research
∙
04/17/2023
Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization
The linearized-Laplace approximation (LLA) has been shown to be effectiv...
share
research
∙
02/14/2023
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization
Model reparametrization – transforming the parameter space via a bijecti...
research
∙
05/20/2022
Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks
Monte Carlo (MC) integration is the de facto method for approximating th...
research
∙
03/07/2022
Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference
Full Bayesian posteriors are rarely analytically tractable, which is why...
research
∙
11/05/2021
Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning
Deep neural networks are prone to overconfident predictions on outliers....
research
∙
06/28/2021
Laplace Redux – Effortless Bayesian Deep Learning
Bayesian formulations of deep learning have been shown to have compellin...
research
∙
06/18/2021
Being a Bit Frequentist Improves Bayesian Neural Networks
Despite their compelling theoretical properties, Bayesian neural network...
research
∙
10/06/2020
Learnable Uncertainty under Laplace Approximations
Laplace approximations are classic, computationally lightweight means fo...
research
∙
10/06/2020
Fixing Asymptotic Uncertainty of Bayesian Neural Networks with Infinite ReLU Features
Approximate Bayesian methods can mitigate overconfidence in ReLU network...
research
∙
03/02/2020
Fast Predictive Uncertainty for Classification with Bayesian Deep Networks
In Bayesian Deep Learning, distributions over the output of classificati...
research
∙
02/24/2020
Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks
The point estimates of ReLU classification networks—arguably the most wi...
research
∙
02/04/2019
Predictive Uncertainty Quantification with Compound Density Networks
Despite the huge success of deep neural networks (NNs), finding good mec...
research
∙
09/10/2018
Improving Response Selection in Multi-turn Dialogue Systems
Building systems that can communicate with humans is a core problem in A...
research
∙
02/03/2018