Ensemble Distillation for Robust Model Fusion in Federated Learning

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 magnetic confinement fusion devices, such as tokamaks, is strongly correlated to the phenomena that occur in the boundary region of the plasma core that faces the wall of the device. The dominant cross-field transport mechanisms from the ...

In magnetic fusion devices, error field (EF) sources, spurious magnetic field perturbations, need to be identified and corrected for safe and stable (disruption-free) tokamak operation. Within Work Package Tokamak Exploitation RT04, a series of studies hav ...

Herein, machine learning (ML) models using multiple linear regression (MLR), support vector regression (SVR), random forest (RF) and artificial neural network (ANN) are developed and compared to predict the output features viz. specific capacitance (Csp), ...

Computing servers have played a key role in developing and processing emerging compute-intensive applications in recent years. Consolidating multiple virtual machines (VMs) inside one server to run various applications introduces severe competence for limi ...

Decision-making permeates every aspect of human and societal development, from individuals' daily choices to the complex decisions made by communities and institutions. Central to effective decision-making is the discipline of optimization, which seeks th ...

Plasmas with negative triangularity (NT) shape have been recently shown to be able to achieve H-mode levels of confinement in L-mode, avoiding detrimental edge localised modes. Therefore, this plasma geometry is now studied as a possible viable option for ...

Machine learning has provided a means to accelerate early-stage drug discovery by combining molecule generation and filtering steps in a single architecture that leverages the experience and design preferences of medicinal chemists. However, designing mach ...

We introduce robust principal component analysis from a data matrix in which the entries of its columns have been corrupted by permutations, termed Unlabeled Principal Component Analysis (UPCA). Using algebraic geometry, we establish that UPCA is a well-de ...

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 ...

The design point that had been chosen for EU DEMO in 2016 is reviewed here and a modification is proposed with a lower aspect ratio. Previously the same aspect ratio, A, was chosen for EU DEMO as in major tokamak experiments including ITER (A = 3.1), and, ...

Reinforcement learning (RL) has shown promising results for real-time control systems, including the domain of plasma magnetic control. However, there are still significant drawbacks compared to traditional feedback control approaches for magnetic confinem ...

Electrochemical Impedance Spectroscopy (EIS) and Equivalent Circuit Models (ECMs) are widely used to characterize the impedance and estimate parameters of electrochemical systems such as batteries. We use a generic ECM with ten parameters grouped to model ...

The implementation of three-dimensional magnetic fields, such as the ones of stellarators, in the GBS code (Ricci et al 2012 Plasma Phys. Control. Fusion54 124047; Giacomin et al 2022 J. Comput. Phys.464 111294) is presented, and simulation results are dis ...

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 ...

Epilepsy, a major neurological disease, requires careful diagnosis and treatment. However, the detection of epileptic seizures remains a significant challenge. Current clinical practice relies on expert analysis of EEG signals, a process that is time-consu ...

In computational hydraulics models, predicting bed topography and bedload transport with sufficient accuracy remains a significant challenge. An accurate assessment of a river's sediment transport rate necessitates a prior understanding of its bed topograp ...

Neural network approaches to approximate the ground state of quantum hamiltonians require the numerical solution of a highly nonlinear optimization problem. We introduce a statistical learning approach that makes the optimization trivial by using kernel me ...

Ensemble Distillation for Robust Model Fusion in Federated Learning

Chat with Graph Search

Divertor turbulence characterisation using Gas Puff Imaging in the TCV tokamak

Error field detection and correction studies towards ITER operation

Machine learning models for prediction of electrochemical properties in supercapacitor electrodes using MXene and graphene nanoplatelets

CloudProphet: A Machine Learning-Based Performance Prediction for Public Clouds

Reliable data-driven decision-making through optimal transport

First-principle based predictions of the effects of negative triangularity on DTT scenarios

Machine learning-aided generative molecular design

Unlabeled Principal Component Analysis and Matrix Completion

Partial discharge localization in power transformer tanks using machine learning methods

Re-design of EU DEMO with a low aspect ratio

Towards practical reinforcement learning for tokamak magnetic control

On the use of Cramér-Rao Lower Bound for least-variance circuit parameters identification of Li-ion cells

Global fluid simulation of plasma turbulence in stellarators with the GBS code

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

Resource-Efficient Continual Learning for Personalized Online Seizure Detection

Stochastic Simulations and Machine Learning Modeling to Predict Bedload Transport and Bed Topography

Learning ground states of gapped quantum Hamiltonians with Kernel Methods