One-Bit Byzantine-Tolerant Distributed Learning via Over-The-Air Computation

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.

Reflective writing is known as a useful method in learning sciences to improve the metacognitive skills of students. However, students struggle to structure their reflections properly, limiting the possible learning gains. Previous works in educational tec ...

Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most existing performance prediction methods heavily rely on the source data in their ...

Data analyses in particle physics rely on an accurate simulation of particle collisions and a detailed simulation of detector effects to extract physics knowledge from the recorded data. Event generators together with a geant-based simulation of the detect ...

Adiabatic quantum-flux parametron (AQFP) is an energy-efficient superconducting technology. Before physical design can be performed, AQFP technology mapping involves not only mapping logic into supported gate types but also legalizing the circuit to fulfil ...

Orthogonal frequency-division multiplexing (OFDM) is widely used to mitigate inter-symbol interference (ISI) from multipath fading. However, the open nature of wireless OFDM systems makes them vulnerable to jamming attacks. In this context, pilot jamming i ...

Monitoring forests, in particular their response to climate and land use change, requires studying long time scales. While efficient deep learning methods have been developed to process short time series of satellite imagery, leveraging long time series of ...

Operators from various industries have been pushing the adoption of wireless sensing nodes for industrial monitoring, and such efforts have produced sizeable condition monitoring datasets that can be used to build diagnosis algorithms capable of warning ma ...

Digital solutions play a key role for enabling blended learning in higher engineering education, where the acquisition and the appropriation of core competences and transversal skills require interactive resources offering a high-level and quasi-profession ...

Vision Transformers (ViTs) demonstrate remarkable performance in image classification through visual-token interaction learning, particularly when equipped with local information via region attention or convolutions. Although such architectures improve the ...

Conventional lasers typically support a well‐defined comb of modes. Coupling many resonators together to form larger complex cavities enables the design of the spatial and spectral distribution of modes, for sensitive and controllable on‐chip light sources ...

Physics-informed machine learning (PIML) is a set of methods and tools that systematically integrate machine learning (ML) algorithms with physical constraints and abstract mathematical models developed in scientific and engineering domains. As opposed to ...

We consider the problem of learning a target function corresponding to a deep, extensive-width, non-linear neural network with random Gaussian weights. We consider the asymptotic limit where the number of samples, the input dimension and the network width ...

There is an everlasting effort in education to successfully ensure that the intended learning objectives are clearly taught and effectively learnt at the end of the educational cycle. This has been especially difficult in teaching and learning complex sets ...

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain. To tackle these issues, this paper proposes a novel Tes ...

To characterize a physical system to behave as desired, either its underlying governing rules must be known a priori or the system itself be accurately measured. The complexity of full measurements of the system scales with its size. When exposed to real-w ...

This paper presents our approach to predicting future error-related events in a robot-mediated gamified phys- ical training activity for stroke patients. The ability to predict future error under such conditions suggests the existence of distinguishable fe ...

Machine Learning (ML) is on the rise in medicine, promising improved diagnostic, therapeutic and prognostic clinical tools. While these technological innovations are bound to transform health care, they also bring new ethical concerns to the forefront. One ...

We introduce a simulation method for dynamic portfolio valuation and risk management building on machine learning with kernels. We learn the dynamic value process of a portfolio from a finite sample of its cumulative cash flow. The learned value process is ...

The increasing use of ground-source heat pumps (GSHPs) for heating and cooling of buildings raises questions regarding the technical potential of GSHPs and their impact on the temperature in the shallow subsurface. In this paper, we develop a method using ...

Plug-and-play denoisers can be used to perform generic image restoration tasks independent of the degradation type. These methods build on the fact that the Maximum a Posteriori (MAP) optimization can be solved using smaller sub-problems, including a MAP d ...

One-Bit Byzantine-Tolerant Distributed Learning via Over-The-Air Computation

Chat with Graph Search

Metacognition meets AI: Empowering reflective writing with large language models

Source-Free Domain-Invariant Performance Prediction

Reweighting simulated events using machine-learning techniques in the CMS experiment

Technology Legalization and Optimization for Adiabatic Quantum-Flux Parametron

Adversarial Training for Jamming-Robust Channel Estimation in OFDM Systems

Multi-temporal forest monitoring in the Swiss Alps with knowledge-guided deep learning

Federated learning with uncertainty-based client clustering for fleet-wide fault diagnosis

SUPPORTING THE FULL LIFE CYCLE OF RICH OPEN EDUCATIONAL RESOURCES WITH A LEARNING EXPERIENCE PLATFORM

AdaNCA: Neural Cellular Automata as Adaptors for More Robust Vision Transformer

Designed Semiconductor Network Random Lasers

Physics-Informed Machine Learning for Modeling and Control of Dynamical Systems

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Planned, taught, learnt: analysis of transversal skills through curriculum using portfolio

TeSLA: Test-Time Self-Learning With Automatic Adversarial Augmentation

Learning of physical systems: from inference to control

Predictive Analysis of Errors During Robot-Mediated Gamified Training

Towards a pragmatist dealing with algorithmic bias in medical machine learning

Machine learning with kernels for portfolio valuation and risk management

Using Machine Learning to estimate the technical potential of shallow ground-source heat pumps with thermal interference

Image Restoration using Plug-and-Play CNN MAP Denoisers