AI Paper Atlas

Research map / Bandits and online learning / Online convex optimization and games

A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks

Owen Marschall, Kyunghyun Cho, Cristina Savin

JMLR 2020 · Bandits and online learning › Online convex optimization and games · approach: Online learning with feedback graphs · 42 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use stochastic rank-1 approximations (UORO, R-KF-RTRL) instead of deterministic onesonline RNN training · Add and Mimic tasksmean gradient alignment with RTRL: UORO 0.043 on Add and 0.084 on Mimic; R-KF-RTRL 0.050 on Add and 0.092 on MimicHurt
use KF-RTRL instead of exact RTRLonline RNN training · Add tasktraining lossNo clear effect
learn A and alpha in KeRNL instead of fixed RFLO feedbackRFLO · Add tasktraining lossHurt
initialize recurrent W as orthogonal or Gaussian rather than symmetric or diagonal (ablation)RFLO · Add taskability to learnImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy