On Quantum Linear Algebra for Machine Learning - IPAM at UCLA

Explore quantum linear algebra applications in machine learning through this 35-minute conference talk by Ewin Tang from the University of Washington. Delve into the quantum singular value transformation (QSVT) framework and its potential for quantum speedups in machine learning problems. Examine the typical structure of QSVT applications, barriers to achieving super-polynomial quantum speedup, and current literature addressing these challenges. Discover the intriguing connection between quantum linear algebra and classical sampling and sketching algorithms. Cover topics such as linear algebra with amplitude encoding, quantum mechanical value transformation, sampling and query access, linear algebra literature, and gradient descent. Gain insights into the cutting-edge research presented at IPAM's Quantum Numerical Linear Algebra Workshop at UCLA.

Intro
Linear algebra with amplitude encoding
Quantum mechanical value transformation
Applications
Sampling and query access
Linear algebra literature
Gradient descent
Summary