Sparse Dictionaries for Continuous-Domain Inverse Problems

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

Motivation Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretati ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

Neural networks have shown to be a powerful tool to represent the ground state of quantum many-body systems, including fermionic systems. However, efficiently integrating lattice symmetries into neural representations remains a significant challenge. In th ...

Proteins are the molecular machines of life, driving essential biological processes such as enzymatic catalysis, cellular signaling, and immune responses. The ability to design entirely new proteins with desired structures and functions has immense implica ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

In this paper we fully describe the trajectory of gradient flow over diagonal linear networks in the limit of vanishing initialisation. We show that the limiting flow successively jumps from a saddle of the training loss to another until reaching the minim ...

Communication by rare, binary spikes is a key factor for the energy efficiency of biological brains. However, it is harder to train biologically-inspired spiking neural networks than artificial neural networks. This is puzzling given that theoretical resul ...

Robustness and stability of image-reconstruction algorithms have recently come under scrutiny. Their importance to medical imaging cannot be overstated. We review the known results for the topical variational regularization strategies ( ℓ2 and ℓ1 regulariz ...

Deep Neural Networks (DNNs) have obtained impressive performance across tasks, however they still remain as black boxes, e.g., hard to theoretically analyze. At the same time, Polynomial Networks (PNs) have emerged as an alternative method with a promising ...

Machine learning has transformed many fields and has recently found applications in chemistry and materials science. The small datasets commonly found in chemistry sparked the development of sophisticated machine learning approaches that incorporate chemic ...

Machine learning models have been shown to leak sensitive information about their training datasets. Models are increasingly deployed on devices, raising concerns that white-box access to the model parameters increases the attack surface compared to black- ...

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...

Neural machine translation (MT) and text generation have recently reached very high levels of quality. However, both areas share a problem: in order to reach these levels, they require massive amounts of data. When this is not present, they lack generaliza ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

We generalize and provide a linear algebra-based perspective on a finite element (FE) ho-mogenization scheme, pioneered by Schneider et al. (2017)[1] and Leuschner and Fritzen (2018)[2]. The efficiency of the scheme is based on a preconditioned, well-scale ...

The goal of this thesis is the development and the analysis of numerical methods for problems where the unknown is a curve on a smooth manifold. In particular, the thesis is structured around the three following problems: homotopy continuation, curve inter ...

Sparse Dictionaries for Continuous-Domain Inverse Problems

Chat with Graph Search

Learning to Reason with Neural Networks: Principles and Methods

A comparative analysis of gene expression profiling by statistical and machine learning approaches

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Spectroscopy of two-dimensional interacting lattice electrons using symmetry-aware neural backflow transformations

Computational design of complex protein folds and soluble analogs of membrane proteins

Understanding generalization and robustness in modern deep learning

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Sparse autoregressive neural networks for classical spin systems

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

High-performance deep spiking neural networks with 0.3 spikes per neuron

Stability of Image-Reconstruction Algorithms

Regularization of polynomial networks for image recognition

Leveraging large language models for predictive chemistry

Investigating the Effect of Misalignment on Membership Privacy in the White-box Setting

Regularization of polynomial networks for image recognition

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Regularization Techniques for Low-Resource Machine Translation

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

An optimal preconditioned FFT-accelerated finite element solver for homogenization

Retraction-based numerical methods for continuation, interpolation and time integration on manifolds