converge to zero when the sample size approaches infinity; and (3) for a fixed dimension of the side information, they only have a logarithmic dependence on the size of the matrix. Differently from many works in approximate recovery, we present results both for bounded Lipschitz losses and for the absolute loss, with the latter relying on Talagrand-type inequalities. The proofs create a bridge between two approaches to the theoretical analysis of matrix completion, since they consist in a combination of techniques from both the exact recovery literature and the approximate recovery literature.

cs.LG↗

arXiv2020

Combinatorial and Structural Results for gamma-Psi-dimensions

This article deals with the generalization performance of margin multi-category classifiers, when minimal learnability hypotheses are made. In that context, the derivation of a guaranteed risk is based on the handling of capacity measures belonging to three main families: Rademacher/Gaussian complexities, metric entropies and scale-sensitive combinatorial dimensions. The scale-sensitive combinatorial dimensions dedicated to the classifiers of this kind are the gamma-Psi-dimensions. We introduce the combinatorial and structural results needed to involve them in the derivation of guaranteed risks and establish the corresponding upper bounds on the metric entropies and the Rademacher complexity. Two major conclusions can be drawn: 1. the gamma-Psi-dimensions always bring an improvement compared to the use of the fat-shattering dimension of the class of margin functions; 2. thanks to their capacity to take into account basic features of the classifier, they represent a promising alternative to performing the transition from the multi-class case to the binary one with covering numbers.

cs.LG↗

arXiv2018

Rademacher Complexity and Generalization Performance of Multi-category Margin Classifiers

One of the main open problems in the theory of multi-category margin classification is the form of the optimal dependency of a guaranteed risk on the number C of categories, the sample size m and the margin parameter gamma. From a practical point of view, the theoretical analysis of generalization performance contributes to the development of new learning algorithms. In this paper, we focus only on the theoretical aspect of the question posed. More precisely, under minimal learnability assumptions, we derive a new risk bound for multi-category margin classifiers. We improve the dependency on C over the state of the art when the margin loss function considered satisfies the Lipschitz condition. We start with the basic supremum inequality that involves a Rademacher complexity as a capacity measure. This capacity measure is then linked to the metric entropy through the chaining method. In this context, our improvement is based on the introduction of a new combinatorial metric entropy bound.

math.ST↗

arXiv2016

L p -norm Sauer-Shelah Lemma for Margin Multi-category Classifiers

In the framework of agnostic learning, one of the main open problems of the theory of multi-category pattern classification is the characterization of the way the complexity varies with the number C of categories. More precisely, if the classifier is characterized only through minimal learnability hypotheses, then the optimal dependency on C that an upper bound on the probability of error should exhibit is unknown. We consider margin classifiers. They are based on classes of vector-valued functions with one component function per category, and the classes of component functions are uniform Glivenko-Cantelli classes. For these classifiers, an L p-norm Sauer-Shelah lemma is established. It is then used to derive guaranteed risks in the L $\infty$ and L 2-norms. These bounds improve over the state-of-the-art ones with respect to their dependency on C, which is sublinear.

math.ST↗

arXiv2008

A Quadratic Loss Multi-Class SVM

Using a support vector machine requires to set two types of hyperparameters: the soft margin parameter C and the parameters of the kernel. To perform this model selection task, the method of choice is cross-validation. Its leave-one-out variant is known to produce an estimator of the generalization error which is almost unbiased. Its major drawback rests in its time requirement. To overcome this difficulty, several upper bounds on the leave-one-out error of the pattern recognition SVM have been derived. Among those bounds, the most popular one is probably the radius-margin bound. It applies to the hard margin pattern recognition SVM, and by extension to the 2-norm SVM. In this report, we introduce a quadratic loss M-SVM, the M-SVM^2, as a direct extension of the 2-norm SVM to the multi-class case. For this machine, a generalized radius-margin bound is then established.

cs.LG↗

arXiv2007

Scale-sensitive Psi-dimensions: the Capacity Measures for Classifiers Taking Values in R^Q

Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such "VC dimensions" exist for models taking values in {0, 1}, {1,..., Q} and R. We introduce the generalizations appropriate for the missing case, the one of models with values in R^Q. This provides us with a new guaranteed risk for M-SVMs which appears superior to the existing one.

cs.LG↗