Zhi-Hua Zhou

Locally optimal online algorithms can completely fail to track changing environments, disproving a foundational conjecture in non-stationary learning while uncovering a geometric surrogate reduction that recovers optimal dynamic regret.

The transition from file storage to database management systems transformed stored data into managed resources into AI model management systems, and AI now faces an analogous transition from AI model storage to AI model management.

A centralized model repository can enhance CSI feedback efficiency, achieving significant performance gains while slashing local training requirements.

High variance in draft quality is tackled head-on, leading to a remarkable 66% increase in throughput for speculative decoding in large language models.

Achieving optimal regret in generalized linear bandits with heavy-tailed noise using a novel one-pass update algorithm could revolutionize decision-making in dynamic environments.

You don't need a full causal graph to avoid undesired outcomes; learning a simple order structure can be enough, and even outperform methods that try to learn the whole graph.