A Theory of Finite-Width Neural Networks: Generalization, Scaling Laws, and the Loss Landscape

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.

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

Low-light photography produces images with low signal-to-noise ratios due to limited photons. In such conditions, common approximations like the Gaussian noise model fall short, and many denoising techniques fail to remove noise effectively. Although deep- ...

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

In the past few years, Machine Learning (ML) techniques have ushered in a paradigm shift, allowing the harnessing of ever more abundant sources of data to automate complex tasks. The technical workhorse behind these important breakthroughs arguably lies in ...

When arranged in a crossbar configuration, resistive memory devices can be used to execute Matrix-Vector Multiplications (MVMs), the most dominant operation of many Machine Learning (ML) algorithms, in constant time complexity. Nonetheless, when performing ...

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 ...

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 ...

The present work proposes a framework for nonlinear model order reduction based on a Graph Convolutional Autoencoder (GCA-ROM). In the reduced order modeling (ROM) context, one is interested in obtaining real -time and many-query evaluations of parametric ...

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 ...

Fluorescence lifetime imaging (FLI) has been receiving increased attention in recent years as a powerful diagnostic technique in biological and medical research. However, existing FLI systems often suffer from a tradeoff between processing speed, accuracy, ...

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 ...

Modern neuroscience research is generating increasingly large datasets, from recording thousands of neurons over long timescales to behavioral recordings of animals spanning weeks, months, or even years. Despite a great variety in recording setups and expe ...

Decentralized learning (DL) is an emerging approach that enables nodes to collaboratively train a machine learning model without sharing raw data. In many application domains, such as healthcare, this approach faces challenges due to the high level of hete ...

Accurate forecasting of photovoltaic (PV) power production is crucial for the integration of more renewable energy sources into the power grid. PV power production is highly intermittent, due to the stochastic cloud behaviour and cloud dynamics. Previous w ...

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 ...

This paper presents a comparison of machine learning (ML) methods used for three-dimensional localization of partial discharges (PD) in a power transformer tank. The study examines ML and deep learning (DL) methods, ranging from support vector machines (SV ...

Cyclic peptides are attractive for drug discovery due to their excellent binding properties and the potential to cross cell membranes. However, by far not all cyclic peptides are cell permeable, and measuring or predicting their membrane permeability is no ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

Federated learning (FL) is a machine learning approach where nodes collaboratively train a global model. As more nodes participate in a round of FL, the effectiveness of individual model updates by nodes also diminishes. In this study, we increase the effe ...

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 ...

A Theory of Finite-Width Neural Networks: Generalization, Scaling Laws, and the Loss Landscape

Chat with Graph Search

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Dark Noise Diffusion: Noise Synthesis for Low-Light Image Denoising

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE

Topics in statistical physics of high-dimensional machine learning

LIONHEART: A Layer-based Mapping Framework for Heterogeneous Systems with Analog In-Memory Computing Tiles

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

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

A graph convolutional autoencoder approach to model order reduction for parametrized PDEs

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

Coupling a recurrent neural network to SPAD TCSPC systems for real-time fluorescence lifetime imaging

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

Robust machine learning for neuroscientific inference

Fair Decentralized Learning

Network time series forecasting in photovoltaics power production

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

Partial discharge localization in power transformer tanks using machine learning methods

Bulk measurement of membrane permeability for random cyclic peptides in living cells to guide drug development

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning

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