Search for tag: "triad distinguished lecture series"

Yuxin Chen - Inference and Uncertainty Quantification for Noise Matrix Completion

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…

From  Kathryn Gentilello on September 17th, 2019 12 plays 0  

Yuxin Chen - Random initialization and implicit regularization in nonconvex statistical estimation

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…

From  Kathryn Gentilello on September 17th, 2019 6 plays 0  

Yuxin Chen - Spectral Methods Meets Asymmetry: Two Recent Stories

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…

From  Kathryn Gentilello on September 9th, 2019 3 plays 0  

Yuxin Chen - Projected Power Method: An Efficient Algorithm for Joint Discrete Assignment

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,…

From  Kathryn Gentilello on September 9th, 2019 6 plays 0  

Yuxin Chen - [Lecture 1] The power of nonconvex optimization in solving random quadratic systems of equations

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…

From  Kathryn Gentilello on September 3rd, 2019 22 plays 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks: Energy landscape and open problems (Lecture 5/5)

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…

From  Kathryn Gentilello on March 28th, 2019 51 plays 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks: Statistical theory for deep ReLU networks (Lecture 4/5)

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…

From  Kathryn Gentilello on March 28th, 2019 36 plays 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks: Advantages of Additional Layers (Lecture 3/5)

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…

From  Kathryn Gentilello on March 18th, 2019 46 plays 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks : Theory for shallow networks (Lecture 2/5)

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…

From  Kathryn Gentilello on March 13th, 2019 66 plays 0  

Johannes Schmidt-Hieber - Mathematics for Deep Neural Networks (Lecture 1/5)

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…

From  Kathryn Gentilello on March 8th, 2019 119 plays 0  

Michael Mitzenmacher - Bloom Filters, Cuckoo Hashing, Cuckoo Filters, Adaptive Cuckoo Filters, and Learned Bloom Filters

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…

From  Kathryn Gentilello on December 3rd, 2018 55 plays 0  

Gabor Lugosi - Mean Estimation: Median-of-Means Tournaments

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…

From  Kathryn Gentilello on November 14th, 2018 19 plays 0  

Gabor Lugosi - Combinatorial Testing Problems

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…

From  Kathryn Gentilello on November 7th, 2018 25 plays 0  

Sara van de Geer - The Debiased Lasso

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…

From  Kathryn Gentilello on September 11th, 2018 130 plays 0  

Sara van de Geer - Compatibility and the Lasso

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…

From  Kathryn Gentilello on September 10th, 2018 82 plays 0