arXiv subjects

Diantong Li

Publications and source records attributed to Diantong Li.

3 recordsLinked to original sources

arXiv2025

Rotation Numbers and Geometric Invariants in Bicycle Dynamics

We study planar bicycle dynamics via the rotation number function associated with a closed front track and bicycle length R. We prove that mode-locking plateaus occur only at integer rotation numbers and that the rotation number function is real-analytic off resonance. From the rotation number function we introduce two new geometric invariants: the critical B-length (right end of the first plateau) and the turning B-length (left end of the maximal monotone interval). We prove that, for a star-shaped curve, these invariants coincide, yielding a sharp transition of the bicycle monodromy: hyperbolic for R below the critical B-length and elliptic for R above it. The proofs combine projectivized SU(1,1) dynamics with Riccati equations and rotation-number theory.

math.DS↗

arXiv2025

None To Optima in Few Shots: Bayesian Optimization with MDP Priors

Bayesian Optimization (BO) is an efficient tool for optimizing black-box functions, but its theoretical guarantees typically hold in the asymptotic regime. In many critical real-world applications such as drug discovery or materials design, where each evaluation can be very costly and time-consuming, BO becomes impractical for many evaluations. In this paper, we introduce the Procedure-inFormed BO (ProfBO) algorithm, which solves black-box optimization with remarkably few function evaluations. At the heart of our algorithmic design are Markov Decision Process (MDP) priors that model optimization trajectories from related source tasks, thereby capturing procedural knowledge on efficient optimization. We embed these MDP priors into a prior-fitted neural network and employ model-agnostic meta-learning for fast adaptation to new target tasks. Experiments on real-world Covid and Cancer benchmarks and hyperparameter tuning tasks demonstrate that ProfBO consistently outperforms state-of-the-art methods by achieving high-quality solutions with significantly fewer evaluations, making it ready for practical deployment.

cs.LG↗

arXiv2025

Constrained Multi-objective Bayesian Optimization through Optimistic Constraints Estimation

Multi-objective Bayesian optimization has been widely adopted in scientific experiment design, including drug discovery and hyperparameter optimization. In practice, regulatory or safety concerns often impose additional thresholds on certain attributes of the experimental outcomes. Previous work has primarily focused on constrained single-objective optimization tasks or active search under constraints. The existing constrained multi-objective algorithms address the issue with heuristics and approximations, posing challenges to the analysis of the sample efficiency. We propose a novel constrained multi-objective Bayesian optimization algorithm COMBOO that balances active learning of the level-set defined on multiple unknowns with multi-objective optimization within the feasible region. We provide both theoretical analysis and empirical evidence, demonstrating the efficacy of our approach on various synthetic benchmarks and real-world applications.

cs.LG↗