Predictive coding learns more sample-efficiently than backpropagation because its updates align better with output prediction errors in deep linear networks, with exact conditions for optimal alignment derived.
Optimizing neural networks with kronecker-factored approx- imate curvature
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
fields
cs.LG 5years
2026 5roles
background 3polarities
background 3representative citing papers
FGN is a positive semidefinite under-approximation of the multiclass GGN obtained by exact decomposition into true-vs-rest and within-competitor terms, exact for binary classification and implemented via matrix-free conjugate gradient on a whitened row-space system.
Gauss-Newton descent whitens errors by projecting Newton directions or gradients onto the tangent space, replacing JJ^T with the identity and removing parameterization distortions that affect Newton descent.
AdaPreLoRA pairs the Adafactor diagonal Kronecker preconditioner on the full weight matrix with a closed-form factor-space solve that selects the update minimizing an H_t-weighted imbalance, yielding competitive results on GPT-2, Mistral-7B, Qwen2-7B and diffusion personalization tasks.
MuonEq introduces pre-orthogonalization equilibration schemes that improve Muon optimizer performance during large language model pretraining.
citing papers explorer
-
Understanding Sample Efficiency in Predictive Coding
Predictive coding learns more sample-efficiently than backpropagation because its updates align better with output prediction errors in deep linear networks, with exact conditions for optimal alignment derived.
-
Fast Gauss-Newton for Multiclass Cross-Entropy
FGN is a positive semidefinite under-approximation of the multiclass GGN obtained by exact decomposition into true-vs-rest and within-competitor terms, exact for binary classification and implemented via matrix-free conjugate gradient on a whitened row-space system.
-
Error whitening: Why Gauss-Newton outperforms Newton
Gauss-Newton descent whitens errors by projecting Newton directions or gradients onto the tangent space, replacing JJ^T with the identity and removing parameterization distortions that affect Newton descent.
-
AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
AdaPreLoRA pairs the Adafactor diagonal Kronecker preconditioner on the full weight matrix with a closed-form factor-space solve that selects the update minimizing an H_t-weighted imbalance, yielding competitive results on GPT-2, Mistral-7B, Qwen2-7B and diffusion personalization tasks.
-
MuonEq: Balancing Before Orthogonalization with Lightweight Equilibration
MuonEq introduces pre-orthogonalization equilibration schemes that improve Muon optimizer performance during large language model pretraining.