How Two-Layer Neural Networks Learn, One (Giant) Step at a Time

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.

In this thesis, we study how combinatorial structures and symmetries emerge from analytic properties of graph polynomials and neural networks. Graph polynomials encode combinatorial aspects of the underlying graph in their coefficients and are remarkably u ...

To protect both local gradients and estimated parameters in distributed learning, this paper introduces a masked diffusion (MD) strategy, leading to two algorithms: the MD stochastic gradient (MD-SG) and the MD primal-dual stochastic gradient (MPD-SG). The ...

Electrochemical gas sensors (EGSs) have been used to measure the surface distributions and vertical profiles of trace gases in the wintertime Arctic boundary layer during the Alaskan Layered Pollution and Chemical Analysis (ALPACA) field experiment in Fair ...

Restoring natural sensation via neuroprosthetics relies on the possibility of encoding complex and nuanced information. For example, an ideal brain–machine interface with sensory feedback would provide the user with sensation about movement, pressure, curv ...

We propose a machine learning-based estimator of the hand state for rehabilitation purposes, using light exoskeletons. These devices are easy to use and useful for delivering domestic and frequent therapies. We build a supervised approach using information ...

A first-principles approach for calculating ion separation in solution through two-dimensional (2D) membranes is proposed and applied. Ionic energy profiles across the membrane are obtained first, where solvation effects are simulated explicitly with machi ...

The Euclid Wide Survey (EWS) is predicted to find approximately 170 000 galaxy-galaxy strong lenses from its lifetime observation of 14 000 deg2 of the sky. Detecting this many lenses by visual inspection with professional astronomers and citizen scientist ...

Teravoxel-scale, cellular-resolution images of cleared rodent brains acquired with light-sheet fluorescence microscopy have transformed the way we study the brain. Realizing the potential of this technology requires computational pipelines that generalize ...

Virtual reality (VR) environments simulating height offer a unique platform to investigate neural adaptations to emotionally salient contexts during locomotion. These simulations allow for controlled analysis of motor‐cognitive interactions under perceived ...

Noise detrimentally affects quantum computations so that they not only become less accurate but also easier to simulate classically as systems scale up. We construct a classical simulation algorithm, lowesa (low weight efficient simulation algorithm), for ...

Forthcoming imaging surveys will increase the number of known galaxy-scale strong lenses by several orders of magnitude. For this to happen, images of billions of galaxies will have to be inspected to identify potential candidates. In this context, deep-le ...

Virtual reality (VR) technology revitalises rehabilitation training by creating rich, interactive virtual rehabilitation scenes and tasks that deeply engage patients. Robotics with immersive VR environments have the potential to significantly enhance the s ...

Planning aircraft trajectories to avoid climate-sensitive areas poses operational challenges, including increased traffic complexity and potential safety risks. This study presents a framework designed to plan operationally feasible climate-friendly routes ...

Electrochemical devices and systems are significant for the development of therapeutic drug monitoring (TDM) and personalized therapy. However, electrochemical sensors are usually not that much selective. Therefore, innovative machine learning (ML) approac ...

Understanding the brain requires studying its multiscale interactions from molecules to networks. The increasing availability of large-scale datasets detailing brain circuit composition, connectivity, and activity is transforming neuroscience. However, int ...

In the field of model predictive control, Dataenabled Predictive Control (DeePC) offers direct predictive control, bypassing traditional modeling. However, challenges emerge with increased computational demand due to recursive data updates. This paper intr ...

Stochastic Nonlinear Optimal Control (SNOC) involves minimizing a cost function that averages out the random uncertainties affecting the dynamics of nonlinear systems. For tractability reasons, this problem is typically addressed by minimizing an empirical ...

The social learning paradigm for distributed hypothesis testing involves a collection of agents interacting over a graph, each observing streaming data that provide evidence about the state of the environment. These agents perform a series of local Bayesia ...

We study robust linear regression in highdimension, when both the dimension d and the number of data points n diverge with a fixed ratio α = n/d, and study a data model that includes outliers. We provide exact asymptotics for the performances of the empiri ...

Accurately predicting the power conversion efficiency (PCE) in dye-sensitized solar cells (DSSCs) represents a crucial challenge, one that is pivotal for the high throughput rational design and screening of promising dye sensitizers. This study presents pr ...

How Two-Layer Neural Networks Learn, One (Giant) Step at a Time

Chat with Graph Search

Combinatorial Aspects of Continuous Optimization: Graph Polynomials and Neural Networks

Masked Diffusion Strategy for Privacy-Preserving Distributed Learning

Surface distributions and vertical profiles of trace gases (CO, O3, NO, NO2) in the Arctic wintertime boundary layer using low-cost sensors during ALPACA-2022

Optimization frameworks for bespoke sensory encoding in neuroprosthetics

Learning Hand State Estimation for a Light Exoskeleton

Ion Sieving in Two-Dimensional Membranes from First Principles

Euclid: Searches for strong gravitational lenses using convolutional neural nets in Early Release Observations of the Perseus field

A deep learning pipeline for three-dimensional brain-wide mapping of local neuronal ensembles in teravoxel light-sheet microscopy

Walking on the Edge: Brain Connectivity Changes in Response to Virtual Height Challenges

Classical simulations of noisy variational quantum circuits

Euclid preparation XXXIII. Characterization of convolutional neural networks for the identification of galaxy-galaxy strong-lensing events

Rehabilitation exoskeleton system with bidirectional virtual reality feedback training strategy

Aircraft Trajectory Planning for Climate Hotspot Avoidance Considering Air Traffic Complexity: A Constrained Multi-Agent Reinforcement Learning Approach

Simultaneous Quantification of Multiple Drugs by Machine Learning on Electrochemical Sensors

Large-Scale Mechanistic Models of Brain Circuits with Biophysically and Morphologically Detailed Neurons

Efficient Recursive Data-enabled Predictive Control

A PAC-Bayesian Framework for Optimal Control with Stability Guarantees

Inverse Graph Learning from Social Interactions

Asymptotic Characterisation of the Performance of Robust Linear Regression in the Presence of Outliers

Advanced High-Throughput Rational Design of Porphyrin-Sensitized Solar Cells Using Interpretable Machine Learning