stochastic processes
In AI, stochastic processes refer to systems that incorporate randomness or uncertainty in their behavior over time. Many algorithms, particularly in reinforcement learning, model environments and decisions using stochastic processes to better simulate real-world variability.
- Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees
- Distances for Markov chains from sample streams
- Flow Matching Neural Processes
- LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models
- Learning to Generalize: An Information Perspective on Neural Processes
- Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction
- System-Embedded Diffusion Bridge Models