mshvartsman
Research Scientist @ FAIR (Meta). Theoretical unification and tool-building are my jams.
@facebookresearch Seattle, WA
Pinned Repositories
aepsych
AEPsych is a tool for adaptive experimentation in psychophysics and perception research, built on top of gpytorch and botorch.
axcpt-jspsych-psiturk
Implementation for running AX-CPT using jsPsych and psiTurk
axcpt-psiturk-coffeescript
Implementation of AX-CPT in Coffeescript (with psiTurk)
cddm
Code for a theory of decision making under dynamic context
hyperopt
Distributed Asynchronous Hyperparameter Optimization in Python
PyMEG
Python scripts for analysing MMF data acquired using MEG.
symbolic-mat-diff
Symbolic matrix differentiation using sympy
vae-tf-bootcamp
VAE+Tensorflow bootcamp
wfpt_py
Expressions relating to wiener first passage times (aka "diffusion decision model" in psychology)
mshvartsman's Repositories
mshvartsman/symbolic-mat-diff
Symbolic matrix differentiation using sympy
mshvartsman/vae-tf-bootcamp
VAE+Tensorflow bootcamp
mshvartsman/wfpt_py
Expressions relating to wiener first passage times (aka "diffusion decision model" in psychology)
mshvartsman/hyperopt
Distributed Asynchronous Hyperparameter Optimization in Python
mshvartsman/axcpt-psiturk-coffeescript
Implementation of AX-CPT in Coffeescript (with psiTurk)
mshvartsman/cddm
Code for a theory of decision making under dynamic context
mshvartsman/aepsych
AEPsych is a tool for adaptive experimentation in psychophysics and perception research, built on top of gpytorch and botorch.
mshvartsman/Ax
Adaptive Experimentation Platform
mshvartsman/brainiak
Brain Imaging Analysis Kit
mshvartsman/fairseq2
FAIR Sequence Modeling Toolkit 2
mshvartsman/gpytorch
A highly efficient and modular implementation of Gaussian Processes in PyTorch
mshvartsman/hddm
HDDM is a python module that implements Hierarchical Bayesian parameter estimation of Drift Diffusion Models (via PyMC).
mshvartsman/hydra
Hydra is a framework for elegantly configuring complex applications
mshvartsman/matnormal_aistats2018
experiments for matnormal paper AISTATS2018
mshvartsman/mshvartsman.github.io
Mike's website
mshvartsman/numpy
Numpy main repository
mshvartsman/optunity
optimization routines for hyperparameter tuning
mshvartsman/PNISpock-split-run-combine
Wrapper scripts for typical embarrasingly parallel workflows on PNI's spock cluster
mshvartsman/pyEPABC
A Python implementation of EP-ABC for likelihood-free, probabilistic inference.
mshvartsman/pymanopt
Python toolbox for optimization on manifolds with support for automatic differentiation
mshvartsman/pymdptoolbox
Markov Decision Process (MDP) Toolbox for Python
mshvartsman/pystan-cache
A PyStan wrapper that caches compiled models
mshvartsman/qmk_firmware
Open-source keyboard firmware for Atmel AVR and Arm USB families
mshvartsman/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.
mshvartsman/rPython
:exclamation: This is a read-only mirror of the CRAN R package repository. rPython — Package Allowing R to Call Python. Homepage: http://rpython.r-forge.r-project.org/
mshvartsman/RunDEMC
Python library for running DEMC on hierarchical models.
mshvartsman/RWiener
Clone of RWiener repository on SF: https://sourceforge.net/projects/rwiener/
mshvartsman/SRM
Shared Response Model (SRM) of NIPS 2015
mshvartsman/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.
mshvartsman/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"