1 code implementation • ICML 2020 • Natasa Tagasovska, Thibault Vatter, Valérie Chavez-Demoulin
Causal inference using observational data is challenging, especially in the bivariate case.
no code implementations • 20 Jun 2023 • Michael Maser, Natasa Tagasovska, Jae Hyeon Lee, Andrew Watkins
As we train our predictive models jointly with a conformer decoder, the new latent embeddings can be mapped to their corresponding inputs, which we call \textit{MoleCLUEs}, or (molecular) counterfactual latent uncertainty explanations \citep{antoran2020getting}.
no code implementations • 18 Oct 2022 • Yanan Xin, Natasa Tagasovska, Fernando Perez-Cruz, Martin Raubal
Particularly, the transportation sector would benefit from the progress in AI and advance the development of intelligent transportation systems.
no code implementations • 16 Apr 2021 • Radhakrishna Achanta, Natasa Tagasovska
We show how our approach can be used for estimating uncertainty in prediction and out-of-distribution detection.
no code implementations • NeurIPS 2020 • Damien Ackerer, Natasa Tagasovska, Thibault Vatter
Atypically to standard NN applications, financial industry practitioners use such models equally to replicate market prices and to value other financial instruments.
1 code implementation • NeurIPS 2019 • Natasa Tagasovska, Damien Ackerer, Thibault Vatter
We introduce the vine copula autoencoder (VCAE), a flexible generative model for high-dimensional distributions built in a straightforward three-step procedure.
no code implementations • 30 Nov 2018 • Vaibhav Kulkarni, Natasa Tagasovska, Thibault Vatter, Benoit Garbinato
We also include two sample tests to assess statistical similarity between the observed and simulated distributions, and we analyze the privacy tradeoffs with respect to membership inference and location-sequence attacks.
1 code implementation • NeurIPS 2019 • Natasa Tagasovska, David Lopez-Paz
To estimate epistemic uncertainty, we propose Orthonormal Certificates (OCs), a collection of diverse non-constant functions that map all training samples to zero.
1 code implementation • 31 Jan 2018 • Natasa Tagasovska, Valérie Chavez-Demoulin, Thibault Vatter
Causal inference using observational data is challenging, especially in the bivariate case.