Publications associées à Probabilistic methods for neural combinatorial optimization

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

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

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

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

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Yi Zhang, Wenlong Liao, Zhe Yang

Recently, remarkable progress has been made in the application of machine learning (ML) techniques (e.g., neural networks) to transformer fault diagnosis. However, the diagnostic processes employed by these techniques often suffer from a lack of interpreta ...

Piscataway2024

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 ...

Brookline2024

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

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

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

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

ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees

Daniel Gatica-Perez, Sina Sajadmanesh

Graph Neural Networks (GNNs) have become a popular tool for learning on graphs, but their widespread use raises privacy concerns as graph data can contain personal or sensitive information. Differentially private GNN models have been recently proposed to p ...

Assoc Computing Machinery2024

Machine Learning Security Against Data Poisoning: Are We There Yet?

Kathrin Grosse

Poisoning attacks compromise the training data utilized to train machine learning (ML) models, diminishing their overall performance, manipulating predictions on specific test samples, and implanting backdoors. This article thoughtfully explores these atta ...

Ieee Computer Soc2024

Probabilistic methods for neural combinatorial optimization

Graph Chatbot

Chattez avec Graph Search

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Topics in statistical physics of high-dimensional machine learning

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

On the Generalization of Stochastic Gradient Descent with Momentum

Machine learning-aided generative molecular design

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees

Machine Learning Security Against Data Poisoning: Are We There Yet?

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Machine learning-aided generative molecular design

On the Generalization of Stochastic Gradient Descent with Momentum

ProGAP: Progressive Graph Neural Networks with Differential Privacy Guarantees

Machine Learning Security Against Data Poisoning: Are We There Yet?

Topics in statistical physics of high-dimensional machine learning

Explainable Fault Diagnosis of Oil-Immersed Transformers: A Glass-Box Model

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks