Publications associées à Sparse Dictionaries for Continuous-Domain Inverse Problems

Publications associées (50)

Learning to Reason with Neural Networks: Principles and Methods

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 ...

EPFL2025

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

Anaïs Betsabeh Haget, Maria Boulougouri

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 ...

OXFORD UNIV PRESS2025

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

Zhixiong Jin

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 ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2025

K-space physics-informed neural network (k-PINN) for compressed spectral mapping and efficient inversion of vibrations in thin composite laminates

Olga Fink

The vibrational response of structural components carries valuable information about their underlying mechanical properties, health status and operational conditions. This underscores the need for the development of efficient physics-based inversion algori ...

Elsevier BV2025

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

Giuseppe Carleo, Jannes Willy E. Nys, Imelda Romero

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 ...

NATURE PORTFOLIO2025

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

Casper Alexander Goverde

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 ...

EPFL2025

Understanding generalization and robustness in modern deep learning

Maksym Andriushchenko

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 ...

EPFL2024

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

Pakshal Narendra Bohra

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 ...

EPFL2024

Sparse autoregressive neural networks for classical spin systems

Giuseppe Carleo, Dian Wu, Indaco Biazzo

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 ...

Iop Publishing Ltd2024

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

Nicolas Henri Bernard Flammarion, Scott William Pesme

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 ...

2023

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

Wulfram Gerstner, Stanislaw Andrzej Wozniak, Guillaume Emmanuel Fernand Bellec, Ana Stanojevic, Angeliki Pantazi

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 ...

Springer Science and Business Media LLC2024

Stability of Image-Reconstruction Algorithms

Michaël Unser, Sebastian Jonas Neumayer, Pol del Aguila Pla

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 ...

2023

Regularization of polynomial networks for image recognition

Volkan Cevher, Grigorios Chrysos, Bohan Wang

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 ...

2023

Leveraging large language models for predictive chemistry

Berend Smit, Philippe Schwaller, Kevin Maik Jablonka, Andres Adolfo Ortega Guerrero

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 ...

Nature Portfolio2024

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

Ana-Maria Cretu

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- ...

Privacy Enhancing Technologies Symposium Advisory Board2024

Regularization of polynomial networks for image recognition

Volkan Cevher, Grigorios Chrysos, Bohan Wang

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 ...

Ieee Computer Soc2023

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

Volkan Cevher, Fanghui Liu

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 ...

2024

Regularization Techniques for Low-Resource Machine Translation

Alejandro Ramírez Atrio

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 ...

EPFL2023

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

Pascal Fua, Mathieu Salzmann, Andrey Davydov

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 ...

Journal of Machine Learning Research Inc.2024

An optimal preconditioned FFT-accelerated finite element solver for homogenization

Till Junge, Ali Falsafi

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 ...

ELSEVIER SCIENCE INC2023