Multi-iteration Stochastic Estimator
Project description
Multi-iteration Stochastic Estimator
The multi-iteration stochastic estimator (MICE) is an estimator of gradients to be used in stochastic optimization. It uses control-variates to build a hierarchy of iterations, adptively sampling to keep the statistical variance below tolerance in an optimal fashion, cost-wise. The tolerance on the statistical error decreases proportionally to the square of the gradient norm, thus, SGD-MICE converges linearly in strongly convex L-smooth functions.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
mice-0.1.4.tar.gz
(203.8 kB
view hashes)
Built Distribution
mice-0.1.4-py3-none-any.whl
(23.6 kB
view hashes)