PBSD derives a reward-reweighted teacher distribution as the analytic optimum of a reward-regularized objective, yielding better stability and performance than KL-based self-distillation on math reasoning and tool-use tasks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
DADA is a parameter-free dual averaging method for convex optimization that adapts to local function growth and applies to nonsmooth, smooth, Holder-smooth, and other classes for both constrained and unbounded domains without prior knowledge of iteration count or accuracy.
citing papers explorer
-
Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization
PBSD derives a reward-reweighted teacher distribution as the analytic optimum of a reward-regularized objective, yielding better stability and performance than KL-based self-distillation on math reasoning and tool-use tasks.
-
DADA: Dual Averaging with Distance Adaptation
DADA is a parameter-free dual averaging method for convex optimization that adapts to local function growth and applies to nonsmooth, smooth, Holder-smooth, and other classes for both constrained and unbounded domains without prior knowledge of iteration count or accuracy.