Analyzing Convergence in Quantum Neural Networks: Deviations from Neural Tangent Kernels
Jul 24, 2023
Speakers
Xuchen You
Speaker · 0 followers
Shouvanik Chakrabarti
Speaker · 0 followers
Boyang Chen
Speaker · 0 followers
About
A quantum neural network (QNN) is a parameterized mapping efficiently implementable on near-term Noisy Intermediate-Scale Quantum (NISQ) computers. It can be used for supervised learning when combined with classical gradient-based optimizers. Despite the existing empirical and theoretical investigations, the convergence of QNN training is not fully understood. Inspired by the success of the neural tangent kernels (NTKs) in probing into the dynamics of classical neural networks, a recent line of works proposes to study over-parameterized QNNs by examining a quantum version of tangent kernels. In this work, we study the dynamics of QNNs and show that contrary to popular belief it is qualitatively different from that of any kernel regression: due to the unitarity of quantum operations, there is a non-negligible deviation from the tangent kernel regression derived at the random initialization. As a result of the deviation, we prove the at-most sublinear convergence for QNNs with Pauli measurements, which is beyond the explanatory power of any kernel regression dynamics.We then present the actual dynamics of QNNs in the limit of over-parameterization. The new dynamics capture the change of convergence rate during training and implies that the range of measurements is crucial to the fast QNN convergence.A quantum neural network (QNN) is a parameterized mapping efficiently implementable on near-term Noisy Intermediate-Scale Quantum (NISQ) computers. It can be used for supervised learning when combined with classical gradient-based optimizers. Despite the existing empirical and theoretical investigations, the convergence of QNN training is not fully understood. Inspired by the success of the neural tangent kernels (NTKs) in probing into the dynamics of classical neural networks, a recent line of…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs
Watch later
Guanting Liu, …
Theoretical Behavior of XAI Methods in the Presence of Suppressor Variables
Watch later
Rick Wilming, …
Constrained Efficient Global Optimization of Expensive Black-box Functions
Watch later
Wenjie Xu, …
Generative Models and Molecular Representations for Chemistry
Watch later
Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions
Watch later
Ezgi Korkmaz, …