"Approximation of Log-Partition Function in Policy Mirror Descent Induces ..."

Zhenghao Xu et al. (2026)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2602.05933

access: open

type: Informal or Other Publication

metadata version: 2026-03-19

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2602-05933
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2602-05933
Zhenghao Xu, Qin Lu, Changlong Yu, Tuo Zhao:
Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training. CoRR abs/2602.05933 (2026)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.