Zobrazeno 1 - 10
of 4 545
pro vyhledávání: '"Calmon, A."'
Autor:
Oesterling, Alex, Verdun, Claudio Mayrink, Long, Carol Xuan, Glynn, Alexander, Paes, Lucas Monteiro, Vithana, Sajani, Cardone, Martina, Calmon, Flavio P.
Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representational harms balance the number of retrieved items across population groups
Externí odkaz:
http://arxiv.org/abs/2407.08571
Differentially private distributed mean estimation (DP-DME) is a fundamental building block in privacy-preserving federated learning, where a central server estimates the mean of $d$-dimensional vectors held by $n$ users while ensuring $(\epsilon,\de
Externí odkaz:
http://arxiv.org/abs/2407.03289
Autor:
Kulynych, Bogdan, Gomez, Juan Felipe, Kaissis, Georgios, Calmon, Flavio du Pin, Troncoso, Carmela
Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the added noise i
Externí odkaz:
http://arxiv.org/abs/2407.02191
A novel approach for modeling Dark Count Rate (DCR) drift in Single-Photon Avalanche Diodes (SPADs) is proposed based on Hot-Carrier Degradation (HCD) inducing silicon-hydrogen bond dissociation at the Si/SiO2 interface. The energy and the quantity o
Externí odkaz:
http://arxiv.org/abs/2407.07105
Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, there has been increasing effo
Externí odkaz:
http://arxiv.org/abs/2405.19562
Machine learning (ML) is widely used to moderate online content. Despite its scalability relative to human moderation, the use of ML introduces unique challenges to content moderation. One such challenge is predictive multiplicity: multiple competing
Externí odkaz:
http://arxiv.org/abs/2402.16979
CLIP embeddings have demonstrated remarkable performance across a wide range of computer vision tasks. However, these high-dimensional, dense vector representations are not easily interpretable, restricting their usefulness in downstream applications
Externí odkaz:
http://arxiv.org/abs/2402.10376
Autor:
Watson-Daniels, Jamelle, Calmon, Flavio du Pin, D'Amour, Alexander, Long, Carol, Parkes, David C., Ustun, Berk
Machine learning models in modern mass-market applications are often updated over time. One of the foremost challenges faced is that, despite increasing overall performance, these updates may flip specific model predictions in unpredictable ways. In
Externí odkaz:
http://arxiv.org/abs/2402.07745
Autor:
Paes, Lucas Monteiro, Suresh, Ananda Theertha, Beutel, Alex, Calmon, Flavio P., Beirami, Ahmad
Machine learning (ML) models used in prediction and classification tasks may display performance disparities across population groups determined by sensitive attributes (e.g., race, sex, age). We consider the problem of evaluating the performance of
Externí odkaz:
http://arxiv.org/abs/2312.03867
This communication reports on a study carried out in the context of the collaborative FOEHN project (Human and Organizational Factors in Non-Destructive Evaluation) supported by the French National Research Agency. The motivation of this project come
Externí odkaz:
http://arxiv.org/abs/2310.14697