wiseodd

vim-paper

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

rustlox

Lox interpreter in Rust --- following the Crafting Interpreters book

lapeft-bayesopt

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

laplace-bayesopt

Laplace approximated BNN surrogate for BoTorch

rustlings

wiseodd.github.io

wiseodd's blog

ziglings

curvlinops

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

rust-playground

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

synthetic_accessibility_project

Project files for synthetic accessibility project.

wiseodd

generative-models

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

asdl

ASDL: Automatic Second-order Differentiation Library for PyTorch

molskill

Extracting medicinal chemistry intuition via preference machine learning

bayesian_ood_training

nanoGPT

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

olympus

Olympus: a benchmarking framework for noisy optimization and experiment planning

phd_thesis_template

compound-density-networks

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

laplace-redux

Laplace Redux -- Effortless Bayesian Deep Learning

rgpr

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

last_layer_laplace

Last-layer Laplace approximation code examples

PyHessian

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

lula

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

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.

pytorch-classification

Classification with PyTorch.

probabilistic-models

Collection of probabilistic models and inference algorithms

PriorNetworks

higher_order_invariance

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

natural-gradients

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