Pinned Repositories
Laplace
Laplace approximations for Deep Learning.
controlled-text-generation
Reproducing Hu, et. al., ICML 2017's "Toward Controlled Generation of Text"
generative-models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
hipsternet
All the hipster things in Neural Net in a single repo
lapeft-bayesopt
Discrete Bayesian optimization with LLMs, PEFT finetuning methods, and the Laplace approximation.
laplace-bayesopt
Laplace approximated BNN surrogate for BoTorch
MCMC
Collection of Monte Carlo (MC) and Markov Chain Monte Carlo (MCMC) algorithms applied on simple examples.
phd_thesis_template
rustlox
Lox interpreter in Rust --- following the Crafting Interpreters book
wiseodd.github.io
wiseodd's blog
wiseodd's Repositories
wiseodd/generative-models
Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.
wiseodd/probabilistic-models
Collection of probabilistic models and inference algorithms
wiseodd/natural-gradients
Collection of algorithms for approximating Fisher Information Matrix for Natural Gradient (and second order method in general)
wiseodd/last_layer_laplace
Last-layer Laplace approximation code examples
wiseodd/wiseodd.github.io
wiseodd's blog
wiseodd/lula
Companion code for the paper "Learnable Uncertainty under Laplace Approximations" (UAI 2021).
wiseodd/compound-density-networks
Implementation of: Kristiadi, Agustinus, and Asja Fischer. "Predictive Uncertainty Quantification with Compound Density Networks." (2019).
wiseodd/lapeft-bayesopt
Discrete Bayesian optimization with LLMs, PEFT finetuning methods, and the Laplace approximation.
wiseodd/bayesian_ood_training
wiseodd/laplace-bayesopt
Laplace approximated BNN surrogate for BoTorch
wiseodd/phd_thesis_template
wiseodd/rgpr
Companion code for the paper "An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence" (NeurIPS 2021)
wiseodd/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.
wiseodd/higher_order_invariance
Code for "Accelerating Natural Gradient with Higher-Order Invariance"
wiseodd/nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
wiseodd/rust-playground
Trying out Rust and `tch-rs` (Rust binding for `libtorch`)
wiseodd/rustlox
Lox interpreter in Rust --- following the Crafting Interpreters book
wiseodd/asdl
ASDL: Automatic Second-order Differentiation Library for PyTorch
wiseodd/curvlinops
scipy linear operators for the Hessian, Fisher/GGN, and more in PyTorch
wiseodd/laplace-redux
Laplace Redux -- Effortless Bayesian Deep Learning
wiseodd/molskill
Extracting medicinal chemistry intuition via preference machine learning
wiseodd/olympus
Olympus: a benchmarking framework for noisy optimization and experiment planning
wiseodd/PriorNetworks
wiseodd/PyHessian
PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks
wiseodd/pytorch-classification
Classification with PyTorch.
wiseodd/rustlings
wiseodd/synthetic_accessibility_project
Project files for synthetic accessibility project.
wiseodd/vim-paper
A light theme for (Neo)Vim, based on the colour of paper as found in various notebooks.
wiseodd/wiseodd
wiseodd/ziglings