Publications associées à Learning Algorithms in the Limit

Publications associées (20)

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases

Pascal Fua, Mathieu Salzmann, Shaifali Parashar, Jan Bednarík

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed su ...

2025

An Analysis of Model Robustness across Concurrent Distribution Shifts

Myeongho Jeon, Shuqing Teresa Yeo

Machine learning models, meticulously optimized for source data, often fail to predict target data when faced with distribution shifts (DSs). Previous benchmarking studies, though extensive, have mainly focused on simple DSs. Recognizing that DSs often occ ...

2025

Preparing Teachers for an Equitable AI Integration in Education

Francesco Mondada, Victoria Abou Khalil, Valentina Ferraioli

This workshop proposal aims to inform the design of teacher training on equity in the use and teaching of AI. AI is transforming both teaching practices and student learning environments and learning content. Teachers are increasingly using AI tools for co ...

Springer Science and Business Media Deutschland GmbH2025

Advances in Algorithms for Sampling, Optimization and Inference in Disordered Systems

Giovanni Piccioli

This thesis focuses on the development of advanced algorithmic techniques, primarily Markov Chain Monte Carlo (MCMC) methods, and message passing algorithms, to tackle high-dimensional optimization and inference problems. The algorithms used have a probabi ...

EPFL2024

Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations

Volkan Cevher, Grigorios Chrysos, Igor Krawczuk, Justin Samuel Deschenaux

Denoising Diffusion Probabilistic Models (DDPMs) exhibit remarkable capabilities in image generation, with studies suggesting that they can generalize by composing latent factors learned from the training data. In this work, we go further and study DDPMs t ...

2024

Neural decoding and feature selection methods for closed-loop control of avoidance behavior

Mahsa Shoaran, Jinhan Liu

Objective. Many psychiatric disorders involve excessive avoidant or defensive behavior, such as avoidance in anxiety and trauma disorders or defensive rituals in obsessive-compulsive disorders. Developing algorithms to predict these behaviors from local fi ...

IOP Publishing2024

Optimal performance of Graph Convolutional Networks on the Contextual Stochastic Block Model

Patrick Thiran, Guillaume Cyprien Dalle

For Graph Neural Networks, oversmoothing denotes the homogenization of vertex embeddings as the number of layers increases. To better understand this phenomenon, we study community detection with a linearized Graph Convolutional Network on the Contextual S ...

2024

Nissl_1, Raw images for Machine learning for histological annotation and quantification of cortical layers

Julie Meystre

This dataset contains images (TIFF image data) of brain juvenile rats Wistar Han (P14) scanned immunostained slides by using an automated slide scanner (Olympus, VS120-L100, GER) equipped with a UPLSAPO 20x/0.75 air objective (Olympus, GER) and a Pike F5 ...

Zenodo2024

Ground-based image deconvolution with Swin Transformer UNet

Frédéric Courbin, Pascale Jablonka, Utsav Akhaury

Aims. As ground-based all-sky astronomical surveys will gather millions of images in the coming years, a critical requirement emerges for the development of fast deconvolution algorithms capable of efficiently improving the spatial resolution of these imag ...

2024

Multi-Label Generalized Zero Shot Chest X-Ray Classification by Combining Image-Text Information With Feature Disentanglement

Seyedbehzad Bozorgtabar

In fully supervised learning-based medical image classification, the robustness of a trained model depends on its exposure to various disease classes. Generalized Zero Shot Learning (GZSL) aims to predict both seen and novel unseen classes. While most GZSL ...

Institute of Electrical and Electronics Engineers2024

Learning Outcomes, Benefits, and Challenges of International Research Experiences for Students (IRES): An Exploratory Study of an IRES Program in China

Yousef Jalali

Despite the increasing number of international programs targeting students’ learning of research and intercultural skills, there has been limited holistic investigation of students’ experiences employing both qualitative and quantitative methods. In this s ...

University of Rhode Island2024

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields: Processed data and trained models

Mathieu Salzmann, Alexander Mathis, Chen Zhao, Haozhe Qi

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields, CVPR 2024 Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis. Affiliation: EPFL Date: June, 2024 Link to the CVPR article: https://openaccess.thecvf.com/conte ...

Zenodo2024

Accelerated design of nickel-cobalt based catalysts for CO2 hydrogenation with human-in-the-loop active machine learning

Andreas Züttel, Yasemen Kuddusi

Thermo-catalytic conversion of CO2 into more valuable compounds, such as methane, is an attractive strategy for energy storage in chemical bonds and creating a carbon-based circular economy. However, designing heterogeneous catalysts remains a challenging, ...

2024

Learning sparse features can lead to overfitting in neural networks

Matthieu Wyart, Leonardo Petrini, Francesco Cagnetta

It is widely believed that the success of deep networks lies in their ability to learn a meaningful representation of the features of the data. Yet, understanding when and how this feature learning improves performance remains a challenge. For example, it ...

Iop Publishing Ltd2023

Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors

Matthias Rottmann

The majority of uncertainty quantification methods for deep object detectors are based on the network output, such as sampling strategies like Monte-Carlo dropout or deep ensembles with straight-forward transfers to object detection. Here, we study gradien ...

IEEE Computer Soc2023

The Esntorch Library: Efficient Implementation of Transformer-based Echo State Networks

Mathieu Louis Rochat

Transformer-based models have revolutionized NLP. But in general, these models are highly resource consuming. Based on this consideration, several reservoir computing approaches to NLP have shown promising results. In this context, we propose EsnTorch, a l ...

Springer Nature2023

Theoretical characterization of uncertainty in high-dimensional linear classification

Lenka Zdeborová, Florent Gérard Krzakala, Lucas Andry Clarte

Being able to reliably assess not only the accuracy but also the uncertainty of models' predictions is an important endeavor in modern machine learning. Even if the model generating the data and labels is known, computing the intrinsic uncertainty after le ...

IOP Publishing Ltd2023

Gaussian Process Regression for Seismic Fragility Assessment: Application to Non-Engineered Residential Buildings in Indonesia

Andri Setiawan

Indonesia is located in a high-seismic-risk region with a significant number of non-engineered houses, which typically have a higher risk during earthquakes. Due to the wide variety of differences even among parameters within one building typology, it is d ...

2023

Data-driven control of room temperature and bidirectional EV charging using deep reinforcement learning: Simulations and experiments

Melanie Nicole Zeilinger, Loris Di Natale

2022

Spatio-Temporal Graph Neural Networks for Multi-Site PV Power Forecasting

Jelena Simeunovic

Accurate forecasting of solar power generation with fine temporal and spatial resolution is vital for the operation of the power grid. However, state-of-the-art approaches that combine machinelearning with numerical weather predictions (NWP) have coarse re ...

2022