arXiv (All)
open access
Exact Tail Laws for Nonlinear SGD with Infinite-Variance Gradients
With infinite-variance gradient noise, SGD can have infinite expected excess objective even when most iterates are close to the optimum. We characterize its accuracy through exact first-order tail probabilities for the last iterate of nonlinear, constant-stepsize SGD. For regularly varying innovatio
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
- Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping#1234952
- Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient Clipping#1227312
- On the Last-Iterate Convergence of Clipped Gradient Methods#1356362
- An error bound-based convergence analysis framework for a class of randomized algorithms#798805
- An error bound-based convergence analysis framework for a class of randomized algorithms#797391
Record · ID 1388122
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