Publications associées à Real-Time Prediction of Students' Activity Progress and Completion Rates

On the Generalization of Stochastic Gradient Descent with Momentum

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Microtome Publishing2024

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

Topics in statistical physics of high-dimensional machine learning

Hugo Chao Cui

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 ...

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

Real-time implementation of the high-fidelity NBI code RABBIT into the discharge control system of ASDEX Upgrade

Federico Alberto Alfredo Felici, Bernhard Sieglin

For the first time, a real-time capable NBI code, which has a comparable fidelity to the much more computationally expensive Monte Carlo codes such as NUBEAM, has been coupled to the discharge control system of a tokamak. This implementation has been done ...

IOP Publishing Ltd2023

The statistical complexity of early-stopped mirror descent

Varun Kanade, Tomas Vaskevicius

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...

Oxford Univ Press2023

Phenomenological theory of variational quantum ground-state preparation

Ivano Tavernelli, Giuseppe Carleo

The variational approach is a cornerstone of computational physics, considering both conventional and quantum computing computational platforms. The variational quantum eigensolver algorithm aims to prepare the ground state of a Hamiltonian exploiting para ...

Amer Physical Soc2023

Universal and adaptive methods for robust stochastic optimization

Ali Kavis

Within the context of contemporary machine learning problems, efficiency of optimization process depends on the properties of the model and the nature of the data available, which poses a significant problem as the complexity of either increases ad infinit ...

EPFL2023

End-to-End Learning for Stochastic Optimization: A Bayesian Perspective

Daniel Kuhn, Yves Rychener, Tobias Sutter

We develop a principled approach to end-to-end learning in stochastic optimization. First, we show that the standard end-to-end learning algorithm admits a Bayesian interpretation and trains a posterior Bayes action map. Building on the insights of this an ...

2023

Using Machine Learning to Predict Mortality for COVID-19 Patients on Day 0 in the ICU

Sahand Jamal Rahi, Nahal Mansouri

Rationale: Given the expanding number of COVID-19 cases and the potential for new waves of infection, there is an urgent need for early prediction of the severity of the disease in intensive care unit (ICU) patients to optimize treatment strategies.Objecti ...

FRONTIERS MEDIA SA2022

ADAGRAD Avoids Saddle Points

Kimon Antonakopoulos, Xiao Wang

Adaptive first-order methods in optimization are prominent in machine learning and data science owing to their ability to automatically adapt to the landscape of the function being optimized. However, their convergence guarantees are typically stated in te ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2022

Pre-bcc: A novel integrated machine learning framework for predicting mechanical and durability properties of blended cement concrete

Hisham Tarek Mohamed Hafez

Partially replacing ordinary Portland cement (OPC) with low-carbon supplementary cementitious materials (SCMs) in blended cement concrete (BCC) is perceived as the most promising route for sustainable concrete production. Despite having a lower environment ...

ELSEVIER SCI LTD2022

Phase diagram of Stochastic Gradient Descent in high-dimensional two-layer neural networks

Florent Gérard Krzakala, Lenka Zdeborová, Bruno Loureiro, Bruno Loureiro, Ludovic Théo Stephan

Despite the non-convex optimization landscape, over-parametrized shallow networks are able to achieve global convergence under gradient descent. The picture can be radically different for narrow net-works, which tend to get stuck in badly-generalizing loca ...

2022

Optical fibre based quench detection in HTS applications using machine learning classifiers

Bertrand Dutoit, Bertrand Dutoit, Arooj Akbar, Nicolo' Riva

A Mach-Zehnder Interferometer (MZI) based optical fibre sensing technique, developed and patented by EPFL, is an efficient and economical way to detect hotspots in High Temperature Superconductor (HTS) applications. Due to the MZI sensitivity being a compo ...

Elsevier2022

Physics-enhanced machine learning with symmetry-adapted and long-range representations

Andrea Grisafi

Theoretical and computational approaches to the study of materials and molecules have, over the last few decades, progressed at an exponential rate. Yet, the possibility of producing numerical predictions that are on par with experimental measurements is t ...

EPFL2021

Critical Parameters for Scalable Distributed Learning with Large Batches and Asynchronous Updates

Martin Jaggi, Sebastian Urban Stich, Amirkeivan Mohtashami

It has been experimentally observed that the efficiency of distributed training with stochastic gradient (SGD) depends decisively on the batch size and—in asynchronous implementations—on the gradient staleness. Especially, it has been observed that the spe ...

MICROTOME PUBLISHING2021

Rapid Noninvasive Skin Monitoring by Surface Mass Recording and Data Learning

Hubert Girault, Horst Pick, Natalia Gasilova, Andreas Stephan Lesch, Tzu-En Lin, Yingdi Zhu, Milica Jovic

Skin problems are often overlooked due to a lack of robust and patient-friendly monitoring tools. Herein, we report a rapid, noninvasive, and high-throughput analytical chemical methodology, aiming at real-time monitoring of skin conditions and early detec ...

2021

Differential Privacy and Byzantine Resilience in SGD: Do They Add Up?

Rachid Guerraoui, Sébastien Louis Alexandre Rouault, John Stephan, Nirupam Gupta, Rafaël Benjamin Pinot

This paper addresses the problem of combining Byzantine resilience with privacy in machine learning (ML). Specifically, we study if a distributed implementation of the renowned Stochastic Gradient Descent (SGD) learning algorithm is feasible with both diff ...

ASSOC COMPUTING MACHINERY2021

Adaptive Social Learning

Ali H. Sayed, Virginia Bordignon

This work proposes a novel strategy for social learning by introducing the critical feature of adaptation. In social learning, several distributed agents update continually their belief about a phenomenon of interest through: i) direct observation of strea ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

Distributed Learning in Non-Convex Environments-Part I: Agreement at a Linear Rate

Ali H. Sayed, Stefan Vlaski

Driven by the need to solve increasingly complex optimization problems in signal processing and machine learning, there has been increasing interest in understanding the behavior of gradient-descent algorithms in non-convex environments. Most available wor ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021