Bayesian Learning
Distributional Successor Features Enable Zero-Shot Policy Optimization
Intelligent agents must be generalists, capable of quickly adapting to various tasks.
Imitation learning (IL) aims to mimic the behavior of an expert in a sequential decision making task by learning from demonstrations, and has been widely applied
Full experimental details are provided in Appendix C.
Deep Bayesian Active Learning for Preference Modeling in Large Language Models
We address this by proposing the B ayesian A ctive L earner for P reference M odeling (BAL-PM), a novel stochastic acquisition policy that not only targets points of high epistemic uncertainty according to the preference model but also seeks to maximize the entropy of the acquired prompt distribution in the feature space spanned by the employed LLM.
Conditional Density Estimation with Histogram Trees
This makes CDE particularly useful in critical application domains. However, interpretable CDE methods are understudied.
Label Noise: Ignorance Is Bliss
We establish a new theoretical framework for learning under multi-class, instance-dependent label noise. This framework casts learning with label noise as a form of domain adaptation, in particular, domain adaptation under posterior drift.
Meta-Learning Universal Priors Using Non-Injective Change of Variables
Critical in this context is the prior knowledge accumulated from related tasks.
Amortized Bayesian Experimental Design for Decision-Making
For example, in personalized medical diagnostics, a model is built based on historical data to facilitate an optimal treatment for a new patient (Bica et al., 2021).