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 better understand 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 quantum stochastic and more general sequence models. I illustrate how quantum-enhanced dimensionality techniques can enable quantum models with memory dimensions lower than provably classical limits while retaining the key quantum capabilities of generating all possibilities in quantum superposition. I outline how such models may offer beyond-quadratic advantage in stochastic and risk analysis and thus accelerate the timeline for advantaged quantum computation. Time permitting.
References:
- Dimension reduction in quantum sampling of stochastic processes, npj Quantum Information, npj Quantum Inf 11, 34 (2025).
- Implementing quantum dimensionality reduction for non-Markovian stochastic simulation, Nature Communications 14.1, 2624 (2024)
- Provable superior accuracy in machine-learned quantum models, Phys. Rev. A 108, 022411 (2023)
- Quantum Adaptive Agents with Efficient Long-Term Memories, Phys. Rev. X 12, 011007 (2023)
- Extreme Dimensionality Reduction with Quantum Modeling, Phys. Rev. Lett. 125, 260501 (2019)
Biography:
Mile Gu is presently deputy director of the Nanyang Quantum Hub at Nanyang Technological University. He also holds an appointment as a Fellow at the Centre for Quantum Technologies and as an Investigator for the Singapore National Research Foundation. There he leads the quantum and complexity scientive initiative, focusing on research interfacing quantum, data and complexity science. He obtained his Ph.D. at the University of Queensland in 2009. He held a faculty position at Tsinghua University at the Institute for Interdisciplinary Information Science.
Seminar by the NYU-ECNU Institute of Physics at NYU Shanghai