Stochastic Quantum Sampling for Non-Logconcave Distributions and Estimating Partition Functions
This provides a quantum advantage for tasks like mixture modeling and multi-stable systems, though it is incremental as it builds on existing quantum simulated annealing and stochastic gradient methods.
The paper tackles the problem of sampling from non-logconcave distributions and estimating partition functions, achieving polynomial speedups in dimension and precision dependencies compared to classical algorithms.
We present quantum algorithms for sampling from non-logconcave probability distributions in the form of $π(x) \propto \exp(-βf(x))$. Here, $f$ can be written as a finite sum $f(x):= \frac{1}{N}\sum_{k=1}^N f_k(x)$. Our approach is based on quantum simulated annealing on slowly varying Markov chains derived from unadjusted Langevin algorithms, removing the necessity for function evaluations which can be computationally expensive for large data sets in mixture modeling and multi-stable systems. We also incorporate a stochastic gradient oracle that implements the quantum walk operators inexactly by only using mini-batch gradients. As a result, our stochastic gradient based algorithm only accesses small subsets of data points in implementing the quantum walk. One challenge of quantizing the resulting Markov chains is that they do not satisfy the detailed balance condition in general. Consequently, the mixing time of the algorithm cannot be expressed in terms of the spectral gap of the transition density, making the quantum algorithms nontrivial to analyze. To overcome these challenges, we first build a hypothetical Markov chain that is reversible, and also converges to the target distribution. Then, we quantified the distance between our algorithm's output and the target distribution by using this hypothetical chain as a bridge to establish the total complexity. Our quantum algorithms exhibit polynomial speedups in terms of both dimension and precision dependencies when compared to the best-known classical algorithms.