On double-descent in uncertainty quantification in overparametrized models

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

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 ...

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 ...

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 ...

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 ...

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 ...

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

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 ...

The simplification of neural network models is described. For example, a method for simplifying a neural network model includes providing the neural network model to be simplified, defining a first temporal filter for the conveyance of input from a neuron ...

Turning pass-through network architectures into iterative ones, which use their own output as input, is a well-known approach for boosting performance. In this paper, we argue that such architectures offer an additional benefit: The convergence rate of the ...

The upcoming Square Kilometre Array Observatory will produce images of neutral hydrogen distribution during the epoch of reionization by observing the corresponding 21-cm signal. However, the 21-cm signal will be subject to instrumental limitations such as ...

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

As a follow-up to the CEA-EPFL PETALE experimental program on stainless steel nuclear data, the EPFL initiated an open-loop pile-oscillation experimental program in the CROCUS reactor: BLOOM. A reproduction of the critical experiments of PETALE, the progra ...

Proprioception tells the brain the state of the body based on distributed sensors in the body. However, the principles that govern proprioceptive processing from those distributed sensors are poorly understood. Here, we employ a task-driven neural network ...

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 ...

Efficient sampling and approximation of Boltzmann distributions involving large sets of binary variables, or spins, are pivotal in diverse scientific fields even beyond physics. Recent advances in generative neural networks have significantly impacted this ...

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 ...

The performance of machine learning algorithms is conditioned by the availability of training datasets, which is especially true for the field of nondestructive evaluation. Here we propose one reconfigurable specimen instead of numerous reference specimens ...

Operators from various industries have been pushing the adoption of wireless sensing nodes for industrial monitoring, and such efforts have produced sizeable condition monitoring datasets that can be used to build diagnosis algorithms capable of warning ma ...

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 ...

The capabilities of deep learning systems have advanced much faster than our ability to understand them. Whilst the gains from deep neural networks (DNNs) are significant, they are accompanied by a growing risk and gravity of a bad outcome. This is troubli ...

On double-descent in uncertainty quantification in overparametrized models

Chat with Graph Search

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

Boosting Protein Graph Representations through Static-Dynamic Fusion

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

A clinical road map for single-cell omics

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

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

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

Simplification of spiking neural network models

Enabling Uncertainty Estimation in Iterative Neural Networks

Deep learning approach for identification of H II regions during reionization in 21-cm observations - II. Foreground contamination

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Design of an Open-Loop Pile-Oscillation Program in the CROCUS Reactor

Task-driven neural network models predict neural dynamics of proprioception: Neural network model weights

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Sparse autoregressive neural networks for classical spin systems

Efficient Continual Finite-Sum Minimization

Reduced Training Data for Laser Ultrasound Signal Interpretation by Neural Networks

Federated learning with uncertainty-based client clustering for fleet-wide fault diagnosis

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

Safe Deep Neural Networks