Uncertainty
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.
A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcuts
Recent evidence suggests that, in some problems, NeSy models can achieve high accuracy on the reasoning task by learning concepts with incorrect semantics .
BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
See more details in our project page: https://sites.google.com/view/be-cause.
Meta-Learning Universal Priors Using Non-Injective Change of Variables
Critical in this context is the prior knowledge accumulated from related tasks.
Estimating Epistemic and Aleatoric Uncertainty with a Single Model
By contrast, epistemic uncertainty describes the inference model's lack of knowledge
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).
Fast Sampling via Discrete Non-Markov Diffusion Models with Predetermined Transition Time
Diffusion-based generative models, as first introduced by Sohl-Dickstein et al. (2015), have shown