Gradient-based meta-learning over neural state-space models adapts a model to a new dynamical system with little target data and few gradient steps, with physical constraints embedded in the architecture.
A New First-Order Meta-Learning Algorithm with Convergence Guarantees
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Learning new tasks by drawing on prior experience gathered from other (related) tasks is a core property of any intelligent system. Gradient-based meta-learning, especially MAML and its variants, has emerged as a viable solution to accomplish this goal. One problem MAML encounters is its computational and memory burdens needed to compute the meta-gradients. We propose a new first-order variant of MAML that we prove converges to a stationary point of the MAML objective, unlike other first-order variants. We also show that the MAML objective does not satisfy the smoothness assumption assumed in previous works; we show instead that its smoothness constant grows with the norm of the meta-gradient, which theoretically suggests the use of normalized or clipped-gradient methods compared to the plain gradient method used in previous works. We validate our theory on a synthetic experiment.
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Meta-Learning for Physically-Constrained Neural System Identification
Gradient-based meta-learning over neural state-space models adapts a model to a new dynamical system with little target data and few gradient steps, with physical constraints embedded in the architecture.