Agustinus Kristiadi (@wiseodd)
github

wiseodd

Twitter logo Share LinkedIn logo Share Facebook logo Share

Top repositories

1

generative-models

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
Python
7,244
star
2

MCMC

Collection of Monte Carlo (MC) and Markov Chain Monte Carlo (MCMC) algorithms applied on simple examples.
Python
339
star
3

hipsternet

All the hipster things in Neural Net in a single repo
Python
285
star
4

controlled-text-generation

Reproducing Hu, et. al., ICML 2017's "Toward Controlled Generation of Text"
Python
243
star
5

probabilistic-models

Collection of probabilistic models and inference algorithms
Python
240
star
6

natural-gradients

Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)
Python
131
star
7

last_layer_laplace

Last-layer Laplace approximation code examples
Jupyter Notebook
75
star
8

cnn-levelset

Source code for Kristiadi and Pranowo, 2017's "Deep Convolutional Level Set Method for Image Segmentation"
Python
58
star
9

wiseodd.github.io

wiseodd's blog
JavaScript
39
star
10

lula

Companion code for the paper "Learnable Uncertainty under Laplace Approximations" (UAI 2021).
Python
17
star
11

compound-density-networks

Implementation of: Kristiadi, Agustinus, and Asja Fischer. "Predictive Uncertainty Quantification with Compound Density Networks." (2019).
Python
15
star
12

cuda-pso

Comparison between CUDA and CPU for PSO using 3-dimensional Levy function as test case
C++
12
star
13

bayesian_ood_training

Jupyter Notebook
9
star
14

laplace-bayesopt

Laplace approximated BNN surrogate for BoTorch
Python
8
star
15

swarm-image-segmenter

Image segmentation using swarm intelligence, accelerated using GPGPU (CUDA)
C++
7
star
16

lapeft-bayesopt

Discrete Bayesian optimization with LLMs, PEFT finetuning methods, and the Laplace approximation.
Python
7
star
17

phd_thesis_template

TeX
4
star
18

rgpr

Companion code for the paper "An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence" (NeurIPS 2021)
Python
4
star
19

two-funds-rebalancer

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.
Python
2
star