Régression non paramétrique | EPFL Graph Search

La régression non paramétrique est une forme d'analyse de la régression dans lequel le prédicteur, ou fonction d'estimation, ne prend pas de forme prédéterminée, mais est construit selon les informations provenant des données. La régression non paramétrique exige des tailles d'échantillons plus importantes que celles de la régression basée sur des modèles paramétriques parce que les données doivent fournir la structure du modèle ainsi que les estimations du modèle. Principe général On dispose de données numériques que l'on suppose corrélées. Une des grandeurs, notée y, est appelée variable expliquée. Les autres sont regroupées dans une variable dite explicative \mathbf{x} qui est un vecteur : :\mathbf{x} = (x_1, x_2,\ldots, x_m). On dispose de n situations (n jeux de valeurs) formant un nuage de points : :(\mathbf{x}^i, y^i) = (x_1^i, x_2^i, \ldots, x_m^i, y^i). La régression consiste à trouver u

Theory of Deep Learning: Neural Tangent Kernel and Beyond

Arthur Ulysse Jacot-Guillarmod

In the recent years, Deep Neural Networks (DNNs) have managed to succeed at tasks that previously appeared impossible, such as human-level object recognition, text synthesis, translation, playing games and many more. In spite of these major achievements, our understanding of these models, in particular of what happens during their training, remains very limited. This PhD started with the introduction of the Neural Tangent Kernel (NTK) to describe the evolution of the function represented by the network during training. In the infinite-width limit, i.e. when the number of neurons in the layers of the network grows to infinity, the NTK converges to a deterministic and time-independent limit, leading to a simple yet complete description of the dynamics of infinitely-wide DNNs. This allowed one to give the first general proof of convergence of DNNs to a global minimum, and yielded the first description of the limiting spectrum of the Hessian of the loss surface of DNNs throughout training.More importantly, the NTK plays a crucial role in describing the generalization abilities of DNNs, i.e. the performance of the trained network on unseen data. The NTK analysis uncovered a direct link between the function learned by infinitely wide DNNs and Kernel Ridge Regression predictors, whose generalization properties are studied in this thesis using tools of random matrix theory. Our analysis of KRR reveals the importance of the eigendecomposition of the NTK, which is affected by a number of architectural choices. In very deep networks, an ordered regime and a chaotic regime appear, determined by the choice of non-linearity and the balance between the weights and bias parameters; these two phases are characterized by different speeds of decay of the eigenvalues of the NTK, leading to a tradeoff between convergence speed and generalization. In practical contexts such as Generative Adversarial Networks or Topology Optimization, the network architecture can be chosen to guarantee certain properties of the NTK and its spectrum.These results give an almost complete description DNNs in this infinite-width limit. It is then natural to wonder how it extends to finite-width networks used in practice. In the so-called NTK regime, the discrepancy between finite- and infinite-widths DNNs is mainly a result of the variance w.r.t. to the sampling of the parameters, as shown empirically and mathematically relying on the similarity between DNNs and random feature models.In contrast to the NTK regime, where the NTK remains constant during training, there exist so-called active regimes, where the evolution of the NTK is significant, which appear in a number of settings. One such regime appears in Deep Linear Networks with a very small initialization, where the training dynamics approach a sequence of saddle-points, representing linear maps of increasing rank, leading to a low-rank bias which is absent in the NTK regime.

EPFL2022

Fréchet means in Wasserstein space

Yoav Zemel

This work studies the problem of statistical inference for Fréchet means in the Wasserstein space of measures on Euclidean spaces,

\mathcal W_2 ( \mathbb R^d )

. This question arises naturally from the problem of separating amplitude and phase variation in point processes, analogous to a well-known problem in functional data analysis. We formulate the point process version of the problem, show that it is canonically equivalent to that of estimating Fréchet means in

\mathcal W_2 ( \mathbb R d )

, and carry out estimation by means of

M

-estimation. This approach allows to achieve consistency in a genuinely nonparametric framework, even in a sparse sampling regime. For Cox processes on the real line, consistency is supplemented by convergence rates and, in the dense sampling regime,

\sqrt n

-consistency and a central limit theorem. Computation of the Fréchet mean is challenging when the processes are multivariate, in which case our Fréchet mean estimator is only defined implicitly as the minimiser of an optimisation problem. To overcome this difficulty, we propose a steepest descent algorithm that approximates the minimiser, and show that it converges to a local minimum. Our techniques are specific to the Wasserstein space, because Hessian-type arguments that are commonly used for similar convergence proofs do not apply to that space. In addition, we discuss similarities with generalised Procrustes analysis. The key advantage of the algorithm is that it requires only the solution of pairwise transportation problems. The results in the preceding paragraphs require properties of Fréchet means in

\mathcal W_2 ( \mathbb R ^d )

whose theory is developed, supplemented by some new results. We present the tangent bundle and exploit its relation to optimal maps in order to derive differentiability properties of the associated Fréchet functional, obtaining a characterisation of Karcher means. Additionally, we establish a new optimality criterion for local minima and prove a new stability result for the optimal maps that, enhanced with the established consistency of the Fréchet mean estimator, yields consistency of the optimal transportation maps.

EPFL2017