Publications related to System and method for privacy-preserving distributed training of machine learning models on distributed datasets

Related publications (32)

Good enough: Intermediate complexity atmospheric models improve the representation of processes affecting seasonal snow

Snow plays a crucial role in processes regulating ecosystems, the climate, and human development. Mountain snowpack in particular has great relevance for downstream communities. Knowledge about the distribution and properties of the snowpack thus help in p ...

EPFL2024

Few-shot Learning for Efficient and Effective Machine Learning Model Adaptation

Arnout Jan J Devos

Machine learning (ML) enables artificial intelligent (AI) agents to learn autonomously from data obtained from their environment to perform tasks. Modern ML systems have proven to be extremely effective, reaching or even exceeding human intelligence. Altho ...

EPFL2024

Network time series forecasting in photovoltaics power production

Jelena Simeunovic

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 ...

EPFL2024

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Anastasiia Koloskova

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

EPFL2024

Robust machine learning for neuroscientific inference

Steffen Schneider

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 ...

EPFL2024

Understanding generalization and robustness in modern deep learning

Maksym Andriushchenko

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

EPFL2024

Urban boundary-layer flows in complex terrain: Dynamic interactions during a hot and dry summer season in Phoenix, Arizona

Aldo Brandi

Anthropogenic modification of natural landscapes to urban environments impacts land-atmosphere interactions in the boundary layer. Ample research has demonstrated the effect of such landscape transitions on development of the urban heat island (UHI), but c ...

Wiley2024

Meta-learning to address diverse Earth observation problems across resolutions

Devis Tuia, Marc Conrad Russwurm, Benjamin Alexander Kellenberger

Earth scientists study a variety of problems with remote sensing data, but they most often consider them in isolation from each other, which limits information flows across disciplines. In this work, we present METEOR, a meta-learning methodology for Earth ...

Springernature2024

Secure and Efficient Cryptographic Algorithms in a Quantum World

Loïs Evan Huguenin-Dumittan

Since the advent of internet and mass communication, two public-key cryptographic algorithms have shared the monopoly of data encryption and authentication: Diffie-Hellman and RSA. However, in the last few years, progress made in quantum physics -- and mo ...

EPFL2024

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

Machine learning-aided generative molecular design

Philippe Schwaller, Jeff Guo

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 ...

Nature Portfolio2024

Random matrix methods for high-dimensional machine learning models

Antoine Philippe Michel Bodin

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

EPFL2024

Untangling the influence of Antarctic and Southern Ocean life on clouds

Julia Schmale, Hélène Paule Angot, Markus Frey

Polar environments are among the fastest changing regions on the planet. It is a crucial time to make significant improvements in our understanding of how ocean and ice biogeochemical processes are linked with the atmosphere. This is especially true over A ...

2023

Improved extended-range prediction of persistent stratospheric perturbations using machine learning

Guillaume Romain Obozinski, Raphaël Gérard Théodore Michel Marie de Deloÿe et Fourcade de Fondeville

On average every 2 years, the stratospheric polar vortex exhibits extreme perturbations known as sudden stratospheric warmings (SSWs). The impact of these events is not limited to the stratosphere: but they can also influence the weather at the surface of ...

Copernicus Gesellschaft Mbh2023

RaFSIP: Parameterizing ice multiplication in models using a machine learning approach

Athanasios Nenes, Paraskevi Georgakaki

Accurately representing mixed-phase clouds (MPCs) in global climate models (GCMs) is critical for capturing climate sensitivity and Arctic amplification. Secondary ice production (SIP), can significantly increase ice crystal number concentration (ICNC) in ...

2024

Communication-efficient distributed training of machine learning models

Thijs Vogels

In this thesis, we explore techniques for addressing the communication bottleneck in data-parallel distributed training of deep learning models. We investigate algorithms that either reduce the size of the messages that are exchanged between workers, or th ...

EPFL2023

Privacy-preserving federated neural network training and inference

Sinem Sav

Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data silos. Sharing, transferring, and centralizing the data from silos, however, is difficult due to current privacy regulations (e.g., H ...

EPFL2023

Snow transport in extreme environments: from small to large scale modeling

Daniela Brito Melo

The cold regions on Earth, such as the polar and high mountain regions, are snow covered for at least a part of the year. These snow-covered surfaces are highly dynamic, particularly under the influence of strong winds. The aeolian or wind-driven transport ...

EPFL2023

Deep Learning Generalization with Limited and Noisy Labels

Mahsa Forouzesh

Deep neural networks have become ubiquitous in today's technological landscape, finding their way in a vast array of applications. Deep supervised learning, which relies on large labeled datasets, has been particularly successful in areas such as image cla ...

EPFL2023

Breaking the Curse of Dimensionality in Deep Neural Networks by Learning Invariant Representations

Leonardo Petrini

Artificial intelligence, particularly the subfield of machine learning, has seen a paradigm shift towards data-driven models that learn from and adapt to data. This has resulted in unprecedented advancements in various domains such as natural language proc ...

EPFL2023