Recognizing and localizing objects in the 3D space is a crucial ability for an AI agent to perceive its surrounding environment.

Over the past decade, machine learning (ML) models are being increasingly deployed to make a variety of consequential decisions ranging from hiring decisions to loan approvals.

The emerging high-quality large structural datasets raise the question of what general functional principles can be gleaned from them. Motivated by this question, we developed a statistical mechanical theory of learning in neural networks that incorporates structural information as constraints.

We study the problem of online multiclass classification in a setting where the learner's feedback is determined by an arbitrary directed graph. While including bandit feedback as a special case, feedback graphs allow a much richer set of applications, including filtering and label efficient classification.