4 papers · 1 filter
A Bayesian Information-Theoretic Approach to Data Attribution
Dharmesh Tailor, Nicolò Felicioni, Kamil Ciosek
Training Data Attribution (TDA) seeks to trace model predictions back to influential training examples, enhancing interpretability and safety. We formulate TDA as a Bayesian inform…
Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence
Dharmesh Tailor, Alvaro H. C. Correia, Eric Nalisnick +1
Uncertainty quantification is an important prerequisite for the deployment of deep learning models in safety-critical areas. Yet, this hinges on the uncertainty estimates being use…
On Equivariant Model Selection through the Lens of Uncertainty
Putri A. van der Linden, Alexander Timans, Dharmesh Tailor +1
Equivariant models leverage prior knowledge on symmetries to improve predictive performance, but misspecified architectural constraints can harm it instead. While work has explored…
Learning to Defer to a Population: A Meta-Learning Approach
Dharmesh Tailor, Aditya Patra, Rajeev Verma +2
The learning to defer (L2D) framework allows autonomous systems to be safe and robust by allocating difficult decisions to a human expert. All existing work on L2D assumes that eac…