Name: Formerly: Harvard Intelligent Probabilistic Systems Group -- Now at Princeton
Type: Organization
Bio: Ryan Adams' research group. Formerly at Harvard, now at Princeton. New Github repositories here: https://github.com/PrincetonLIPS
Location: Princeton University, Princeton, NJ
Blog: https://lips.cs.princeton.edu
Formerly: Harvard Intelligent Probabilistic Systems Group -- Now at Princeton's Projects
LaTeX package for randomizing author order based on a public seed.
Efficiently computes derivatives of numpy code.
Gradient-based variational autoencoders to generate class-conditional natural images.
Code for performing Bayesian regression with structured sparsity from a Gaussian field.
MCMC for the Dark Energy Spectroscopic Instrument
Implementation of an algorithm for Markov chain Monte Carlo with data subsampling
A Numpy wrapper that adds a gpufloat32 dtype to Numpy.
Library of common tools for machine learning research.
Github page for Harvard Intelligent Probabilistic Systems Group
Exploring differentiation with respect to hyperparameters
Kayak is a library for automatic differentiation with applications to deep neural networks.
Linefeed-delimited pickle for Unix-style piping of arbitrary Python data
A simple abstraction layer for matrix computations in Python, making it easy to switch between CPU and NVIDIA or Intel coprocessors.
Fastidious accounting of entropy streams into and out of optimization and sampling algorithms.
A project to enable optimization of molecules by transforming them to and from a continuous representation.
Convolutional nets which can take molecular graphs of arbitrary size as input.
A python framework for fitting biophysical models to optically recorded neural signals.
Dependent multinomials made easy: stick-breaking with the Pólya-gamma augmentation
Implementation in C and Theano of the method Probabilistic Backpropagation for scalable Bayesian inference in deep neural networks.
Spearmint Bayesian optimization codebase
Website for viewing a git repo as a lab notebook. Figures and text files can be included with markdown-like syntax.