no code implementations • 2 May 2024 • Boris van Breugel, Mihaela van der Schaar
Recent text and image foundation models are incredibly impressive, and these models are attracting an ever-increasing portion of research resources.
no code implementations • 20 Dec 2023 • Fernando Pérez-García, Sam Bond-Taylor, Pedro P. Sanchez, Boris van Breugel, Daniel C. Castro, Harshita Sharma, Valentina Salvatelli, Maria T. A. Wetscherek, Hannah Richardson, Matthew P. Lungren, Aditya Nori, Javier Alvarez-Valle, Ozan Oktay, Maximilian Ilse
Biomedical imaging datasets are often small and biased, meaning that real-world performance of predictive models can be substantially lower than expected from internal testing.
no code implementations • 19 Dec 2023 • Nabeel Seedat, Nicolas Huynh, Boris van Breugel, Mihaela van der Schaar
Machine Learning (ML) in low-data settings remains an underappreciated yet crucial problem.
no code implementations • 25 Sep 2023 • Yangming Li, Boris van Breugel, Mihaela van der Schaar
In light of our theoretical studies, we introduce soft mixture denoising (SMD), an expressive and efficient model for backward denoising.
1 code implementation • 16 May 2023 • Boris van Breugel, Zhaozhi Qian, Mihaela van der Schaar
Generating synthetic data through generative models is gaining interest in the ML community and beyond, promising a future where datasets can be tailored to individual needs.
no code implementations • 7 Apr 2023 • Boris van Breugel, Mihaela van der Schaar
Generating synthetic data through generative models is gaining interest in the ML community and beyond.
1 code implementation • 24 Feb 2023 • Boris van Breugel, Hao Sun, Zhaozhi Qian, Mihaela van der Schaar
In this work we argue for a realistic MIA setting that assumes the attacker has some knowledge of the underlying data distribution.
no code implementations • 11 Nov 2022 • Tennison Liu, Alex J. Chan, Boris van Breugel, Mihaela van der Schaar
It is important to guarantee that machine learning algorithms deployed in the real world do not result in unfairness or unintended social consequences.
no code implementations • NeurIPS 2023 • Hao Sun, Boris van Breugel, Jonathan Crabbe, Nabeel Seedat, Mihaela van der Schaar
Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models.
1 code implementation • NeurIPS 2021 • Boris van Breugel, Trent Kyono, Jeroen Berrevoets, Mihaela van der Schaar
In this paper, we introduce DECAF: a GAN-based fair synthetic data generator for tabular data.
3 code implementations • 17 Feb 2021 • Ahmed M. Alaa, Boris van Breugel, Evgeny Saveliev, Mihaela van der Schaar
In this paper, we introduce a 3-dimensional evaluation metric, ($\alpha$-Precision, $\beta$-Recall, Authenticity), that characterizes the fidelity, diversity and generalization performance of any generative model in a domain-agnostic fashion.
1 code implementation • EACL 2021 • Daniel de Vassimon Manela, David Errington, Thomas Fisher, Boris van Breugel, Pasquale Minervini
The first approach is an online method which is effective at removing skew at the expense of stereotype.