Zobrazeno 1 - 10
of 1 023
pro vyhledávání: '"Sapiro, Guillermo"'
Autor:
Wehenkel, Antoine, Gamella, Juan L., Sener, Ozan, Behrmann, Jens, Sapiro, Guillermo, Cuturi, Marco, Jacobsen, Jörn-Henrik
Driven by steady progress in generative modeling, simulation-based inference (SBI) has enabled inference over stochastic simulators. However, recent work has demonstrated that model misspecification can harm SBI's reliability. This work introduces ro
Externí odkaz:
http://arxiv.org/abs/2405.08719
Tokens or patches within Vision Transformers (ViT) lack essential semantic information, unlike their counterparts in natural language processing (NLP). Typically, ViT tokens are associated with rectangular image patches that lack specific semantic co
Externí odkaz:
http://arxiv.org/abs/2402.17863
Current approaches to group fairness in federated learning assume the existence of predefined and labeled sensitive groups during training. However, due to factors ranging from emerging regulations to dynamics and location-dependency of protected gro
Externí odkaz:
http://arxiv.org/abs/2402.14929
Autor:
Wehenkel, Antoine, Behrmann, Jens, Miller, Andrew C., Sapiro, Guillermo, Sener, Ozan, Cuturi, Marco, Jacobsen, Jörn-Henrik
Over the past decades, hemodynamics simulators have steadily evolved and have become tools of choice for studying cardiovascular systems in-silico. While such tools are routinely used to simulate whole-body hemodynamics from physiological parameters,
Externí odkaz:
http://arxiv.org/abs/2307.13918
Autor:
Wehenkel, Antoine, Behrmann, Jens, Hsu, Hsiang, Sapiro, Guillermo, Louppe, Gilles, Jacobsen, Jörn-Henrik
Publikováno v:
Transaction on Machine Learning Research, 2023
Hybrid modelling reduces the misspecification of expert models by combining them with machine learning (ML) components learned from data. Similarly to many ML algorithms, hybrid model performance guarantees are limited to the training distribution. L
Externí odkaz:
http://arxiv.org/abs/2202.03881
Collaborative filtering is the de facto standard for analyzing users' activities and building recommendation systems for items. In this work we develop Sliced Anti-symmetric Decomposition (SAD), a new model for collaborative filtering based on implic
Externí odkaz:
http://arxiv.org/abs/2201.11936
Publikováno v:
2022 ACM Conference on Fairness, Accountability, and Transparency (FAccT '22). Association for Computing Machinery, New York, NY, USA, 142-159
Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minimax group fairness in federated learning scenarios where different participating entitie
Externí odkaz:
http://arxiv.org/abs/2201.08304
Machine learning models are updated as new data is acquired or new architectures are developed. These updates usually increase model performance, but may introduce backward compatibility errors, where individual users or groups of users see their per
Externí odkaz:
http://arxiv.org/abs/2112.10290
Autor:
Schlesinger, Oded, Kundu, Raj, Isaev, Dmitry, Choi, Jessica Y., Goetz, Stefan M., Turner, Dennis A., Sapiro, Guillermo, Peterchev, Angel V., Di Martino, J. Matias
Publikováno v:
In Computers in Biology and Medicine August 2024 178
Federated learning is an increasingly popular paradigm that enables a large number of entities to collaboratively learn better models. In this work, we study minmax group fairness in paradigms where different participating entities may only have acce
Externí odkaz:
http://arxiv.org/abs/2110.01999