arXiv (OAI Expanded)
open access
Layer-wise Derivative Controlled Networks Achieve Competitive Accuracy and Gradient Stability Across Data Regimes
Derivative-controlled networks based on ChainzRule (CR) combine cubic polynomial layers with a lightweight forward-mode per-layer Jacobian penalty (DREG). In this second paper of a multi-part series, we evaluate the generalization properties of CR across data regimes. We ablate the shape of the DR
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
- Multiscale Renormalization of Weighted Networks#1142884
- NICE: Scale-Stable Perturbations for Graph Neural Network Explanations via Noise Corruption#628305
- GRZO: Group-Relative Zeroth-Order Optimization for Large Language Model Fine-Tuning#792759
- Finite-size effects in on-line learning of multilayer neural networks#230059
- Robust Knowledge Distillation for Resource-Constrained Applications: Evaluating Offline KD Techniques for Large–Compact Heterogeneous CNNs#448476
Record · ID 1084238
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