Bayes-optimal Learning of Deep Random Networks of Extensive-width

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.

Accurately estimating model performance poses a significant challenge, particularly in scenarios where the source and target domains follow different data distributions. Most existing performance prediction methods heavily rely on the source data in their ...

Adiabatic quantum-flux parametron (AQFP) is an energy-efficient superconducting technology. Before physical design can be performed, AQFP technology mapping involves not only mapping logic into supported gate types but also legalizing the circuit to fulfil ...

Reflective writing is known as a useful method in learning sciences to improve the metacognitive skills of students. However, students struggle to structure their reflections properly, limiting the possible learning gains. Previous works in educational tec ...

Data analyses in particle physics rely on an accurate simulation of particle collisions and a detailed simulation of detector effects to extract physics knowledge from the recorded data. Event generators together with a geant-based simulation of the detect ...

This study investigates the impact of protracted humanitarian crises on urban development in Bol, a city in Chad’s Lake region, with a focus on spatial transformations and planning implications. The purpose is to assess how displacement-driven urbanization ...

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

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 ...

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 ...

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 ...

Herein, machine learning (ML) models using multiple linear regression (MLR), support vector regression (SVR), random forest (RF) and artificial neural network (ANN) are developed and compared to predict the output features viz. specific capacitance (Csp), ...

Throughout history, the pace of knowledge and information sharing has evolved into an unthinkable speed and media. At the end of the XVII century, in Europe, the ideas that would shape the "Age of Enlightenment" were slowly being developed in coffeehouses, ...

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 ...

This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...

Catastrophic overfitting (CO) in single-step adversarial training (AT) results in abrupt drops in the adversarial test accuracy (even down to 0%). For models trained with multi-step AT, it has been observed that the loss function behaves locally linearly w ...

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 ...

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 ...

The field of biometrics, and especially face recognition, has seen a wide-spread adoption the last few years, from access control on personal devices such as phones and laptops, to automated border controls such as in airports. The stakes are increasingly ...

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 ...

We present a finite elements-neural network approach for the numerical approximation of parametric partial differential equations. The algorithm generates training data from finite element simulations, and uses a data -driven (supervised) feedforward neura ...

Bayes-optimal Learning of Deep Random Networks of Extensive-width

Chat with Graph Search

Source-Free Domain-Invariant Performance Prediction

Deep-Learning Reconstruction for 7T MP2RAGE and SPACE MRI: Improving Image Quality at High Acceleration Factors

Technology Legalization and Optimization for Adiabatic Quantum-Flux Parametron

Metacognition meets AI: Empowering reflective writing with large language models

Reweighting simulated events using machine-learning techniques in the CMS experiment

Spatiotemporal dynamics and humanitarian crisis in Bol (Chad): Satellite imagery analysis

Random matrix methods for high-dimensional machine learning models

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

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

Topics in statistical physics of high-dimensional machine learning

Machine learning models for prediction of electrochemical properties in supercapacitor electrodes using MXene and graphene nanoplatelets

Machine Learning for Modeling Stock Returns

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

High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization

Efficient local linearity regularization to overcome catastrophic overfitting

Deep Learning Theory Through the Lens of Diagonal Linear Networks

Understanding generalization and robustness in modern deep learning

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

Safe Deep Neural Networks

Error assessment of an adaptive finite elements-neural networks method for an elliptic parametric PDE