The α-potential game framework reduces α-Nash equilibria in distributed jump diffusion games to finite-dimensional control problems, with explicit polynomial and logarithmic α decay rates for asymmetric networks and Nash equilibrium construction for heterogeneous mean-variance portfolio games.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
MetaAdamW uses a lightweight Transformer encoder on gradient and momentum statistics to adapt learning rates and weight decay per parameter group, trained via a meta-objective with gradient alignment, loss decrease, and generalization gap plus priority-injected homoscedastic uncertainty weighting.
citing papers explorer
-
Distributed games with jumps: An $\alpha$-potential game approach
The α-potential game framework reduces α-Nash equilibria in distributed jump diffusion games to finite-dimensional control problems, with explicit polynomial and logarithmic α decay rates for asymmetric networks and Nash equilibrium construction for heterogeneous mean-variance portfolio games.
-
A Self-Attentive Meta-Optimizer with Group-Adaptive Learning Rates and Weight Decay
MetaAdamW uses a lightweight Transformer encoder on gradient and momentum statistics to adapt learning rates and weight decay per parameter group, trained via a meta-objective with gradient alignment, loss decrease, and generalization gap plus priority-injected homoscedastic uncertainty weighting.