From Discrete Measurements to Bounded Gradient Estimates: A Look at Some Regularizing Structures

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.

Deep neural networks often fail to generalize when deployed in dynamic and unpredictable real-world environments, where data distributions at test time can differ significantly from those encountered during training. Since simulating all possible distribut ...

This study investigates how landing stability on slopestyle jumps is affected by jump design and the athletes' aerial maneuvers, in World Cup skiers and snowboarders. The data were recorded on rollover jumps from a World Cup Slopestyle competition using a ...

Sharpness-aware minimization (SAM) has been shown to improve the generalization of neural networks. However, each SAM update requires sequentially computing two gradients, effectively doubling the per-iteration cost compared to base optimizers like SGD. We ...

What training should engineering students receive to enable them to contribute to reducing bias, discrimination and the persistent lack of diversity in engineering? Collaboration is central to professional engineering work and, consequently, teamwork and g ...

Neurotechnology applies methods and devices to mitigate the burden of neurological and mental disorders. In particular, neural interfaces establish a long-term, seamless, symbiotic integration between implants and neural tissue. Materials play a pivotal ro ...

Tepotinib is approved for the treatment of patients with non-small-cell lung cancer harboring MET exon 14 skipping alterations. While edema is the most prevalent adverse event (AE) and a known class effect of MET inhibitors including tepotinib, there is st ...

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

Despite the growing interest in emotions in engineering education, empirical research on incorporating them into engineering ethics education is limited. Therefore, we designed this experimental study to assess how different methods for integrating compass ...

The variational approach is a cornerstone of computational physics, considering both conventional and quantum computing computational platforms. The variational quantum eigensolver algorithm aims to prepare the ground state of a Hamiltonian exploiting para ...

Being able to work effectively in a team is a vital professional skill but how do students in different disciplines, engineering and hospitality, display their emotions when working together? We investigated their self-reported use of emotional labour stra ...

Multiple drug concentrations concurrent detection and quantification based on electrochemical sensors are of great importance for therapeutic drug monitoring (TDM) and the development of personalized therapy. Cyclic voltammogram (CV) results obtained by el ...

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 ...

Lack of incentives mainly explains why the implementation of novel methods and technologies in bridge engineering practice is generally postponed by the engineering community despite the urgent need to advance also bridge engineering to meet the objectives ...

Smart contracts have emerged as the most promising foundations for applications of the blockchain technology. Even though smart contracts are expected to serve as the backbone of the next-generation web, they have several limitations that hinder their wide ...

Team projects are an integral part of the student learning experience. However, emotions can significantly affect student performance during team projects. Students use different emotion regulation strategies, such as surface-acting (emotive dissonance) an ...

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 ...

Control design for robotic systems is complex and often requires solving an optimization to follow a trajectory accurately. Online optimization approaches like Model Predictive Control (MPC) have been shown to achieve great tracking performance, but requir ...

Borrowing some quotes from Harper Lee's novel "To Kill A Mockingbird" to help frame our manuscript, we discuss methods to profile local proteomes. We initially focus on chemical biology regimens that function in live organisms and use reactive biotin speci ...

We propose an adaptive quantum algorithm to prepare accurate variational time evolved wave functions. The method is based on the projected variational quantum dynamics (pVQD) algorithm, that performs a global optimization with linear scaling in the number ...

Rectified-linear-unit (ReLU) neural networks, which play a prominent role in deep learning, generate continuous and piecewise-linear (CPWL) functions. While they provide a powerful parametric representation, the mapping between the parameter and function s ...

From Discrete Measurements to Bounded Gradient Estimates: A Look at Some Regularizing Structures

Chattez avec Graph Search

Adaptive Test-Time Learning Under Domain Shift: From Augmentation to Prolonged Adaptation

Equivalent Fall Height and Aerial Maneuver Difficulty Both Influence Landing Stability on World Cup Slopestyle Rollover Jumps For Skiers and Snowboarders

SAMPa: Sharpness-aware Minimization Parallelized

Educating Engineering Students to Address Bias and Discrimination Within Their Project Teams

Engineering Materials for Neurotechnology

Explainable machine learning prediction of edema adverse events in patients treated with tepotinib

Robust Collaborative Learning with Linear Gradient Overhead

The impact of different methods of increasing the intensity of compassion in engineering ethics cases

Phenomenological theory of variational quantum ground-state preparation

“But of course i’m going to look happy” or “He needed to know I was angry”? Comparing use of emotional labour in teamwork in engineering and hospitality students

Automatic simulation of electrochemical sensors by machine learning for drugs quantification

Leveraging Continuous Time to Understand Momentum When Training Diagonal Linear Networks

Making Bridges Sustainable

Towards General-Purpose Decentralized Computing with Permissionless Extensibility

Emotional labor experienced in team-projects: A comparison of engineering and hospitality students

Understanding generalization and robustness in modern deep learning

Training Efficient Controllers via Analytic Policy Gradient

Climbing into their Skin to Understand Contextual Protein-Protein Associations and Localizations: Functional Investigations in Transgenic Live Model Organisms

Adaptive projected variational quantum dynamics

Stable parameterization of continuous and piecewise-linear functions