|
Noisy matrix completion aims at estimating a low-rank matrix given
only partial and corrupted entries. Despite substantial progress in designing
efficient estimation algorithms, it remains largely…
name
Yuxin Chen Date
September 5th, 2019
|
|
Recent years have seen a flurry of activities in designing
provably efficient nonconvex procedures for solving statistical estimation /
learning problems. Due to the highly nonconvex nature of the…
name
Yuxin Chen Date
August 29th, 2019
|
|
This talk is concerned with the interplay between asymmetry and
spectral methods. Imagine that we have access to an asymmetrically perturbed
low-rank data matrix. We attempt estimation of the…
name
Yuxin Chen Date
September 4th, 2019
|
|
Various applications involve assigning discrete label values to a
collection of objects based on some pairwise noisy data. Due to the
discrete---and hence nonconvex---structure of the problem,…
name
Yuxin Chen Date
September 3rd, 2019
|
|
We consider the fundamental problem of solving random quadratic systems of equations in n variables, which spans many applications ranging from the century-old phase retrieval problem to various…
name
Yuxin Chen Date
August 28th, 2019
|
|
name
Duen Horng (Polo) Chau Date
August 8th, 2019
|
|
To derive a theory for gradient descent methods, it is important to have some understanding of the energy landscape. In this lecture, an overview of existing results is given. The second part of the…
name
Johannes Schmidt-Hieber Date
March 18th, 2019
|
|
We outline the theory underlying the recent bounds on the estimation risk of deep ReLU networks. In the lecture, we discuss specific properties of the ReLU activation function that relate to skipping…
name
Johannes Schmidt-Hieber Date
March 15th, 2019
|
|
Why are deep networks better than shallow networks? We provide a survey of the existing ideas in the literature. In particular, we discuss localization of deep networks, functions that can be easily…
name
Johannes Schmidt-Hieber Date
March 13th, 2019
|
|
We start with the universal approximation theorem and discuss several proof strategies that provide some insights into functions that can be easily approximated by shallow networks. Based on this, a…
name
Johannes Schmidt-Hieber Date
March 8th, 2019
|
|
Lecture 1) Survey on neural network structures and deep learning There are many different types of neural networks that differ in complexity and the data types that can be processed. This lecture…
name
Johannes Schmidt-Hieber Date
March 6th, 2019
|
|
I will go over some of my past and present work on hashing-based data structures. After presenting some background on Bloom filters and cuckoo hashing, we will describe cuckoo filters, an efficient…
name
Michael Mitzenmacher Date
November 26th, 2018
|
|
In these lectures we discuss some statistical problems with an interesting combinatorial structure behind. We start by reviewing the "hidden clique" problem, a simple prototypical example…
name
Gabor Lugosi Date
October 25th, 2018
|
|
In these lectures we discuss some statistical problems with an interesting combinatorial structure behind. We start by reviewing the "hidden clique" problem, a simple prototypical example…
name
Gabor Lugosi Date
October 18th, 2018
|
|
In the third lecture we use sparsity to establish confidence intervals for a
parameter of interest. The idea is to use the penalized estimator as an initial
estimator in a one-step Newton-Raphson…
name
Sara van de Geer biography
Sara van de Geer has been Full Professor at the Seminar for Statistics at ETH Zurich since September 2005. Her main field of research is mathematical statistics, with special interest in high-dimensional problems. Date
September 6th, 2018
|
|
We will see in the first lecture that one needs conditions
which relate the penalty to the risk function. They have in a certain sense to
be “compatible”. We discuss these compatibility…
name
Sara van de Geer biography
Sara van de Geer has been Full Professor at the Seminar for Statistics at ETH Zurich since September 2005. Her main field of research is mathematical statistics, with special interest in high-dimensional problems. Date
September 4th, 2018
|