| Single-model uncertainties for deep learning N Tagasovska, D Lopez-Paz Advances in Neural Information Processing Systems, 6417-6428, 2019 | 273 | 2019 |
| Deep Smoothing of the Implied Volatility Surface D Ackerer, N Tagasovska, T Vatter Proceedings of 34th Conference on Neural Information Processing Systems …, 2020 | 41 | 2020 |
| Distinguishing Cause from Effect Using Quantiles: Bivariate Quantile Causal Discovery N Tagasovska, V Chavez-Demoulin, T Vatter Proceedings of the 37th International Conference on Machine Learning, ICML, 2020 | 37* | 2020 |
| Copulas as High-Dimensional Generative Models: Vine Copula Autoencoders N Tagasovska, D Ackerer, T Vatter Advances in Neural Information Processing Systems, 6528-6540, 2019 | 37 | 2019 |
| Generative Models for Simulating Mobility Trajectories V Kulkarni, N Tagasovska, T Vatter, B Garbinato Workshop on Modeling and Decision-Making in the Spatiotemporal Domain, 32nd …, 2018 | 31 | 2018 |
| Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling R Lopez*, N Tagasovska*, S Ra, K Cho, J Pritchard, A Regev 2nd Conference on Causal Learning and Reasoning (CLeaR), 2022 | 18 | 2022 |
| Distributed clustering of categorical data using the information bottleneck framework N Tagasovska, P Andritsos Information Systems 72, 161-178, 2017 | 10 | 2017 |
| Bimodal feature-based fusion for real-time emotion recognition in a mobile context S Gievska, K Koroveshovski, N Tagasovska 2015 International Conference on Affective Computing and Intelligent …, 2015 | 9 | 2015 |
| Vision Paper: Causal Inference for Interpretable and Robust Machine Learning in Mobility Analysis Y Xin, N Tagasovska, F Perez-Cruz, M Raubal ACM SIGSPATIAL 2022, 2022 | 7 | 2022 |
| A Pareto-optimal compositional energy-based model for sampling and optimization of protein sequences N Tagasovska, NC Frey, A Loukas, I Hötzel, J Lafrance-Vanasse, RL Kelly, ... NeurIPS 2022 AI for Science workshop, 2022 | 5 | 2022 |
| Efficiency comparison of DFT/IDFT algorithms by evaluating diverse hardware implementations, parallelization prospects and possible improvements D Efnusheva, N Tagasovska, A Tentov, M Kalendar Proc. Second International Conference on Applied Innovations in IT, Germany, 2014 | 5 | 2014 |
| Retrospective Uncertainties for Deep Models using Vine Copulas N Tagasovska, F Ozdemir, A Brando Proceedings of the 26th International Conference on Artificial Intelligence …, 2023 | 2 | 2023 |
| Performances of LEON3 IP Core in WiGig Environment on Receiving Side N Tagasovska, P Grnarova, A Tentov, D Efnusheva New Trends in Networking, Computing, E-learning, Systems Sciences, and …, 2015 | 1 | 2015 |
| An Efficient 64-Point IFFT Hardware Module Design D Efnusheva, A Tentov, N Tagasovska New Trends in Networking, Computing, E-learning, Systems Sciences, and …, 2015 | 1 | 2015 |
| MoleCLUEs: Molecular Conformers Maximally In-Distribution for Predictive Models M Maser, N Tagasovska, JH Lee, A Watkins NeurIPS 2023 AI for Science Workshop, 2023 | | 2023 |
| Antibody DomainBed: Out-of-Distribution Generalization in Therapeutic Protein Design N Tagasovska, JW Park, M Kirchmeyer, NC Frey, AM Watkins, AA Ismail, ... | | 2023 |
| MoleCLUEs: Optimizing Molecular Conformers by Minimization of Differentiable Uncertainty M Maser*, N Tagasovska*, JH Lee, A Watkins arXiv preprint arXiv:2306.11681, 2023 | | 2023 |
| BOtied: Multi-objective Bayesian optimization with tied multivariate ranks JW Park*, N Tagasovska*, M Maser, S Ra, K Cho arXiv preprint arXiv:2306.00344, 2023 | | 2023 |
| Uncertainty Surrogates for Deep Learning R Achanta, N Tagasovska arXiv preprint arXiv:2104.08147, 2021 | | 2021 |
