SurpriseOpt: An Adaptive First-Order Optimizer Driven by Boredom

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1. 1Active Inference for Global Optimization in Discontinuous Environments2026
2. 2Surprise-Adaptive Intrinsic Motivation for Unsupervised Reinforcement Learning2024
3. 3Optimization via First-Order Switching Methods: Skew-Symmetric Dynamics and Optimistic Discretization2025
4. 4Dynamic Inverse Optimization under Drift and Shocks: Theory, Regret Bounds, and Applications2025
5. 5OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations2024