A loss-driven framework for Bayesian active learning that targets downstream decision losses directly.
May 8, 2026
🎉 Thrilled to share that our paper, “Loss-Driven Bayesian Active Learning,” has been accepted at AISTATS 2026! I am incredibly grateful to my awesome collaborators, Freddie Bickford Smith and Tom Rainforth, for their ideas, support, and all the work we put into this project together.
Jan 1, 2026