Quantum algorithms for Gaussian process regression lose their exponential speedup because kernel matrix condition numbers grow at least linearly with dataset size.
The condition number of a randomly perturbed matrix
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Let $M$ be an arbitrary $n$ by $n$ matrix. We study the condition number a random perturbation $M+N_n$ of $M$, where $N_n$ is a random matrix. It is shown that, under very general conditions on $M$ and $M_n$, the condition number of $M+N_n$ is polynomial in $n$ with very high probability. The main novelty here is that we allow $N_n$ to have discrete distribution.
citation-role summary
background 1
citation-polarity summary
fields
quant-ph 1years
2025 1verdicts
ACCEPT 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Assessing Quantum Advantage for Gaussian Process Regression
Quantum algorithms for Gaussian process regression lose their exponential speedup because kernel matrix condition numbers grow at least linearly with dataset size.