arXiv (All)
open access
Approaching Backpropagation Accuracy with Weight Perturbation on MNIST
Weight perturbation (WP) estimates learning directions from random parameter perturbations and a scalar change in loss, without backpropagating derivatives. We examine how batch size, training duration, and estimator stabilization affect its attainable accuracy in fully connected MNIST networks. In
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- The Multiple Timescales of Gradient Descent on the Edge of Stability: A Perturbative Derivation of the Central Flow#821022
- Adaptive back-propagation in on-line learning of multilayer networks#978333
- Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy#1200917
- Stability and Generalization of Straight-Through Estimators for Training Two-Layer Quantized Neural Networks#974007
- Distilling Graph Geometry: Knowledge Gap from GNNs to MLPs#1234945
Record · ID 1357320
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive