Publication List

Thesis

Low-Cost Bayesian Methods for Fixing Neural Networks' Overconfidence

Agustinus Kristiadi

PhD Thesis, University of Tuebingen 2023
Paper
Predictive Uncertainty Quantification With Compound Density Networks

Agustinus Kristiadi

Master Thesis, University of Bonn 2019
Paper

Conference

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 E Turner, Alireza Makhzani

ICML 2024
Paper

Github
Position: Bayesian Deep Learning is Needed 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, 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 Ruegammer, Yee Whye Teh, Max Welling, Andrew Gordon Wilson, Ruqi Zhang

ICML 2024
Paper
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, Alan Aspuru-Guzik, Geoff Pleiss

ICML 2024
Paper

Github
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
Paper

Github
The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

Agustinus Kristiadi, Felix Dangel, Philipp Hennig

NeurIPS 2023
Spotlight

Paper
Posterior Refinement Improves Sample Efficiency in Bayesian Neural Networks

Agustinus Kristiadi, Runa Eschenhagen, Philipp Hennig

NeurIPS 2022
Paper

Github
Fast Predictive Uncertainty for Classification with Bayesian Deep Networks

Marius Hobbhahn, Agustinus Kristiadi, Philipp Hennig

UAI 2022
Paper

Github
Being a Bit Frequentist Improves Bayesian Neural Networks

Agustinus Kristiadi, Matthias Hein, Philipp Hennig

AISTATS 2022
Paper

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

Luca Rendsburg, Agustinus Kristiadi, Philipp Hennig, Ulrike von Luxburg

AISTATS 2022
Paper

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

Agustinus Kristiadi, Matthias Hein, Philipp Hennig

NeurIPS 2021
Spotlight

Paper
Laplace Redux - Effortless Bayesian Deep Learning

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

NeurIPS 2021
Paper

Github
Learnable Uncertainty under Laplace Approximations

Agustinus Kristiadi, Matthias Hein, Philipp Hennig

UAI 2021
Long Talk

Paper

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

Agustinus Kristiadi, Matthias Hein, Philipp Hennig

ICML 2020
Paper
Incorporating Literals into Knowledge Graph Embeddings

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

ISWC 2019
Paper

Github
Improving Response Selection in Multi-turn Dialogue Systems

Debanjan Chaudhuri, Agustinus Kristiadi, Jens Lehmann, Asja Fischer

CoNLL 2018
Paper

Github
Parallel Particle Swarm Optimization for Image Segmentation

Agustinus Kristiadi, Pranowo, Paulus Mudjihartono

Digital Enterprise and Information Systems 2013
Paper

Github
Parallel Particle Swarm Optimization for Image Segmentation

Agustinus Kristiadi, Pranowo, Paulus Mudjihartono

Digital Enterprise and Information Systems 2013
Paper

Github

Journal

Deep Convolutional Level Set Method for Image Segmentation

Agustinus Kristiadi, Pranowo

Journal of ICT Research and Applications 11(3) 2017
Paper

Github

Workshop

A Critical Look At Tokenwise Reward-Guided Text Generation

Ahmad Rashid, Ruotian Wu, Julia Grosse, Agustinus Kristiadi*, Pascal Poupart*

ICML Workshop on Foundation Models in the Wild 2024
Paper
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 2024
Paper

Github
Uncertainty-Guided Optimization on Large Language Model Search Trees

Julia Grosse, Ruotian Wu, Ahmad Rashid, Philipp Hennig, Pascal Poupart, Agustinus Kristiadi

AABI 2024
Paper

Github
If Optimizing for General Parameters in Chemistry Is Useful, Why Is It Hardly Done?

Stefan Schmid, Ella Rajaonson, Cher-Tian Ser, Mohammad Haddadnia, Shi Xuan Leong, Alan Aspuru-Guzik, Agustinus Kristiadi, Kjell Jorner, Felix Strieth-Kalthoff

AI4Mat - NeurIPS 2024
Paper
Dimension Deficit: Is 3D a Step Too Far for Optimizing Molecules?

Andres Guzman Cordero, Luca Thiede, Gary Tom, Alan Aspuru-Guzik, Felix Strieth-Kalthoff, Agustinus Kristiadi

AI4Mat - NeurIPS 2024
Paper
Promises and Pitfalls of the Linearized Laplace in Bayesian Optimization

Agustinus Kristiadi, Alexander Immer, Runa Eschenhagen, Vincent Fortuin

AABI 2023
Paper

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

Runa Eschenhagen, Erik Daxberger, Philipp Hennig, Agustinus Kristiadi

NeurIPS Workshop of Bayesian Deep Learning 2021
Paper
Predictive Uncertainty Quantification with Compound Density Networks

Agustinus Kristiadi, Sina Daeubener, Asja Fischer

NeurIPS Workshop of Bayesian Deep Learning 2019
Paper

Github

Preprint

On the Disconnect Between Theory and Practice of Overparametrized Neural Networks

Jonathan Wenger, Felix Dangel, Agustinus Kristiadi

ArXiv 2023
Paper