Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory
Yuan-chin Ivan Chang
Recurrent neural networks maintain a hidden state , but its probabilistic meaning is often unclear. We study hidden-state stability through \emph{backward coherence}: the exte…
cs.LG2026
ALMAB-DC: Active Learning, Multi-Armed Bandits, and Distributed Computing for Sequential Experimental Design and Black-Box Optimization
Foo Hui-Mean, Yuan-chin I Chang
Sequential experimental design under expensive, gradient-free objectives is a central challenge in computational statistics: evaluation budgets are tightly constrained and informat…