$$ \newcommand{\dint}{\mathrm{d}} \newcommand{\vphi}{\boldsymbol{\phi}} \newcommand{\vpi}{\boldsymbol{\pi}} \newcommand{\vpsi}{\boldsymbol{\psi}} \newcommand{\vomg}{\boldsymbol{\omega}} \newcommand{\vsigma}{\boldsymbol{\sigma}} \newcommand{\vzeta}{\boldsymbol{\zeta}} \renewcommand{\vx}{\mathbf{x}} \renewcommand{\vy}{\mathbf{y}} \renewcommand{\vz}{\mathbf{z}} \renewcommand{\vh}{\mathbf{h}} \renewcommand{\b}{\mathbf} \renewcommand{\vec}{\mathrm{vec}} \newcommand{\vecemph}{\mathrm{vec}} \newcommand{\mvn}{\mathcal{MN}} \newcommand{\G}{\mathcal{G}} \newcommand{\M}{\mathcal{M}} \newcommand{\N}{\mathcal{N}} \newcommand{\S}{\mathcal{S}} \newcommand{\I}{\mathcal{I}} \newcommand{\diag}[1]{\mathrm{diag}(#1)} \newcommand{\diagemph}[1]{\mathrm{diag}(#1)} \newcommand{\tr}[1]{\text{tr}(#1)} \renewcommand{\C}{\mathbb{C}} \renewcommand{\R}{\mathbb{R}} \renewcommand{\E}{\mathbb{E}} \newcommand{\D}{\mathcal{D}} \newcommand{\inner}[1]{\langle #1 \rangle} \newcommand{\innerbig}[1]{\left \langle #1 \right \rangle} \newcommand{\abs}[1]{\lvert #1 \rvert} \newcommand{\norm}[1]{\lVert #1 \rVert} \newcommand{\two}{\mathrm{II}} \newcommand{\GL}{\mathrm{GL}} \newcommand{\Id}{\mathrm{Id}} \newcommand{\grad}[1]{\mathrm{grad} \, #1} \newcommand{\gradat}[2]{\mathrm{grad} \, #1 \, \vert_{#2}} \newcommand{\Hess}[1]{\mathrm{Hess} \, #1} \newcommand{\T}{\text{T}} \newcommand{\dim}[1]{\mathrm{dim} \, #1} \newcommand{\partder}[2]{\frac{\partial #1}{\partial #2}} \newcommand{\rank}[1]{\mathrm{rank} \, #1} \newcommand{\inv}1 \newcommand{\map}{\text{MAP}} \newcommand{\L}{\mathcal{L}} \DeclareMathOperator*{\argmax}{arg\,max} \DeclareMathOperator*{\argmin}{arg\,min} $$

Agustinus Kristiadi

Email

agustinus[at]kristia.de

Google Scholar

https://scholar.google.com/citations?user=_1qe2mYAAAAJ&hl=en

LinkedIn

https://www.linkedin.com/in/agustinus-kristiadi/

Github

https://github.com/wiseodd

Interest

Uncertainty quantification in deep learning

Bayesian inference

Riemannian and information geometry

Education

University of Tübingen, Germany

Ph.D., Computer Science, 2019-

Methods of Machine Learning group, advised by Philipp Hennig

University of Bonn, Germany

M.Sc., Computer Science, 2017-2019

Theoretical Computer Science, Intelligent Systems

Thesis: Predictive Uncertainty Quantification with Compound Density Networks

Grade: 1.1 (3.9 GPA equivalent)

Universitas Atma Jaya Yogyakarta, Indonesia

B.Eng., Informatics Engineering, 2009-2013

Numerics, Soft Computing

Thesis: Parallel Particle Swarm Optimization for Image Segmentation

GPA: 3.9

Teaching

University of Tübingen

Tutor, Data Literacy, Winter Semester 2021-2022

Tutor, Probabilistic Machine Learning, Summer Semester 2021

Tutor, Data Literacy, Winter Semester 2020-2021

Tutor, Probabilistic Machine Learning, Summer Semester 2020

Tutor, Data Literacy, Winter Semester 2019-2020

Universitas Atma Jaya Yogyakarta

Tutor, Advanced Data Structure, 2012

Tutor, Database, 2011

Academic Experience

Methods of Machine Learning group, University of Tübingen

Research Assistant, 2019-

Smart Data Analytics (SDA) group, University of Bonn

Student Research Assistant, 2017-2019

Universitas Atma Jaya Yogyakarta

Research Assistant, 2016-2017

Industry Experience

GDP Labs

Software Engineer, 2013-2015

Astra International

Software Engineering Intern, 2012

Language

English (IELTS 8.0)

German (A2)

Indonesian (native)

Javanese (native)

Publication

An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence

Kristiadi, Agustinus, Matthias Hein, and Philipp Hennig.

NeurIPS 2021 [Spotlight] [arxiv]

Laplace Redux -- Effortless Bayesian Deep Learning

Daxberger*, Erik, Agustinus Kristiadi*, Alexander Immer*, Runa Eschenhagen*, Matthias Bauer, and Philipp Hennig.

NeurIPS 2021 [arxiv] [code]

Learnable Uncertainty under Laplace Approximations

Kristiadi, Agustinus, Matthias Hein, and Philipp Hennig.

UAI 2021 [arxiv] [code]

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

Kristiadi, Agustinus, Matthias Hein, and Philipp Hennig.

ICML 2020 [abs] [code]

Predictive Uncertainty Quantification with Compound Density Networks

Kristiadi, Agustinus, Sina Däubener, and Asja Fischer.

Bayesian Deep Learning Workshop, NeurIPS 2019 [arxiv] [code]

Incorporating Literals into Knowledge Graph Embeddings

Kristiadi, Agustinus*, Mohammad Asif Khan*, Denis Lukovnikov, Jens Lehmann, and Asja Fischer.

ISWC 2019 [arxiv] [code]

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

Chauduri, Debanjan, Agustinus Kristiadi, Jens Lehmann, Asja Fischer.

CoNLL 2018 [arxiv] [code]

Deep Convolutional Level Set Method for Image Segmentation

Kristiadi, Agustinus, and Pranowo Pranowo.

Journal of ICT Research and Applications 11.3 (2017) [pdf] [code]

Parallel Particle Swarm Optimization for Image Segmentation

Kristiadi, Agustinus, Pranowo Pranowo, and Paulus Mudjihartono.

DEIS 2013 [pdf] [code]

Preprint

Being a Bit Frequentist Improves Bayesian Neural Networks

Agustinus Kristiadi, Matthias Hein, and Philipp Hennig.

[arxiv]

Fast Predictive Uncertainty for Classification with Bayesian Deep Networks

Hobbhahn, Marius, Agustinus Kristiadi, and Philipp Hennig.

[arxiv]