activity
20182025
most citedMixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning

2 citations · 3 across the 3 of their papers we have counts for

collaborators

6 papers

stat.ML20221 cited

Discovering Inductive Bias with Gibbs Priors: A Diagnostic Tool for Approximate Bayesian Inference

Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig +1

Full Bayesian posteriors are rarely analytically tractable, which is why real-world Bayesian inference heavily relies on approximate techniques. Approximations generally differ fro…

cs.LG20212 cited

Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning

Runa Eschenhagen, Erik Daxberger, Philipp Hennig +1

Deep neural networks are prone to overconfident predictions on outliers. Bayesian neural networks and deep ensembles have both been shown to mitigate this problem to some extent. I…

stat.ML2020

Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks

Agustinus Kristiadi, Matthias Hein, Philipp Hennig

The point estimates of ReLU classification networks---arguably the most widely used neural network architecture---have been shown to yield arbitrarily high confidence far away from…

stat.ML2019

Predictive Uncertainty Quantification with Compound Density Networks

Agustinus Kristiadi, Sina Däubener, Asja Fischer

Despite the huge success of deep neural networks (NNs), finding good mechanisms for quantifying their prediction uncertainty is still an open problem. Bayesian neural networks are…

cs.AI2018

Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge

Debanjan Chaudhuri, Agustinus Kristiadi, Jens Lehmann +1

Building systems that can communicate with humans is a core problem in Artificial Intelligence. This work proposes a novel neural network architecture for response selection in an…

cs.AI2018

Incorporating Literals into Knowledge Graph Embeddings

Agustinus Kristiadi, Mohammad Asif Khan, Denis Lukovnikov +2

Knowledge graphs, on top of entities and their relationships, contain other important elements: literals. Literals encode interesting properties (e.g. the height) of entities that…