arXiv (All)
open access
High-Probability Convergence of Clipped SGD under Heavy-Tailed Noise and $(L_0,L_1)$-Smoothness
Gradient clipping is widely used in language-model training to control heavy-tailed gradient noise and can improve convergence guarantees over stochastic gradient descent (SGD) under $(L_0,L_1)$-smoothness. Under these joint conditions, a central challenge is to obtain high-probability guarantees wi
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
- Almost Sure Convergence Analysis of Stochastic Gradient Methods with Clipping and Additive Noise#1012349
- Cached LLM Probability Retrieval for Speech Recognition#617696
- Cached LLM Probability Retrieval for Speech Recognition#617196
- Adam under Generalized Smoothness with Second-Moment-Type Stochastic Gradients#1142096
- How Far is Adam from Natural Gradient Descent?#1154627
Record · ID 1141417
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