Approximation Property of Dropout Neural Networks: Sobolev Rates and Confidence Bounds
arXiv 2610.02253v1•e49a3afa2101b3bcbe62518ecdc1c4f26e9feac01ccbc12c1d007dee40884e49
Paper metadata
- arXiv ID
- 2610.02253
- Version
- v1
- Category
- cs.LG, cs.NA, math.NA
- Authors
- Jia-He Yao
- Publication date
- 2026-10-05T04:00:00Z
- Source identifier
- 2610.02253v1
- Public record ID
- record:sha256:e49a3afa2101b3bcbe62518ecdc1c4f26e9feac01ccbc12c1d007dee40884e49
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- e49a3afa2101b3bcbe62518ecdc1c4f26e9feac01ccbc12c1d007dee40884e49
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.