Bayesian Learning
When Y our AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback Leon Lang University of Amsterdam Davis Foote
Modeling the human as Boltzmann-rational w.r.t. a belief over trajectories, we prove conditions under which RLHF is
PAC Learning Linear Thresholds from Label Proportions
The goal is to train a good instance classifier.
Markov Equivalence and Consistency in Differentiable Structure Learning Chang Deng Kevin Bello
These results are then generalized to general models and likelihoods, where the same claims hold.
BayesTune: Bayesian Sparse Deep Model Fine-tuning
Deep learning practice is increasingly driven by powerful foundation models (FM), pre-trained at scale and then fine-tuned for specific tasks of interest.
Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
When releasing outputs from confidential data, agencies need to balance the analytical usefulness of the released data with the obligation to protect data subjects'
A Bayesian Approach To Analysing Training Data Attribution In Deep Learning
Training data attribution (TDA) techniques find influential training data for the model's prediction on the test data of interest.