Concept

Loss function

Related publications (32)

Extensions of Peer Prediction Incentive Mechanisms

As large, data-driven artificial intelligence models become ubiquitous, guaranteeing high data quality is imperative for constructing models. Crowdsourcing, community sensing, and data filtering have long been the standard approaches to guaranteeing or imp ...

EPFL2024

Stability: a search for structure

Wouter Jongeneel

In this thesis we study stability from several viewpoints. After covering the practical importance, the rich history and the ever-growing list of manifestations of stability, we study the following. (i) (Statistical identification of stable dynamical syste ...

EPFL2024

Efficient local linearity regularization to overcome catastrophic overfitting

Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora

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 ...

2024

Random matrix methods for high-dimensional machine learning models

Antoine Philippe Michel Bodin

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 ...

EPFL2024

Optimal regimes for algorithm-assisted human decision-making

Mats Julius Stensrud, Aaron Leor Sarvet

We consider optimal regimes for algorithm-assisted human decision-making. Such regimes are decision functions of measured pre-treatment variables and, by leveraging natural treatment values, enjoy a superoptimality property whereby they are guaranteed to o ...

2024

Less Conservatism, Stronger Robustness: Iterative Robust Gain-Scheduled Path Following Control of Autonomous Bus With Unstructured and Changing Dynamics

Denis Gillet, Man Shi, Jianwei Li

Path-following control is a critical technology for autonomous vehicles. However, time-varying parameters, parametric uncertainties, external disturbances, and complicated environments significantly challenge autonomous driving. We propose an iterative rob ...

Ieee-Inst Electrical Electronics Engineers Inc2024

Fair real-time control of energy storage systems in active distribution networks in the presence of uncertainties

Plouton Grammatikos

The thesis explores the issue of fairness in the real-time (RT) control of battery energy storage systems (BESSs) hosted in active distribution networks (ADNs) in the presence of uncertainties by proposing and experimentally validating appropriate control ...

EPFL2024

Data-driven modeling of beam loss in the LHC

Tatiana Pieloni, Ekaterina Krymova, Michael Schenk, Loïc Thomas Davies Coyle

In the Large Hadron Collider, the beam losses are continuously measured for machine protection. By design, most of the particle losses occur in the collimation system, where the particles with high oscilla-tion amplitudes or large momentum error are scrape ...

FRONTIERS MEDIA SA2023

Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation

Mathieu Salzmann, Yinlin Hu, Fulin Liu

Most modern image-based 6D object pose estimation methods learn to predict 2D-3D correspondences, from which the pose can be obtained using a PnP solver. Because of the non-differentiable nature of common PnP solvers, these methods are supervised via the i ...

Ieee Computer Soc2023

Learning curves for the multi-class teacher-student perceptron

Lenka Zdeborová, Bruno Loureiro, Elisabetta Cornacchia, Bruno Loureiro, Francesca Mignacco

One of the most classical results in high-dimensional learning theory provides a closed-form expression for the generalisation error of binary classification with a single-layer teacher-student perceptron on i.i.d. Gaussian inputs. Both Bayes-optimal (BO) ...

IOP Publishing Ltd2023

Graph Chatbot

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.