Publications associées à Neural Tangent Kernel: Convergence and Generalization in Neural Networks (Invited Paper)

Publications associées (45)

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

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

Search for Pair Production of Heavy Particles Decaying to a Top Quark and a Gluon in the Lepton Plus Jets Final State in Proton-proton Collisions at √s=13 Tev

Jan Steggemann, Anna Mascellani, Joanna Malgorzata Wanczyk

A search is presented for the pair production of new heavy resonances, each decaying into a top quark (t) or antiquark and a gluon (g). The analysis uses data recorded with the CMS detector from proton-proton collisions at a center-of-mass energy of 13 TeV ...

SPRINGER2025

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

Boosting Resource-Constrained Federated Learning Systems with Guessed Updates

Mohamed Yassine Boukhari, Anne-Marie Kermarrec, Rafael Pereira Pires, Rishi Sharma, Akash Balasaheb Dhasade

Federated learning (FL) enables a set of client devices to collaboratively train a model without sharing raw data. This process, though, operates under the constrained computation and communication resources of edge devices. These constraints combined with ...

Institute of Electrical and Electronics Engineers (IEEE)2025

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

On the Perspectives of Image-to-Lidar Constraints in Dynamic Network Optimisation

Thibaut Stoltz, Jan Skaloud, Davide Antonio Cucci, Laurent Valentin Jospin, Kyriaki Mouzakidou

The evolution of airborne mapping witnesses the introduction of hybrid lidar-camera systems to enhance data collection, i.e. to obtain simultaneously high-density point-cloud and texture. Yet, the common adjustment of both optical data streams is a nontriv ...

International Society for Photogrammetry and Remote Sensing2025

Modelleyen: Continual Learning and Planning via Structured Modelling of Environment Dynamics

Boi Faltings, Zeki Doruk Erden

The current machine learning paradigm relies on continuous representations and fixed neural network architectures to approximate environmental structures, leading to challenges with continual learning, internal structure design, and goal-directed behavior ...

Springer Science and Business Media Deutschland GmbH2025

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

Minh Hieu Lê

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

Springer Science and Business Media Deutschland GmbH2025

Overcoming Distribution Shifts and Imbalance Challenges in Representation Learning for Deep Regression Models

Ismail Nejjar

Deep learning has shown remarkable potential for industrial applications, particularly in predictive maintenance and condition monitoring. A key challenge in this domain is prognostics, specifically predicting the Remaining Useful Life (RUL) of assets - a ...

EPFL2025

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Thomas Grégoire Stegmüller

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

EPFL2025

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

Person Re-Identification and its Application to Multi-Object Tracking

Vladimir Dominic K. Somers

Multi-Object Tracking (MOT) is a fundamental computer vision task that involves detecting objects of interest in video frames and associating detections of the same object across time to form trajectories. For association, appearance cues, extracted throug ...

EPFL2025

Scalable kernel logistic regression with Nyström approximation: Theoretical analysis and application to discrete choice modelling

Michel Bierlaire

The application of kernel-based Machine Learning (ML) techniques to discrete choice modelling using large datasets often faces challenges due to memory requirements and the considerable number of parameters involved in these models. This complexity hampers ...

2025

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

M2SKD: Multi-to-Single Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Systems

David Atienza Alonso, Amir Aminifar, Tomas Teijeiro Campo, Alireza Amirshahi, Saleh Baghersalimi, Farnaz Forooghifar

Integrating low-power wearable systems into routine health monitoring is an ongoing challenge. Recent advances in the computation capabilities of wearables make it possible to target complex scenarios by exploiting multiple biosignals and using high-perfor ...

2024

Machine Learning for Modeling Stock Returns

Teng Andrea Xu

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

EPFL2024

Aggregating Spatial and Photometric Context for Photometric Stereo

David Honzátko

Photometric stereo, a computer vision technique for estimating the 3D shape of objects through images captured under varying illumination conditions, has been a topic of research for nearly four decades. In its general formulation, photometric stereo is an ...

EPFL2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Volkan Cevher, Grigorios Chrysos, Fanghui Liu

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

2024

On the number of regions of piecewise linear neural networks

Michaël Unser, Alexis Marie Frederic Goujon

Many feedforward neural networks (NNs) generate continuous and piecewise-linear (CPWL) mappings. Specifically, they partition the input domain into regions on which the mapping is affine. The number of these so-called linear regions offers a natural metric ...

2024