Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guarantees

arXiv 2603.22355•23eee20b23360419b36222c2619442204501db40e2ce85005d703d2b2bc29927
Bayesian-inferenceLaplace-approximationPAC-BayesRLHFRashomon-setSPDEactive-learningconvergencedeep-learningdifferential-privacye-valuesgeneralizationinformation-theoryinterpretabilityknowledge-distillationlarge-language-modelslow-rankmachine-learningmodel-evaluationpost-selectionposterior-contractionprivacytheoryvariational-inferencevine-copulas

Paper metadata

arXiv ID
2603.22355
Version
Not specified by this published record
Category
Statistics — Machine Learning (stat.ML)

The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.

Evidence and limitations

Source ID
arxiv_stat_ml
Record identifier
23eee20b23360419b36222c2619442204501db40e2ce85005d703d2b2bc29927
Enrichment time
2026-03-25T07:23:54Z
AI-assisted enrichment
Yes

This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.