Stochastic optimal control, which has the goal of driving the behavior of noisy systems, is broadly applicable in science, engineering and artificial intelligence. Our work introduces Stochastic Optimal Control Matching (SOCM), a novel Iterative Diffusion Optimization (IDO) technique for stochastic optimal control that stems from the same philosophy as the conditional score matching loss for diffusion models.

While successful, these methods are mainly designed for sampling from unconstrained domains.

Multi-label active learning is a crucial yet challenging area in contemporary machine learning, often complicated by a large and sparse label space.

To overcome this challenge, diverging from conventional efforts of expanding the solver's search scope, we focus on enabling information to actively propagate to the solver through heat diffusion.

Furthermore, the exploration of temporal context information within PSs is also a serious challenge.

Evaluating machine learning models requires evaluation data.

Multi-task learning is a promising paradigm for handling several tasks simultaneously using a unified architecture.

We study the proportional clustering problem of Chen et al. (ICML '19) and relate

Classical worst-case optimization theory neither explains the success of optimization in machine learning, nor does it help with step size selection.

Scene flow estimation is an essential ingredient for a variety of real-world applications, especially for autonomous agents, such as self-driving cars and robots.