SubMAPG uses a new Partition Multilinear Extension to derive unbiased policy gradients from submodular difference rewards, delivering 1/2-approximation and sublinear dynamic regret for online distributed task allocation in open multi-agent systems.
Proceedings of the fortieth annual ACM symposium on Theory of computing , pages=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
A Poisson process yields the tight (1-1/e) approximation for monotone submodular maximization subject to a matroid constraint without discretization or rounding.
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.
citing papers explorer
-
Submodular Multi-Agent Policy Learning for Online Distributed Task Allocation in Open Multi-Agent Systems
SubMAPG uses a new Partition Multilinear Extension to derive unbiased policy gradients from submodular difference rewards, delivering 1/2-approximation and sublinear dynamic regret for online distributed task allocation in open multi-agent systems.
-
A Poisson Process for Submodular Maximization
A Poisson process yields the tight (1-1/e) approximation for monotone submodular maximization subject to a matroid constraint without discretization or rounding.
-
Training Deep Learning Models with Norm-Constrained LMOs
Scion is a new stochastic LMO-based optimizer family that unifies existing methods, supports unconstrained problems, and delivers hyperparameter transferability plus speedups on nanoGPT training.