Skip to main content

Stochastic optimization routines for Theano

Project description


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 -, v))
loss = err.mean() + abs(u).mean() + (v * v).mean()

# Minimize the regularized loss with respect to a data matrix.
y =, 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()))

    batch_size=A,                 # Process y as a single batch.
    max_gradient_norm=1,          # Prevent gradient explosion!

# 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 ='rmsprop',

for metrics, _ in opt.iterate(train=[[y]],

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 ='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.

More Information



Mailing list:!forum/downhill-users

Project details

Download files

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

Source Distribution

downhill-0.4.0.tar.gz (20.0 kB view hashes)

Uploaded source

Built Distribution

downhill-0.4.0-py2.py3-none-any.whl (24.6 kB view hashes)

Uploaded 3 5

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page