Kartik Sonawane

DP-HPO: Approximate Dynamic Programming for Neural Network Hyperparameter Optimisation with Evaluation Caching

2026 · Zenodo (CERN European Organization for Nuclear Research)

Abstract—Neural network performance is highly sensitive to hyperparameter settings, yet exhaustive search over the configuration space is computationally prohibitive. We present DP-HPO, a framework that formulates hyperparameter optimisation (HPO) as a finite-horizon Markov Decision Process …