Research
I am a postdoctoral researcher in the Department of Statistics at UC Berkeley, where I am advised by Ryan Tibshirani. I completed my PhD in Statistics in 2024 at Stanford University, where I was advised by Emmanuel Candès. Before that, I obtained my BSc in Math and Computer Science at McGill. My research develops new methods for quantifying and communicating the uncertainty underlying predictions made by black-box models. You can reach me at igibbs@berkeley.edu. A copy of my CV is available here.
Publications
Gibbs, I. and Candès, E. (2025+). Characterizing the training-conditional coverage of full conformal inference in high dimensions. arXiv preprint.
Gibbs, I., Cherian, J., and Candès, E. (2025). Conformal prediction with conditional Guarantees. Journal of the Royal Statistical Society: Series B.
Cherian, J., Gibbs, I., and Candès, E. (2024). Large language model validity via enhanced conformal prediction methods. Advances in Neural Information Processing Systems.
Gibbs, I. and Candès, E. (2024). Conformal inference for online prediction with arbitrary distribution shifts. Journal of Machine Learning Research.
Gibbs, I. and Candès, E. (2021). Adaptive conformal inference under distribution shift. Advances in Neural Information Processing Systems. (oral presentation)
Gibbs, I. and Chen, L. (2020). Asymptotic properties of random Voronoi cells with arbitrary underlying density. Advances in Applied Probability.
Gibbs, I., Leavey, K., Benton, S.J., Grynspan, D., Bainbridge, S.A., and Cox, B.J. (2019). Placental transcriptional and histologic subtypes of normotensive fetal growth restriction are comparable to preeclampsia. American Journal of Obstetrics and Gynecology.