Dimension-Free PAC-Bayes Generalization for Deep Neural Networks via Dirichlet Processes AEYX7SEVBG
| URI | m2://res/AEYX7SEVBG |
|---|---|
| Kind | preprint |
| Creators | Sumit Vashishtha |
| Date | 2026-10-15 |
| Subjects | arxiv stat.ML, arxiv cs.LG, arxiv math.ST, arxiv stat.TH |
| Scope | border |
Expressions
e1: version, preprint
| Date | 2026-10-15 |
|---|---|
| Ids | arXiv 2610.21340 |
Items in this resource
The mentions of the inventory that name this resource. Each name links to the card of its inventory row.
| Item | Kind | Where | Source |
|---|---|---|---|
| Optimal Partition Scale and Minimax Trade-Off | statement | lemma 1 | arxiv |
| Analytical Partition Divergence | statement | theorem 3 | arxiv |
| Dirichlet Process | definition | definition 1 | arxiv |
| 9P0FWJP8H6 | statement | theorem 1 | arxiv |
| Data-Processing Invariance | statement | theorem 2 | arxiv |
| Dimension-Free Projected DP-PAC-Bayes Certificate | statement | theorem 4 | arxiv |
| Measurability of Optimization Mappings under the Weak Topology | statement | proposition 2 | arxiv |
| Metric Entropy Manifold Adaptation | statement | theorem 5 | arxiv |
| Weight-Space Divergence Scaling under Deep Compositions | statement | proposition 1 | arxiv |
Catalogue records
- arxiv: 2610.21340 (work)