arXiv (All)
open access
Rare Gate Disagreements Can Limit Plasticity: When Gradient Flow Mispredicts Finite-Batch SGD
Population gradient flow is a common tool for reasoning about how neural networks adapt, including after pretraining. We show that it can mispredict finite-batch stochastic gradient descent (SGD) qualitatively, and we trace the discrepancy to a specific mechanism. In a two-unit ReLU regression, a so
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
- Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs#997322
- Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less#168301
- On the Plasticity Collapse in Continual Machine Unlearning#790270
- Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift#1326319
- UnAct: Gradient-Free Unlearning via Targeted Activation Intervention#1200077
Record · ID 1248755
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