Research Group "Stochastic Algorithms and Nonparametric Statistics"
Research Seminar "Mathematical Statistics" Summer Semester 2018
|
|
| 18.04.18 | Dr. Alexandra Suvorikova (WIAS Berlin) |
| Gaussian process forecast with multidimensional distributional input In this work, we focus on forecasting a Gaussian process indexed by probability distributions. We introduce a family of positive definite kernels constructed with the use of optimal transportation distance and provide their probabilistic understanding. The technique allows to forecast efficiently Gaussian processes, which opens new perspective in Gaussian process modelling. |
|
| 25.04.18 | Nicolai Baldin (University of Cambridge, GB) |
| Optimal link prediction with matrix logistic regression
In this talk, we will consider the problem of link prediction, based on partial observation of a large network, and on side information associated to its vertices. The generative model is formulated as a matrix logistic regression. The performance of the model is analysed in a high-dimensional regime under a structural assumption. The minimax rate for the Frobenius-norm risk is established and a combinatorial estimator based on the penalised maximum likelihood approach is shown to achieve it. Furthermore, it is shown that this rate cannot be attained by any (randomised) algorithm computable in polynomial time under a computational complexity assumption. (joint work with Q. Berthet) |
|
| 02.05.18 | No Seminar |
| |
|
| 09.05.18 | Prof. Gitta Kutyniok (TU Berlin) |
| Optimal approximation with sparsely connected deep neural
networks Despite the outstanding success of deep neural networks in real-world applications, most of the related research is empirically driven and a mathematical foundation is almost completely missing. One central task of a neural network is to approximate a function, which for instance encodes a classi cation task. In this talk, we will be concerned with the question, how well a function can be approximated by a neural network with sparse connectivity. Using methods from approximation theory and applied harmonic analysis, we will derive a fundamental lower bound on the sparsity of a neural network. By explicitly constructing neural networks based on certain representation systems, so-called -shearlets, we will then demonstrate that this lower bound can in fact be attained. Finally, we present numerical experiments, which surprisingly show that already the standard backpropagation algorithm generates deep neural networks obeying those optimal approximation rates. This is joint work with H. Bolcskei (ETH Zurich), P. Grohs (Uni Vienna), and P. Petersen (TU Berlin). |
|
| 16.05.18 | Prof. Moritz Jirak (TU Braunschweig), Martin Wahl (HU Berlin) |
| Relative perturbation bounds with applications to empirical covariance operators A problem of fundamental importance in quantitative science is to estimate how a perturbation of a covariance operator effects the corresponding eigenvalues and eigenvectors. Due to its importance, this problem has been heavily investigated and discussed in the literature. In this talk, we present general perturbation expansions for a class of symmetric, compact operators. Applied to empirical covariance operators, these expansions allow us to describe how perturbations carry over to eigenvalues and vectors in terms of necessary and sucient conditions, characterising the perturbation transition. We demonstrate the usefulness of these expansions by discussing pca and fpca in various setups, including more exotic cases where the data is assumed to have high persistence in the dependence structure or exhibits (very) heavy tails. This talk is jointly given by Moritz Jirak and Martin Wahl, and divided into two parts. |
|
| 23.05.18 | Prof. Markus Reiss, Randolf Altmeyer (Humoldt-Universität zu Berlin) |
| A nonparametric estimation problem for linear SPDEs (Abstract) |
|
| 30.05.18 | Florian Schäfer (California Institute of Technology, USA) |
| Compression, inversion, and approximate PCA of dense kernel matrices
at near-linear computational complexity Many popular methods in machine learning, statistics, and uncertainty quantification rely on priors given by smooth Gaussian processes, like those obtained from the Matern covariance functions. Furthermore, many physical systems are described in terms of elliptic partial differential equations. Therefore, implicitely or explicitely, numerical simulation of these systems requires an ecient numerical representation of the corresponding Green's operator. The resulting kernel matrices are typically dense, leading to (often prohibitive) O (N^2) or O(N^3) computational complexity. In this work, we prove rigorously that the dense N x N kernel matrices obtained from elliptic boundary value problems and measurement points distributed approximately uniformly in a d-dimensional domain can be Cholesky factorised to accuracy in computational complexity O(N log^2(N) log^2d(N/e)) in time and O (N log(N) log d(N/e)) in space. For the closely related Matern covariances we observe very good results in practise, even for parameters corresponding to non-integer order equations. As a byproduct, we obtain a sparse PCA with near-optimal low-rank approximation property and a fast solver for elliptic PDE. We emphasise that our algorithm requires no analytic expression for the covariance function. Our work is inspired by the probabilistic interpretation of the Cholesky factorisation, the screening effect in spatial statistics, and recent results in numerical homogenisation. |
|
| 06.06.18 | |
| |
|
| 13.06.18 | Prof. Alain Celisse (Université des Sciences et Technologies de Lille, France) |
| |
|
| 20.06.18 | Prof. Zuoqiang Shi (Tsinghua University, Beijing, China) |
| The seminar takes place at room 406, 4th floor! | Low dimensional manifold model for image processing
In this talk, I will introduce a novel low dimensional manifold model for image processing problem. This model is based on the observation that for many natural images, the patch manifold usually has low dimension structure. Then, we use the dimension of the patch manifold as a regularization to recover the original image. Using some formula in differential geometry, this problem is reduced to solve Laplace-Beltrami equation on manifold. The Laplace-Beltrami equation is solved by the point integral method. Numerical tests show that this method gives very good results in image inpainting, denoising and super-resolution problem. This is joint work with Stanley Osher and Wei Zhu. |
| 27.06.18 | Stanislav Nagy (Charles University Prague) |
| Statistical depth for functional data The concept of data depth is an attempt to generalize quantiles to complex data (random vectors, random functions, or distributions on manifolds and graphs). The main idea is, for a general space S, to assign to any points from S its depth D(s; P) with respect to a probability distribution P on S. The depth D(s; P) says how "centrally located" s is with respect to P. The point maximizing D(:; P) over the sample space is a generalized median; loci of points with high depth constitute inner depth-quantile regions of P. We study depth designed for functional data, and its general framework. We show that most known functional depths can be classi ed into few groups, within which they share similar theoretical properties. We focus on uniform sample consistency results, and demonstrate that some well-known approaches to depth assessment are hardly theoretically adequate. |
|
| 04.07.18 | N.N. |
| |
|
| 11.07.18 | NO Seminar there is: IRTG Summer Camp |
| |
|
| 18.07.18 | Jan van Waaij (HU Berlin) |
| Adaptive nonparametric Bayesian methods for SDEs We consider continuous time observations (Xt_0\le t\le T of the SDE dXt = \Theta(Xt)dt + dWt: Our goal is estimating the unknown drift function \Theta. Due to their numerical advantages, Bayesian methods are often used for this. In this talk I discuss optimal rates of convergence for these methods. I will start with an introduction to Bayesian methods for SDEs and what sufficient con- ditions are for posterior convergence. I show that the sufficient conditions are satisfied for the Gaussian process prior, which leads to optimal convergence rates, provided the smoothness of \Theta matches the smootness of the Gaussian process. Adaptivity can be obtained by equipping the hyperparameter(s) of the Gaussian process prior with an additional prior. We discuss several choices for such hyperparameters. A new promising approach to obtain adaptivity is empirical Bayes. Here the optimal hyperparameters for the Gaussian process prior are first esti- mated from the data and then the prior with those hyperparameters plugged- in is used for the inference. This talk is based on van Waaij, 2018 and joint work with Frank van der Meulen (TU Delft), Moritz Schauer (Leiden University) and Harry van Zanten (University of Amsterdam). |
last reviewed: July 6, 2018 by Christine Schneider