REVIEW 1 cited by
On the Variance of Unbiased Online Recurrent Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
On the Variance of Unbiased Online Recurrent Optimization
read the original abstract
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.
Forward citations
Cited by 1 Pith paper
-
A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks
A framework unifies recent online RNN training algorithms along four axes and demonstrates performance clustering on synthetic tasks, indicating that gradient alignment is insufficient to explain success especially fo...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.