method · first seen 5 Oct 2026
natural gradient descent
Also: NGD, natural gradient, natural gradient flow, natural policy gradient
Optimization that preconditions gradient steps with the Fisher information metric to follow steepest descent on the statistical manifold.
Mentions per week
PapersCodeDiscussion
Earliest sources
- How Inefficient Is Natural Gradient Descent? From Exact Optimality to Θ( \sqrt{ \log d } ) DivergencePapers · 5 Oct 2026 · Guni Sharon, Alan Kuhnle
- Inference and learning in sparse autoencoders as natural gradient flowPapers · 5 Oct 2026 · Hadi Vafaii, Tejas Rao, David Chanin, Thomas Fel, Jacob L. Yates, Bruno Olshause…
- LOCU: Lowdin-Orthogonalized Constraint Updates for Multi-Constraint Policy OptimizationPapers · 19 Oct 2026 · Joonyoung Lim, Younghwan Yoo
- Last-Iterate Convergence for Constrained MDPs: From Dual Descent to Primal-DualPapers · 29 Oct 2026 · Michael Lu, Max Qiushi Lin, Mo Chen, Sharan Vaswani
- Natural Gradient Learning in Predictive Coding through Lateral CircuitsPapers · 12 Nov 2026 · Lhea Beumer, Sander de Haan, Niclas Pokel, Pau Vilimelis Aceituno, Benjamin F. G…
- Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEsPapers · 13 Nov 2026 · Stanislas Pamela, Nicolas Pailliez, Emmanuel Franck, Victor Michel-Dansac, Laure…
Latest sources
- Fuse-PINN: Combining Finite Element Methods and Physics-Informed Neural Networks to enable massively parallel simulations of non-linear PDEsPapers · 13 Nov 2026 · Stanislas Pamela, Nicolas Pailliez, Emmanuel Franck, Victor Michel-Dansac, Laure…
- Natural Gradient Learning in Predictive Coding through Lateral CircuitsPapers · 12 Nov 2026 · Lhea Beumer, Sander de Haan, Niclas Pokel, Pau Vilimelis Aceituno, Benjamin F. G…
- Last-Iterate Convergence for Constrained MDPs: From Dual Descent to Primal-DualPapers · 29 Oct 2026 · Michael Lu, Max Qiushi Lin, Mo Chen, Sharan Vaswani
- LOCU: Lowdin-Orthogonalized Constraint Updates for Multi-Constraint Policy OptimizationPapers · 19 Oct 2026 · Joonyoung Lim, Younghwan Yoo
- Inference and learning in sparse autoencoders as natural gradient flowPapers · 5 Oct 2026 · Hadi Vafaii, Tejas Rao, David Chanin, Thomas Fel, Jacob L. Yates, Bruno Olshause…
- How Inefficient Is Natural Gradient Descent? From Exact Optimality to Θ( \sqrt{ \log d } ) DivergencePapers · 5 Oct 2026 · Guni Sharon, Alan Kuhnle