The Inductive Bias of Quantum Kernels
Dec 6, 2021
Speakers
Jonas M. Kübler
Speaker · 0 followers
Simon Buchholz
Speaker · 0 followers
Bernhard Schölkopf
Speaker · 14 followers
About
It has been hypothesized that quantum computers may lend themselves well to applications in machine learning. In the present work, we analyze function classes defined via quantum kernels. Quantum computers offer the possibility to efficiently compute inner products of exponentially large density operators that are classically hard to compute. However, having an exponentially large feature space renders the problem of generalization hard. Furthermore, being able to evaluate inner products in high dimensional spaces efficiently by itself does not guarantee a quantum advantage, as already classically tractable kernels can correspond to high- or infinite-dimensional reproducing kernel Hilbert spaces (RKHS). We analyze the spectral properties of quantum kernels and find that we can expect an advantage if their RKHS is low dimensional and contains functions that are hard to compute classically. If the target function is known to lie in this class, this implies a quantum advantage, as the quantum computer can encode this inductive bias, whereas there is no classically efficient way to constrain the function class in the same way. However, we show that finding suitable quantum kernels is not easy because the kernel evaluation might require exponentially many measurements. In conclusion, our message is a somewhat sobering one: we conjecture that quantum machine learning models can offer speed-ups only if we manage to encode knowledge about the problem at hand into quantum circuits, while encoding the same bias into a classical model would be hard. These situations may plausibly occur when learning on data generated by a quantum process, however, they appear to be harder to come by for classical datasets.It has been hypothesized that quantum computers may lend themselves well to applications in machine learning. In the present work, we analyze function classes defined via quantum kernels. Quantum computers offer the possibility to efficiently compute inner products of exponentially large density operators that are classically hard to compute. However, having an exponentially large feature space renders the problem of generalization hard. Furthermore, being able to evaluate inner products in high…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
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
Dock2D: Toy datasets for the molecular recognition problem
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Measuring Generalization with Optimal Transport
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognition
Watch later
Yichong Leng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Arbitrary Conditional Distributions with Energy
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Effect of Radiology Report Labeler Quality on Deep Learning Models for Chest X-Ray Interpretation
Watch later
Saahil Jain, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%