Fork me on GitHub

Trending arXiv

Note: this version is tailored to @Smerity - though you can run your own! Trending arXiv may eventually be extended to multiple users ...


On the Variance of Unbiased Online Recurrent Optimization

Tim Cooijmans, James Martens

The recently proposed Unbiased Online Recurrent Optimization algorithm (UORO, arXiv:1702.05043) uses an unbiased approximation of RTRL to achieve fully online gradient-based learning in RNNs. In this work we analyze the variance of the gradient estimate computed by UORO, and propose several possible changes to the method which reduce this variance both in theory and practice. We also contribute significantly to the theoretical and intuitive understanding of UORO (and its existing variance reduction technique), and demonstrate a fundamental connection between its gradient estimate and the one that would be computed by REINFORCE if small amounts of noise were added to the RNN's hidden units.

Captured tweets and retweets: 1