I’m a machine learning researcher focusing on the empirical study of deep learning models to improve their reliability in high stakes domains such as healthcare. At Brown University, I work with my PhD advisor, Michael Littman, studying the inductive bias of overparameterized models. For the past two summers, I collaborated with Michela Paganini at Facebook AI Research on model pruning. Prior to starting my PhD, I was an active core maintainer at Project Jupyter, which maintains open source projects such as the Jupyter Notebook. I also worked as a Data Scientist, collaborating with colleagues at organizations such as McKinsey and DARPA.
I believe that the open science movement is important for improving transparency and accountability in machine learning. At Project Jupyter I co-maintained reproducibility tools such as binder and repo2docker. I also am a co-organizer of the Machine Learning Reproducibility Challenge and Machine Learning Retrospectives.
Email me at jessica_forde at brown.edu.
Fun Fact: My Project Jupyter code is in the GitHub Arctic Code Vault, 250 meters underground in a former coal mine in Svalbard, Norway.
Selected Publications
- Cooper AF, Lu Y, Forde JZ, De Sa C. Hyperparameter Optimization Is Deceiving Us, and How to Stop It. NeurIPS. 2021.
- Forde JZ*, Cooper AF*, Kwegyir-Aggrey K, De Sa C, Littman M. Model Selection’s Disparate Impact in Real-World Deep Learning Applications. Science and Engineering of Deep Learning Workshop, ICLR 2021. Contributed Talk.
- Paganini M, Forde JZ. Bespoke vs. Prêt-à-Porter Lottery Tickets: Exploiting Mask Similarity for Trainable Sub-Network Finding. 2020.
- Paganini M, Forde JZ. dagger: A Python Framework for Reproducible Machine Learning Experiment Orchestration. 2020.
- Paganini M, Forde J. Streamlining Tensor and Network Pruning in PyTorch. ML for Developing Countries Workshop, ICLR 2020. Contributed Talk.
- Paganini M, Forde J. On Iterative Neural Network Pruning, Reinitialization, and the Similarity of Masks. ML for Developing Countries Workshop, ICLR 2020.
- Zech JR, Forde JZ, Littman ML. Individual predictions matter: Assessing the effect of data ordering in training fine-tuned CNNs for medical imaging. ML for Healthcare Workshop, NeurIPS 2019.
- Forde JZ, Paganini M. The scientific method in the science of machine learning. Debugging Machine Learning Models Workshop, ICLR 2019. Contributed Talk
- Forde J, Bussonnier M, Fortin F-A, Granger B, Head T, Holdgraf C, et al. Reproducing Machine Learning Research on Binder. 2018.
- Project Jupyter, M. Bussonnier, J. Forde, J. Freeman, B. Granger, T. Head, C. Holdgraf, K. Kelley, G. Nalvarte, A. Osheroff,M. Pacer, Y. Panda, F. Perez, B. Ragan-Kelley, and C. Willing. Binder 2.0-Reproducible, interactive, sharable environments for science at scale. Scipy. 2018.