Ioana Bica

Researcher, DeepMind

Joined

September 2019

Names

Ioana Bica (Preferred)

Emails

****@eng.ox.ac.uk (Confirmed)

****@gmail.com (Confirmed)

****@deepmind.com (Confirmed)

Personal Links

Homepage

Career & Education History

Researcher

DeepMind (deepmind.com)

2022 – Present

PhD student

University of Oxford (ox.ac.uk)

2018 – 2022

MS student

University of Cambridge (cam.ac.uk)

2017 – 2018

Undergrad student

University of Cambridge (cam.ac.uk)

2014 – 2017

Advisors, Relations & Conflicts

PhD Advisor

Mihaela van der Schaar

2018 – 2022

Expertise

causal inference

causality

counterfactuals

Present

healthcare

Present

self-supervised learning

representation learning

Present

Publications

Improving fine-grained understanding in image-text pre-training
Ioana Bica, Anastasija Ilic, Matthias Bauer, Goker Erdogan, Matko Bošnjak, Christos Kaplanis, Alexey A. Gritsenko, Matthias Minderer, Charles Blundell, Razvan Pascanu, Jovana Mitrovic
- ICML 2024 Poster
- Readers: Everyone
Neural Algorithmic Reasoning with Causal Regularisation
Beatrice Bevilacqua, Kyriacos Nikiforou, Borja Ibarz, Ioana Bica, Michela Paganini, Charles Blundell, Jovana Mitrovic, Petar Veličković
- ICML 2023 Poster
- Readers: Everyone
Dynamic Outcomes-Based Clustering of Disease Trajectory in Mechanically Ventilated Patients
Emma Charlotte Rocheteau, Ioana Bica, Pietro Lio, Ari Ercole
- Published: 02 Dec 2022, Last Modified: 05 May 2023
- TS4H Poster
- Readers: Everyone
Pushing the limits of self-supervised learning: Can we outperform supervised learning without labels?
Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Benchmarking Heterogeneous Treatment Effect Models through the Lens of Interpretability
Jonathan Crabbé, Alicia Curth, Ioana Bica, Mihaela van der Schaar
- Published: 17 Sept 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Datasets and Benchmarks
- Readers: Everyone
Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?
Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Holger Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic
- 26 May 2022 (modified: 30 Dec 2025)
- ICML 2022 Pre-training Workshop
- Readers: Everyone
Data-IQ: Characterizing subgroups with heterogeneous outcomes in tabular data
Nabeel Seedat, Jonathan Crabbé, Ioana Bica, Mihaela van der Schaar
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation
Ioana Bica, Mihaela van der Schaar
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation
Alex Chan, Ioana Bica, Alihan Hüyük, Daniel Jarrett, Mihaela van der Schaar
- Published: 11 Oct 2021, Last Modified: 12 Oct 2025
- NeurIPS 2021 Datasets and Benchmarks Track (Round 2)
- Readers: Everyone
The Medkit-Learn(ing) Environment: Medical Decision Modelling through Simulation
Alex Chan, Ioana Bica, Alihan Hüyük, Daniel Jarrett, Mihaela van der Schaar
- 08 Jun 2021 (modified: 26 May 2025)
- Submitted to NeurIPS 2021 Datasets and Benchmarks Track (Round 1)
- Readers: Everyone

View all 18 publications

Co-Authors

View all 35 co-authors