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

Agustinus's Portrait

Agustinus Kristiadi

Postdoc at the Vector Institute, Toronto


Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets

Wu Lin*, Felix Dangel*, Runa Eschenhagen, Kirill Neklyudov, Agustinus Kristiadi, Richard Turner, Alireza Makhzani
ICML 2024 [arxiv] [code]

A Sober Look at LLMs for Material Discovery: Are They Actually Good for Bayesian Optimization Over Molecules?

Agustinus Kristiadi, Felix Strieth-Kalthoff, Marta Skreta, Pascal Poupart, Alán Aspuru-Guzik, Geoff Pleiss
ICML 2024 [arxiv] [code]

Position Paper: Bayesian Deep Learning in the Age of Large-Scale AI

Theodore Papamarkou, Maria Skoularidou, Konstantina Palla, Laurence Aitchison, Julyan Arbel, David Dunson, Maurizio Filippone, Vincent Fortuin, Philipp Hennig, Jose Miguel Hernandez Lobato, Aliaksandr Hubin, Alexander Immer, Theofanis Karaletsos, Mohammad Emtiyaz Khan, Agustinus Kristiadi, Yingzhen Li, Stephan Mandt, Christopher Nemeth, Michael A. Osborne, Tim G. J. Rudner, David Rügamer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang
ICML 2024 [arxiv]

Preventing Arbitrarily High Confidence on Far-Away Data in Point-Estimated Discriminative Neural Networks

Ahmad Rashid, Serena Hacker, Guojun Zhang, Agustinus Kristiadi, Pascal Poupart
AISTATS 2024 [arxiv] [code]

The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

Agustinus Kristiadi, Felix Dangel, and Philipp Hennig
NeurIPS 2023 [Spotlight] [arxiv]

Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks

Agustinus Kristiadi, Runa Eschenhagen, and Philipp Hennig
NeurIPS 2022 [arxiv] [code]

Fast Predictive Uncertainty for Classification with Bayesian Deep Networks

Marius Hobbhahn, Agustinus Kristiadi, and Philipp Hennig
UAI 2022 [paper] [code]

Being a Bit Frequentist Improves Bayesian Neural Networks

Agustinus Kristiadi, Matthias Hein, and Philipp Hennig
AISTATS 2022 [paper] [code]

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

Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, and Ulrike von Luxburg
AISTATS 2022 [paper] [code]

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

Agustinus Kristiadi, Matthias Hein, and Philipp Hennig
NeurIPS 2021 [Spotlight] [paper] [code]

Laplace Redux -- Effortless Bayesian Deep Learning

Erik Daxberger*, Agustinus Kristiadi*, Alexander Immer*, Runa Eschenhagen*, Matthias Bauer, and Philipp Hennig
NeurIPS 2021 [paper] [code]

Learnable Uncertainty Under Laplace Approximations

Agustinus Kristiadi, Matthias Hein, and Philipp Hennig
UAI 2021 [Long Talk] [paper] [code]

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

Agustinus Kristiadi, Matthias Hein, and Philipp Hennig
ICML 2020 [paper] [code]

Incorporating Literals into Knowledge Graph Embeddings

Agustinus Kristiadi*, 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

Debanjan Chauduri, Agustinus Kristiadi, Jens Lehmann, Asja Fischer
CoNLL 2018 [arxiv] [code]

Deep Convolutional Level Set Method for Image Segmentation

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

Parallel Particle Swarm Optimization for Image Segmentation

Agustinus Kristiadi, Pranowo, and Paulus Mudjihartono
DEIS 2013 [pdf] [code]


Uncertainty-Guided Optimization on Large Language Model Search Trees

Julia Grosse, Ruotian Wu, Ahmad Rashid, Philipp Hennig, Pascal Poupart, Agustinus Kristiadi
AABI, co-located with ICML 2024 [arxiv] [code]

How Useful is Intermittent, Asynchronous Expert Feedback for Bayesian Optimization?

Agustinus Kristiadi, Felix Strieth-Kalthoff, Sriram Ganapathi Subramanian, Vincent Fortuin, Pascal Poupart, Geoff Pleiss
AABI, co-located with ICML 2024 [arxiv] [code]

A Critical Look At Tokenwise Reward-Guided Text Generation

Ahmad Rashid, Ruotian Wu, Julia Grosse, Agustinus Kristiadi*, Pascal Poupart*
ArXiv [arxiv]

Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization

Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, and Vincent Fortuin
AABI, co-located with ICML 2023 [arxiv]

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

Runa Eschenhagen, Erik Daxberger, Philipp Hennig, Agustinus Kristiadi
Bayesian Deep Learning Workshop, NeurIPS 2021 [arxiv]

Predictive Uncertainty Quantification with Compound Density Networks

Agustinus Kristiadi, Sina Däubener, and Asja Fischer
Bayesian Deep Learning Workshop, NeurIPS 2019 [arxiv] [code]


On the Disconnect Between Theory and Practice of Overparametrized Neural Networks

Jonathan Wenger, Felix Dangel, Agustinus Kristiadi
ArXiv [arxiv]