Learning Ridge Functions With Randomized Sampling In High Dimensions

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Depth sensing is essential for intelligent computer vision applications, but it often suffers from low range precision and spatial resolution. To address this problem, we propose a novel framework that combines non-uniform sampling and reconstruction based ...

The recent geopolitical conflicts in Europe have underscored the vulnerability of the current energy system to the volatility of energy carrier prices. In the prospect of defining robust energy systems ensuring sustainable energy supply in the future, the ...

Surrogate-based optimization is widely used for aerodynamic shape optimization, and its effectiveness depends on representative sampling of the design space. However, traditional sampling methods are hard-pressed to effectively sample high-dimensional desi ...

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an ...

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 reported rate of the occurrence of unilateral spatial neglect (USN) is highly variable likely due to the lack of validity and low sensitivity of classical tools used to assess it. Virtual reality (VR) assessments try to overcome these limitations by pr ...

The Dark Energy Spectroscopic Instrument (DESI) was designed to conduct a survey covering 14,000 deg(2) over 5 yr to constrain the cosmic expansion history through precise measurements of baryon acoustic oscillations (BAO). The scientific program for DESI ...

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

The remarkable ability of deep learning (DL) models to approximate high-dimensional functions from samples has sparked a revolution across numerous scientific and industrial domains that cannot be overemphasized. In sensitive applications, the good perform ...

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 ...

Mitigating the energy requirements of artificial intelligence requires novel physical substrates for computation. Phononic metamaterials have vanishingly low power dissipation and hence are a prime candidate for green, always-on computers. However, their u ...

Given the patchy nature of gas plumes and the slow response of conventional gas sensors, the use of mobile robots for Gas Source Localization (GSL) tasks presents significant challenges. These aspects increase the difficulties in obtaining gas measurements ...

The COVID-19 pandemic has led to a significant increase in working from home worldwide, making the workfrom-home (WFH) setting a crucial context for studying the influence of indoor environmental quality (IEQ) on workers' well-being and productivity. A nar ...

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 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 ...

We present Epidemic Learning ( EL ), a simple yet powerful decentralized learning (DL) algorithm that leverages changing communication topologies to achieve faster model convergence compared to conventional DL approaches. At each round of EL, each node sen ...

Bioaerosols are emitted from various sources into the indoor environment and can positively and negatively impact human health. Humans are the major source of bioaerosol emissions indoors, specifically for bacteria. However, efficient sampling to guarantee ...

The recent geopolitical conflicts in Europe highlighted the sensibility of the current energy system to the volatility of energy carrier prices. In the prospect of defining robust energy system configurations to ensure energy supply stability, it is necess ...

Years of a fierce competition have naturally selected the fittest deep learning algorithms. Yet, although these models work well in practice, we still lack a proper characterization of why they do so. This poses serious questions about the robustness, trus ...

Domain generalization (DG) aims to learn a model from multiple training (i.e., source) domains that can generalize well to the unseen test (i.e., target) data coming from a different distribution. Single domain generalization (SingleDG) has recently emerge ...

Learning Ridge Functions With Randomized Sampling In High Dimensions

Chattez avec Graph Search

High-Quality Reconstruction of Depth Maps From Graph-Based Non-Uniform Sampling

Identification of typical district configurations: A two-step global sensitivity analysis framework

DiffAirfoil: An Efficient Novel Airfoil Sampler Based on Latent Space Diffusion Model for Aerodynamic Shape Optimization

Gibbs sampling the posterior of neural networks

Performing and Detecting Backdoor Attacks on Face Recognition Algorithms

An immersive virtual reality tool for assessing left and right unilateral spatial neglect

Validation of the Scientific Program for the Dark Energy Spectroscopic Instrument

Graph generative deep learning models with an application to circuit topologies

Towards Trustworthy Deep Learning for Image Reconstruction

On the Generalization of Stochastic Gradient Descent with Momentum

In-Sensor Passive Speech Classification with Phononic Metamaterials

Sense in Motion with Belief Clustering: Efficient Gas Source Localization with Mobile Robots

A state-of-the-art, systematic review of indoor environmental quality studies in work-from-home settings

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

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

Epidemic Learning: Boosting Decentralized Learning with Randomized Communication

Comparison of two methods for bioaerosol sampling and characterization in a low-biomass chamber environment

Identification of typical district configurations: A two-step global sensitivity analysis framework

The inductive bias of deep learning: Connecting weights and functions

Center-aware Adversarial Augmentation for Single Domain Generalization