#bayesian-neural-networks2 articles

2 articles

AINeutralarXiv – CS AI · 5d ago4/104

🧠

Sample-efficient and Scalable Exploration in Continuous-Time RL

Researchers introduce COMBRL, a new reinforcement learning algorithm designed for continuous-time systems using nonlinear ordinary differential equations. The algorithm achieves sublinear regret and better sample efficiency compared to existing methods by combining probabilistic models with uncertainty-aware exploration.

AINeutralarXiv – CS AI · Feb 274/107

🧠

From Shallow Bayesian Neural Networks to Gaussian Processes: General Convergence, Identifiability and Scalable Inference

Researchers established a new theoretical framework connecting Bayesian neural networks to Gaussian processes, developing improved convergence results and identifiability properties. They introduced a scalable computational method using Nyström approximation for training and prediction, demonstrating competitive performance on real-world datasets.