Related publications (63)

Exploiting the Signal-Leak Bias in Diffusion Models

Sabine Süsstrunk, Radhakrishna Achanta, Mahmut Sami Arpa, Martin Nicolas Everaert, Athanasios Fitsios

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate that this signa ...
2024

Unbiasing time-dependent Variational Monte Carlo by projected quantum evolution

Giuseppe Carleo, Clemens Giuliani, Alessandro Sinibaldi, Filippo Vicentini

We analyze the accuracy and sample complexity of variational Monte Carlo approaches to simulate the dynamics of many-body quantum systems classically. By systematically studying the relevant stochastic estimators, we are able to: (i) prove that the most us ...
Wien2023

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

Roland John Tormey, Siara Ruth Isaac, Nihat Kotluk

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 ...
2023

Penalising the biases in norm regularisation enforces sparsity

Nicolas Henri Bernard Flammarion, Etienne Patrice Boursier

Controlling the parameters' norm often yields good generalisation when training neural networks. Beyond simple intuitions, the relation between parameters' norm and obtained estimators theoretically remains misunderstood. For one hidden ReLU layer networks ...
2023

Perturbation theory models for LSST-era galaxy clustering: Tests with subpercent mock catalog measurements in Fourier and configuration space

Jonathan Andrew Blazek

We analyze the clustering of galaxies using the z = 1.006 snapshot of the CosmoDC2 simulation, a high-fidelity synthetic galaxy catalog designed to validate analysis methods for the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST). We prese ...
AMER PHYSICAL SOC2022

An automatized method to determine latencies of motor-evoked potentials under physiological and pathophysiological conditions

Friedhelm Christoph Hummel, Takuya Morishita, Pierre Theopistos Vassiliadis, Claudia Bigoni, Andéol Geoffroy Cadic-Melchior

Background. Latencies of motor evoked potentials (MEPs) can provide insights into the motor neuronal pathways activated by transcranial magnetic stimulation. Notwithstanding its clinical relevance, accurate, unbiased methods to automatize latency detection ...
IOP Publishing Ltd2022

Controlling the rotation of drift tearing modes by biased electrode in ADITYA-U tokamak

Harshita Raj, Ankit Kumar, Abhijit Sen, Rohit Kumar, Sameer Kumar

The influence of background plasma poloidal rotation on the rotation frequency of the m/n = 2/1 drift tearing mode (DTM) has been studied in ADITYA-U tokamak. The poloidal rotation velocity of the background plasma in the ion diamagnetic direction is incre ...
2021

Monte Carlo Estimators for Differential Light Transport

Wenzel Alban Jakob, Tizian Lucien Zeltner, Sébastien Nicolas Speierer

Physically based differentiable rendering algorithms propagate derivatives through realistic light transport simulations and have applications in diverse areas including inverse reconstruction and machine learning. Recent progress has led to unbiased metho ...
ASSOC COMPUTING MACHINERY2021

Countering Bias in Personalized Rankings From Data Engineering to Algorithm Development

Mirko Marras

This tutorial presents recent advances on the assessment and mitigation of data and algorithmic bias in personalized rankings. We first introduce fundamental concepts and definitions associated with bias issues, covering the state of the art and describing ...
IEEE COMPUTER SOC2021

Advances in Bias-aware Recommendation on the Web

Mirko Marras

The goal of this tutorial is to provide the WSDM community with recent advances on the assessment and mitigation of data and algorithmic bias in recommender systems. We first introduce conceptual foundations, by presenting the state of the art and describi ...
ASSOC COMPUTING MACHINERY2021

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.