Skip to main content
This is a pre-production deployment of Warehouse. Changes made here affect the production instance of PyPI (pypi.python.org).
Help us improve Python packaging - Donate today!

Stochastic optimization routines for Theano

Project Description

DOWNHILL

The downhill package provides algorithms for minimizing scalar loss functions that are defined using Theano.

Several optimization algorithms are included:

All algorithms permit the use of regular or Nesterov-style momentum as well.

Quick Start: Matrix Factorization

Let’s say you have 100 samples of 1000-dimensional data, and you want to represent your data as 100 coefficients in a 10-dimensional basis. This is pretty straightforward to model using Theano: you can use a matrix multiplication as the data model, a squared-error term for optimization, and a sparse regularizer to encourage small coefficient values.

Once you have constructed an expression for the loss, you can optimize it with a single call to downhill.minimize:

import downhill
import numpy as np
import theano
import theano.tensor as TT

FLOAT = 'df'[theano.config.floatX == 'float32']

def rand(a, b):
    return np.random.randn(a, b).astype(FLOAT)

A, B, K = 20, 5, 3

# Set up a matrix factorization problem to optimize.
u = theano.shared(rand(A, K), name='u')
v = theano.shared(rand(K, B), name='v')
z = TT.matrix()
err = TT.sqr(z - TT.dot(u, v))
loss = err.mean() + abs(u).mean() + (v * v).mean()

# Minimize the regularized loss with respect to a data matrix.
y = np.dot(rand(A, K), rand(K, B)) + rand(A, B)

# Monitor during optimization.
monitors = (('err', err.mean()),
            ('|u|<0.1', (abs(u) < 0.1).mean()),
            ('|v|<0.1', (abs(v) < 0.1).mean()))

downhill.minimize(
    loss=loss,
    train=[y],
    patience=0,
    batch_size=A,                 # Process y as a single batch.
    max_gradient_norm=1,          # Prevent gradient explosion!
    learning_rate=0.1,
    monitors=monitors,
    monitor_gradients=True)

# Print out the optimized coefficients u and basis v.
print('u =', u.get_value())
print('v =', v.get_value())

If you prefer to maintain more control over your model during optimization, downhill provides an iterative optimization interface:

opt = downhill.build(algo='rmsprop',
                     loss=loss,
                     monitors=monitors,
                     monitor_gradients=True)

for metrics, _ in opt.iterate(train=[[y]],
                              patience=0,
                              batch_size=A,
                              max_gradient_norm=1,
                              learning_rate=0.1):
    print(metrics)

If that’s still not enough, you can just plain ask downhill for the updates to your model variables and do everything else yourself:

updates = downhill.build('rmsprop', loss).get_updates(
    batch_size=A, max_gradient_norm=1, learning_rate=0.1)
func = theano.function([z], loss, updates=list(updates))
for _ in range(100):
    print(func(y))  # Evaluate func and apply variable updates.
Release History

Release History

This version
History Node

0.4.0

History Node

0.3.2

History Node

0.3.1

History Node

0.3.0

History Node

0.2.2

History Node

0.2.1

History Node

0.2.0

History Node

0.1.0

Download Files

Download Files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

File Name & Checksum SHA256 Checksum Help Version File Type Upload Date
downhill-0.4.0-py2.py3-none-any.whl (24.6 kB) Copy SHA256 Checksum SHA256 3.5 Wheel Jan 12, 2017
downhill-0.4.0.tar.gz (20.0 kB) Copy SHA256 Checksum SHA256 Source Jan 12, 2017

Supported By

WebFaction WebFaction Technical Writing Elastic Elastic Search Pingdom Pingdom Monitoring Dyn Dyn DNS Sentry Sentry Error Logging CloudAMQP CloudAMQP RabbitMQ Heroku Heroku PaaS Kabu Creative Kabu Creative UX & Design Fastly Fastly CDN DigiCert DigiCert EV Certificate Rackspace Rackspace Cloud Servers DreamHost DreamHost Log Hosting