BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Learning to predict arbitrary quantum processes
DTSTART:20221121T160000
DTEND:20221121T170000
DTSTAMP:20260407T043910Z
UID:d40a5a5c3d1697b3e8d18e55f8293d8237f92bbacc81d143b373ce74
CATEGORIES:Conferences - Seminars
DESCRIPTION:Dr Sitan Chen\nIn this talk\, Dr Chen will present an efficien
 t machine learning (ML) algorithm for predicting any unknown quantum proce
 ss E over n qubits. For a wide range of distributions D on arbitrary 
 n-qubit states\, Dr Chen shows that this ML algorithm can learn to predict
  any local property of the output from the unknown process E\, with a sma
 ll average error over input states drawn from D. The ML algorithm is comp
 utationally efficient even when the unknown process is a quantum circuit w
 ith exponentially many gates. The algorithm combines efficient procedures 
 for learning properties of an unknown state and for learning a low-degree 
 approximation to an unknown observable. The analysis hinges on proving new
  norm inequalities\, including a quantum analogue of the classical Bohnenb
 lust-Hille inequality\, which we derive by giving an improved algorithm fo
 r optimizing local Hamiltonians. Overall\, the results highlight the poten
 tial for ML models to predict the output of complex quantum dynamics much 
 faster than the time needed to run the process itself.\n\nThis online talk
  will be 45 minutes\, with 15 minutes for questions.
LOCATION:https://epfl.zoom.us/j/66813683077?pwd=UzY5c3lnM3k0YmNKN0dGSkozMk
 tNZz09
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR