AWhat changed
Trains recurrent update rules across optimization tasks, sharing a coordinatewise LSTM's parameters while retaining separate hidden states to propose gradient-history-dependent parameter steps.
Scientific scope
Trains recurrent update rules across optimization tasks, sharing a coordinatewise LSTM's parameters while retaining separate hidden states to propose gradient-history-dependent parameter steps. Meta-gradients drop optimizee second-derivative paths and optimize a finite weighted trajectory objective; transfer beyond training-task structure is empirical, not arbitrary-function convergence. LSTMs, meta-learning and earlier learned-update methods are inherited rather than newly invented.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Meta-gradients drop optimizee second-derivative paths and optimize a finite weighted trajectory objective; transfer beyond training-task structure is empirical, not arbitrary-function convergence. LSTMs, meta-learning and earlier learned-update methods are inherited rather than newly invented.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction