Sub-network Laplace approximations always underestimate an idealized predictive variance, and the proposed gradient- and greedy-based parameter selection rules provably close that gap better than existing heuristics.
arXiv preprint arXiv:2404.02649 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 2roles
other 1polarities
unclear 1representative citing papers
MetaSD integrates multiple heterogeneous drafters into speculative decoding, dynamically selecting them via alignment feedback modeled as a multi-armed bandit to consistently outperform single-drafter baselines.
citing papers explorer
-
Optimality of Sub-network Laplace Approximations: New Results and Methods
Sub-network Laplace approximations always underestimate an idealized predictive variance, and the proposed gradient- and greedy-based parameter selection rules provably close that gap better than existing heuristics.
-
Multi-Drafter Speculative Decoding with Alignment Feedback
MetaSD integrates multiple heterogeneous drafters into speculative decoding, dynamically selecting them via alignment feedback modeled as a multi-armed bandit to consistently outperform single-drafter baselines.