Code for "Deep Convolutional Networks as shallow Gaussian Processes"
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Deep Convolutional Networks as shallow Gaussian Processes

Note for reviewers: there is identifying information in the commit history.

Code for "Deep Convolutional Networks as shallow Gaussian Processes" (OpenReview, by Anonymous Authors.


This package has been tested only with python 3.5 and 3.6.

First, you need to install the package in developer mode. This will download and install all necessary python dependencies:

cd convnets-as-gps
# optionally: pip install --user -e .
pip install -e .

If you have an "old" CPU, this might crash and return "Illegal Instruction". This is because recent versions of Tensorflow come with AVX instructions enabled. Install tensorflow 1.5.0 to fix this.

Running the experiments

Easy way to run all the experiments: read/run run_all_experiments.bash

All the experiments in the paper are run in a two-stage process:

  1. Run or, to compute kernel matrices and save them to disk in a working directory. Disk space required: about 15GB for 1 run. Run python3 --help for detailed information, but here are example invocations:
python3 --seed=<random seed> --n_max=200 --path=/path/to/working/directory
python3 --n_gpus=1 --n_max=200 --path=/path/to/working/directory

In particular, the n_max flag determines how many training examples your GPU processes simultaneously. The memory requirements scale roughly proportionally to n_max^2, adjust the number for your particular hardware.

You might run into "Matrix is singular" errors. In my testing, those can be removed by reducing n_max. This must be a bug of some kind in the libraries that I use (Tensorflow maybe?), but I have no skill or time to acquire the skill to troubleshoot it. Just reduce n_max.

  1. Run to invert the kernel matrix and calculate test results. This requires a lot of CPU RAM memory, at least enough to hold the matrix to invert with 64-bit precision. For MNIST, the main kernel matrix is ~12GB, so you need ~24GB of memory to maintain a decent speed. I'm sure there's a way to do the inverse reasonably fast and more memory-efficiently, but that would take quite a bit of development time.

BibTex citation record

Redacted. Please don't look in the commit history.