Tag
This paper introduces spectral effective-rank entropy as a metric to measure and control critic complexity in actor-critic reinforcement learning, demonstrating its measurability and controllability in TD3 and PPO experiments.
Proposes mechanism-driven monitors for preemptive detection of LLM training instability by deriving internal signals from low-precision flash attention and MoE routers, enabling detection thousands of steps before loss divergence.
The paper proposes using spectral entropy as a metric to quantify noise introduced by explainability techniques in ECG arrhythmia classification, helping to distinguish true model signal from XAI-generated artifacts.
CHIAR-Former uses spectral entropy-based routing to dynamically select between DCT, RBF, and self-attention operators, achieving improved efficiency on large text datasets while maintaining performance through hybrid attention mechanisms.