Agustinus Kristiadi

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

A Python collection of 20+ GAN variants and 5 Variational Autoencoder implementations in PyTorch and TensorFlow, useful for learning generative AI by running and comparing each model.

Collection of Monte Carlo (MC) and Markov Chain Monte Carlo (MCMC) algorithms applied on simple examples.

All the hipster things in Neural Net in a single repo

Collection of probabilistic models and inference algorithms

Reproducing Hu, et. al., ICML 2017's "Toward Controlled Generation of Text"

Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)

Last-layer Laplace approximation code examples

A very opiniated publication-ready plotting library

Source code for Kristiadi and Pranowo, 2017's "Deep Convolutional Level Set Method for Image Segmentation"

Discrete Bayesian optimization with LLMs, PEFT finetuning methods, and the Laplace approximation.

Companion code for the paper "Learnable Uncertainty under Laplace Approximations" (UAI 2021).

Implementation of: Kristiadi, Agustinus, and Asja Fischer. "Predictive Uncertainty Quantification with Compound Density Networks." (2019).

Comparison between CUDA and CPU for PSO using 3-dimensional Levy function as test case

Laplace approximated BNN surrogate for BoTorch

No description.

Image segmentation using swarm intelligence, accelerated using GPGPU (CUDA)

Official experiment code for the "Sober Look at LLMs for Material Discovery" paper.

No description.

Companion code for the paper "An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence" (NeurIPS 2021)

Given your current portfolio value, desired allocation after rebalancing, and the amount of cash you have, this script will output how much of your cash should be used to buy stock/bonds (in percent). Only works for portfolios with two funds, e.g. the Couch Potato and classic two-funds 60-40 portfolios.

No description.

AOC 2025 solutions in Roc

No description.

Lox compiler written in Zig

Agustinus' Advent of Code 2024 Solutions in Gleam

No description.

The simplest, fastest repository for training/finetuning medium-sized GPTs.

MA-INF 4222: NLP Lab (University of Bonn)

Code for "Accelerating Natural Gradient with Higher-Order Invariance"

pytorch implementation of fast-neural-style

LaTeX style file for the Symposium of Probabilistic Machine Learning (ProbML; formerly AABI)

Course website for Western's CS9840

My NixOS configurations

Implementations of treesearch algorithms on toy, random tree MDPs.

ASDL: Automatic Second-order Differentiation Library for PyTorch

Advent of Code 2016 in OCaml

Advent of Code 2015 solutions in Rust

My solution to https://exercism.org/tracks/gleam

No description.

🎁 Gleam's standard library

scipy linear operators for the Hessian, Fisher/GGN, and more in PyTorch

No description.

Lox interpreter in Rust

TUI for the Slurm Workload Manager

A launch point for your personal nvim configuration

No description.

Trying out Rust and `tch-rs` (Rust binding for `libtorch`)

Project files for synthetic accessibility project.

Extracting medicinal chemistry intuition via preference machine learning

A light theme for (Neo)Vim, based on the colour of paper as found in various notebooks.

Olympus: a benchmarking framework for noisy optimization and experiment planning

Classification with PyTorch.

No description.

PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

Laplace Redux -- Effortless Bayesian Deep Learning

Datasets, Transforms and Models specific to Computer Vision

GUI frontend for image segmentation using PSO and CUDA, using Qt.

Python module to compute the RESCAL tensor factorization