Optimal Learning of Quantum Hamiltonians From High-Temperature Gibbs States

Speaker: Ewin Tang , University of Washington

Date: Wednesday, March 30, 2022

Time: 4:00 PM to 5:00 PM Note: all times are in the Eastern Time Zone

Public: Yes


Event Type: Seminar

Room Description: https://mit.zoom.us/j/94625002202?pwd=bkROYjdBZStKeUIzVlNNTU11MVp6dz09

Host: Rahul Ilango, MIT

Contact: Rahul Ilango, rilango@mit.edu

Relevant URL: https://mit.zoom.us/j/94625002202?pwd=bkROYjdBZStKeUIzVlNNTU11MVp6dz09

Speaker URL: https://ewintang.com/

Speaker Photo:

Reminders to: theory-seminars@csail.mit.edu, seminars@csail.mit.edu

Reminder Subject: TALK: Optimal Learning of Quantum Hamiltonians From High-Temperature Gibbs States

Abstract: Hamiltonian learning is the problem of learning a geometrically local N-qubit Hamiltonian H to precision ɛ, supposing we are given copies of its Gibbs state ρ = exp(-βH) / Tr(exp(-βH)) at a known inverse temperature β. This is the quantum generalization of the problem of parameter learning Markov Random Fields. I will present an algorithm that solves this problem with optimal sample complexity (number of copies of ρ needed) and optimal time complexity in the high-temperature (low β) regime. This improves on the previous best algorithm given by Anshu et al. (FOCS 2020), for the high-temperature regime. This work was done jointly with Jeongwan Haah and Robin Kothari.

Research Areas:
Algorithms & Theory, AI & Machine Learning

Impact Areas:
Big Data

See other events that are part of the Algorithms and Complexity Seminar 2022.

Created by Noah Golowich Email at Monday, March 28, 2022 at 3:22 PM.