arXiv (All)
open access
Why Adaptive Optimizers Underestimate Rare Tokens
In the softmax output layer, a rare token receives a small positive logit gradient on most steps and a much larger negative gradient on the few steps when it is the target. SGD simply adds these contributions. Coordinate-wise adaptive methods such as Adam, RMSProp, and sign descent instead divide ea
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
- How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations#1141558
- Mind the Gap: The Disconnect Between Synthetic and Natural Edge Weights in Parallel Single-Source Shortest Path#821964
- LoRA-GA$^2$: Low Rank Adaptation with Multi-step Gradient Adaptive Alignment#821989
- dSTAR: Straggler Tolerant and Byzantine Resilient Distributed SGD#1035272
- Beneath the Tokens: A Performance Engineering Study of Multi-Token Prediction in GPU-Accelerated LLM Inference#1129785
Record · ID 1141856
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