Michael Shvartsman's repositories
symbolic-mat-diff
Symbolic matrix differentiation using sympy
vae-tf-bootcamp
VAE+Tensorflow bootcamp
axcpt-psiturk-coffeescript
Implementation of AX-CPT in Coffeescript (with psiTurk)
aepsych
AEPsych is a tool for adaptive experimentation in psychophysics and perception research, built on top of gpytorch and botorch.
Ax
Adaptive Experimentation Platform
fairseq2
FAIR Sequence Modeling Toolkit 2
hydra
Hydra is a framework for elegantly configuring complex applications
matnormal_aistats2018
experiments for matnormal paper AISTATS2018
mshvartsman.github.io
Mike's website
numpy
Numpy main repository
optunity
optimization routines for hyperparameter tuning
PNISpock-split-run-combine
Wrapper scripts for typical embarrasingly parallel workflows on PNI's spock cluster
pymdptoolbox
Markov Decision Process (MDP) Toolbox for Python
pystan-cache
A PyStan wrapper that caches compiled models
qmk_firmware
Open-source keyboard firmware for Atmel AVR and Arm USB families
rand_tensor
This code package generates random tensors with user specified marginal means and covariances from one of two optional distributions. The first is the maximum-entropy-distribution with the specified marginal means and covariances. The second is the tensor-normal-distribution with the specified means and covariances.
RunDEMC
Python library for running DEMC on hierarchical models.
stan
Stan development repository (home page is linked below). The master branch contains the current release. The develop branch contains the latest stable development. See the Developer Process Wiki for details.
whoops_yall
Whoops ya'll is a psiTurk compatible experiment for paying people when an experiment goes badly for some reason. You enter the workerIds of people who you owe money to and can reject all others. Payment is handled quickly and easily via psiTurk's command line features. When you make a whoops, use "whoops ya'll"