8 citations · 26 across the 13 of their papers we have counts for
15 papers
Brownian Heads for Deep ReLU Representations: Activation Mass and the Cost of Same-Sample Selection
Mahdi Mohammadigohari, Nicole Mücke
Deep representation learning often selects hidden features and fits the final predictor on the same sample, so fixed-feature analysis performed after selection can omit selection c…
A Smoothed Discrepancy Principle for Random Feature Methods and Neural Networks
Mike Nguyen, Nicole Mücke
We study data-driven early stopping for spectral regularisation methods in the classical non-parametric regression setting. Building on the discrepancy principle, we propose a mult…
Random Features for Operator-Valued Kernels: Bridging Kernel Methods and Neural Operators
Mike Nguyen, Nicole Mücke
In this work, we investigate the generalization properties of random feature methods. Our analysis extends prior results for Tikhonov regularization to a broad class of spectral re…
Optimal Convergence Rates for Neural Operators
Mike Nguyen, Nicole Mücke
We introduce the neural tangent kernel (NTK) regime for two-layer neural operators and analyze their generalization properties. For early-stopped gradient descent (GD), we derive f…
Statistical inverse learning problems with random observations
Abhishake Rastogi, Tapio Helin, Nicole Mücke
We provide an overview of recent progress in statistical inverse problems with random experimental design, covering both linear and nonlinear inverse problems. Different regulariza…
How many Neurons do we need? A refined Analysis for Shallow Networks trained with Gradient Descent
Mike Nguyen, Nicole Mücke
We analyze the generalization properties of two-layer neural networks in the neural tangent kernel (NTK) regime, trained with gradient descent (GD). For early stopped GD we derive…
Learning linear operators: Infinite-dimensional regression as a well-behaved non-compact inverse problem
Mattes Mollenhauer, Nicole Mücke, T. J. Sullivan
We consider the problem of learning a linear operator between two Hilbert spaces from empirical observations, which we interpret as least squares regression in infinite dimensi…
Algorithm Unfolding for Block-sparse and MMV Problems with Reduced Training Overhead
Jan Christian Hauffen, Peter Jung, Nicole Mücke
In this paper we consider algorithm unfolding for the Multiple Measurement Vector (MMV) problem in the case where only few training samples are available. Algorithm unfolding has b…
From inexact optimization to learning via gradient concentration
Bernhard Stankewitz, Nicole Mücke, Lorenzo Rosasco
Optimization in machine learning typically deals with the minimization of empirical objectives defined by training data. However, the ultimate goal of learning is to minimize the e…
Stochastic Gradient Descent Meets Distribution Regression
Nicole Mücke
Stochastic gradient descent (SGD) provides a simple and efficient way to solve a broad range of machine learning problems. Here, we focus on distribution regression (DR), involving…
Lepskii Principle in Supervised Learning
Gilles Blanchard, Peter Mathé, Nicole Mücke
In the setting of supervised learning using reproducing kernel methods, we propose a data-dependent regularization parameter selection rule that is adaptive to the unknown regulari…
Empirical Risk Minimization in the Interpolating Regime with Application to Neural Network Learning
Nicole Mücke, Ingo Steinwart
A common strategy to train deep neural networks (DNNs) is to use very large architectures and to train them until they (almost) achieve zero training error. Empirically observed go…
Reducing training time by efficient localized kernel regression
Nicole Mücke
We study generalization properties of kernel regularized least squares regression based on a partitioning approach. We show that optimal rates of convergence are preserved if the n…
Kernel regression, minimax rates and effective dimensionality: beyond the regular case
Gilles Blanchard, Nicole Mücke
We investigate if kernel regularization methods can achieve minimax convergence rates over a source condition regularity assumption for the target function. These questions have be…
Parallelizing Spectral Algorithms for Kernel Learning
Gilles Blanchard, Nicole Mücke
We consider a distributed learning approach in supervised learning for a large class of spectral regularization methods in an RKHS framework. The data set of size n is partitioned…