- PhD Student
Machine Learning Researcher at Microsoft Research Cambridge (Jan 2023 - present)
In March 2023, I passed my PhD viva with minor corrections. Thesis title: Out-of-distribution generalisation in machine learning. My examiners were Ferenc Huszár and Artur d'Avila Garcez.
2021-2022 Wiseman Prize winner
Recipient of the Young AI Researcher 2022 Award
Myson College Exhibition for Personal Achievement 2023 (awarded by Lucy Cavendish College)
Research areas:
- Out-of-distribution generalisation in machine learning:
- Learning invariant features across multiple training distributions
- Applications in healthcare and fairness
- Multi-agent communication:
- Emergent communication in referential games
- Graph representation learning
- Visual relational reasoning
Teaching
Publications
Preprints:
Massiceti D., Longden C., Słowik A., Wills S., Grayson M., Morrison C. (2023) Explaining CLIP's performance disparities on data from blind/low vision users. arXiv preprint arXiv:2311.17315.
Conference publications:
Słowik A., Bottou L., Holden S. B., Jamnik M. (2022) On the Relation between Distributionally Robust Optimization and Data Curation (Student Abstract). The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022). (AAAI-22 Best Student Abstract Honorable Mention)
Słowik A., Bottou L. (2021) On Distributionally Robust Optimization and Data Rebalancing. The 25th International Conference on Artificial Intelligence and Statistics (AISTATS 2022).
Lamb A., Goyal A., Słowik A., Beaudoin P., Mozer M., Bengio Y. (2021) Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers. The 24th International Conference on Artificial Intelligence and Statistics (AISTATS 2021).
Słowik A.*, Gupta, A.*, Hamilton, W. L., Jamnik, M., Holden, S. B., Pal, C. (2021) Structural Inductive Biases in Emergent Communication. Proceedings of The 43rd Annual Meeting of the Cognitive Science Society (CogSci 2021). (oral presentation)
Danel T., Spurek P., Tabor J., Śmieja M., Struski Ł., Słowik A., Maziarka Ł. (2020) Spatial Graph Convolutional Networks. International Conference on Neural Information Processing (ICONIP 2020).
Słowik A., Mangla C., Jamnik M., Holden S. B., Paulson L. C. (2020) Bayesian Optimisation for Heuristic Configuration in Automated Theorem Proving (Student Abstract). The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020).
Workshop presentations:
Słowik A., Bottou L. (2021) Algorithmic Bias and Data Bias: Understanding the Relation between Distributionally Robust Optimization and Data Curation. NeurIPS workshop on Algorithmic Fairness through the Lens of Causality and Robustness (AFCR 2021). (contributed talk)
Słowik A., Bottou L. (2021) On the Relation between Distributionally Robust Optimization and Data Curation. NeurIPS Workshop on Optimization for Machine Learning (OPT 2021). (contributed talk)
Aubin B., Słowik A., Arjovsky M., Bottou L., Lopez-Paz D. (2020) Linear unit-tests for invariance discovery. NeurIPS Workshop on Causal Discovery and Causality-Inspired Machine Learning. (oral presentation)
Guo S., Ren Y., Słowik A., Mathewson K. (2020) Inductive Bias and Language Expressivity in Emergent Communication. 4th NeurIPS Workshop on Emergent Communication: Talking to Strangers: Zero-Shot Emergent Communication.
Gupta* A., Słowik* A., Hamilton W. L., Jamnik M., Holden S. B., Pal C. (2020) Analyzing Structural Priors in Multi-Agent Communication. Workshop on Adaptive and Learning Agents at AAMAS 2020. (oral presentation)
Słowik* A., Gupta* A., Hamilton W. L., Jamnik M., Holden S. B. (2020) Towards Graph Representation Learning in Emergent Communication. Workshop on Reinforcement Learning in Games at AAAI 2020.
Antoniou A., Słowik A., Crowley E. J., Storkey A. J. (2018) Dilated DenseNets for Relational Reasoning. Women in Machine Learning Workshop at NeurIPS 2018 (WiML 2018), Theoretical Foundations of Machine Learning (TFML 2019), Transylvanian Machine Learning Summer School (TMLSS). (oral presentation)
