Publications associées à Stochastic Spectral Descent for Discrete Graphical Models

Publications associées (40)

Human interpretable structure-property relationships in chemistry using explainable machine learning and large language models

Philippe Schwaller, Geemi Piyathma Wellawatte

Explainable Artificial Intelligence (XAI) is an emerging field in AI that aims to address the opaque nature of machine learning models. Furthermore, it has been shown that XAI can be used to extract input-output relationships, making them a useful tool in ...

NATURE PORTFOLIO2025

Leaf Level Ash Dieback Disease Detection and Online Severity Estimation With UAVs

Mirko Kovac

Ash dieback, caused by the fungal pathogen Hymenoscyphus fraxineus, is devastating ash tree populations across U.K. and Europe, with projections indicating that up to 80% of ash trees may die as a result of the disease. The extensive loss of this keystone ...

2025

Boosting Protein Graph Representations through Static-Dynamic Fusion

Pengkang Guo, Pierre Vandergheynst, Bruno Emanuel Ferreira De Sousa Correia, Daniel Probst

Machine learning for protein modeling faces significant challenges due to proteins' inherently dynamic nature, yet most graph-based machine learning methods rely solely on static structural information. Recently, the growing availability of molecular dynam ...

2025

Characterization of Machine Learning-Based Surrogate Models of Neural Activation Under Electrical Stimulation

Silvestro Micera, Simone Romeni

Bioelectromagnetics published by Wiley Periodicals LLC on behalf of Bioelectromagnetics Society.Electrical stimulation of peripheral nerves via implanted electrodes has been shown to be a promising approach to restore sensation, movement, and autonomic fun ...

2025

A clinical road map for single-cell omics

Grégoire Courtine, Jocelyne Bloch

In a matter of years, single-cell omics has matured from a pioneering technique employed by just a handful of specialized laboratories to become a ubiquitous feature of biological research and a key driver of scientific discovery. The widespread adoption a ...

2025

Efficient Continual Finite-Sum Minimization

Ioannis Mavrothalassitis, Volkan Cevher, Leello Tadesse Dadi, Efstratios Panteleimon Skoulakis

Given a sequence of functions

f_1,\ldots,f_n

with

f_i:\mathcal{D}\mapsto \mathbb{R}

, finite-sum minimization seeks a point

{x}^\star \in \mathcal{D}

minimizing

\sum_{j=1}^nf_j(x)/n

. In this work, we propose a key twist into the finite-sum minimizat ...

2024

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

Geometric Learning: Leveraging differential geometry for learning and control

Bernardo Fichera

In this thesis, we concentrate on advancing high-level behavioral control policies for robotic systems within the framework of Dynamical Systems (DS). Throughout the course of this research, a unifying thread weaving through diverse fields emerges, and tha ...

EPFL2024

On the Generalization of Stochastic Gradient Descent with Momentum

Volkan Cevher, Kimon Antonakopoulos

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

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Nicolas Henri Bernard Flammarion, Scott William Pesme, Hristo Georgiev Papazov

In this work, we investigate the effect of momentum on the optimisation trajectory of gradient descent. We leverage a continuous-time approach in the analysis of momentum gradient descent with step size

\gamma

and momentum parameter

\beta

that allows u ...

2024

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Scott William Pesme

In this PhD manuscript, we explore optimisation phenomena which occur in complex neural networks through the lens of

2

-layer diagonal linear networks. This rudimentary architecture, which consists of a two layer feedforward linear network with a diagonal ...

EPFL2024

Anomalous and Chern topological waves in hyperbolic networks

Romain Christophe Rémy Fleury, Haoye Qin, Zhe Zhang, Aleksi Antoine Bossart, Zhechen Zhang

Hyperbolic lattices are a new type of synthetic materials based on regular tessellations in non-Euclidean spaces with constant negative curvature. While so far, there has been several theoretical investigations of hyperbolic topological media, experimental ...

Nature Research2024

Revisiting Character-level Adversarial Attacks for Language Models

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Yongtao Wu, Elias Abad Rocamora

Adversarial attacks in Natural Language Processing apply perturbations in the character or token levels. Token-level attacks, gaining prominence for their use of gradient-based methods, are susceptible to altering sentence semantics, leading to invalid adv ...

2024

JPEG AI: The First International Standard for Image Coding Based on an End-to-End Learning-Based Approach

Touradj Ebrahimi

In 2019, the JPEG Standardization Committee initiated JPEG AI to define the first image coding specifications, taking advantage of an end-to-end learning-based coding approach. The JPEG AI specifications will be soon published as an international standard ...

2024

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

Statistical Inference for Inverse Problems: From Sparsity-Based Methods to Neural Networks

Pakshal Narendra Bohra

In inverse problems, the task is to reconstruct an unknown signal from its possibly noise-corrupted measurements. Penalized-likelihood-based estimation and Bayesian estimation are two powerful statistical paradigms for the resolution of such problems. They ...

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

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

Residual-based attention in physics-informed neural networks

Nikolaos Stergiopoulos, Sokratis Anagnostopoulos

Driven by the need for more efficient and seamless integration of physical models and data, physics -informed neural networks (PINNs) have seen a surge of interest in recent years. However, ensuring the reliability of their convergence and accuracy remains ...

Elsevier Science Sa2024

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