Title： Dimensional Reduction in the Presence of Quantum Agents

Speaker: Prof. Mile Gu (Nanyang Technological University)

Date and Time：2023年06月29日 10:00

Location：培黎职业学院综合楼

Abstract:

Dimensionality reduction captures the spirit of Occam’s razor – asking the fundamental question: What features of current data are the essential indicators of future behaviour? By isolating such features and discarding the rest, we gain a better understanding of underlying causal behaviour, while enabling models with reduced memory costs and enhanced generalisation capability. Could quantum computers offer fundamental advantages in this arena? Here I will outline our ongoing work along these directions in the context of stochastic modelling and quantum-enhanced adaptive agents, and outline their potential implications for understanding complexity and non-Markovianity.

References:

· Implementing quantum dimensionality reduction for non-Markovian stochastic simulation, Nature Communications 14.1, 2624.

· Quantum Adaptive Agents with Efficient Long-Term Memories, Phys. Rev. X 12, 011007,

· Extreme Dimensionality Reduction with Quantum Modeling, Phys. Rev. Lett. 125, 260501

· Provable superior accuracy in machine learned quantum models, arXiv:2105.14434

Speaker Information:

Gu is originally from New Zealand and obtained his Ph.D. at the University of Queensland. After a faculty position at Tsinghua, he joined Nanyang Technological University in 2016. There he presently leads the quantum and complexity science initiative, with a focus on quantum-enhanced modelling, causal inference, and data analytics. Gu also holds joint appointments at the Centre for Quantum technologies as a CQT Fellow, and is principal investigator of the French-Singapore joint institute Majulab. Gu’s previous accolades include the National Research Foundation Fellow, the Young China 1000 talent, and was also winner of the 2020 IBM Quantum Pitch Contest.