On the query complexity of sampling from non-log-concave distributions

• URL: http://arxiv.org/abs/2502.06200v2
• Date: Wed, 12 Feb 2025 03:10:55 GMT
• Title: On the query complexity of sampling from non-log-concave distributions
• Authors: Yuchen He, Chihao Zhang,
• Abstract summary: We study the problem of sampling from a $d$-dimensional distribution with density $p(x)propto e-f(x)$, which does not necessarily satisfy good isoperimetric conditions. We show that for a wide range of parameters, sampling is strictly easier than optimization by a super-exponential factor in the dimension $d$.
• Score: 2.4253233571593547
• License:
• Abstract: We study the problem of sampling from a $d$-dimensional distribution with density $p(x)\propto e^{-f(x)}$, which does not necessarily satisfy good isoperimetric conditions. Specifically, we show that for any $L,M$ satisfying $LM\ge d\ge 5$, $\epsilon\in \left(0,\frac{1}{32}\right)$, and any algorithm with query accesses to the value of $f(x)$ and $\nabla f(x)$, there exists an $L$-log-smooth distribution with second moment at most $M$ such that the algorithm requires $\left(\frac{LM}{d\epsilon}\right)^{\Omega(d)}$ queries to compute a sample whose distribution is within $\epsilon$ in total variation distance to the target distribution. We complement the lower bound with an algorithm requiring $\left(\frac{LM}{d\epsilon}\right)^{\mathcal O(d)}$ queries, thereby characterizing the tight (up to the constant in the exponent) query complexity for sampling from the family of non-log-concave distributions. Our results are in sharp contrast with the recent work of Huang et al. (COLT'24), where an algorithm with quasi-polynomial query complexity was proposed for sampling from a non-log-concave distribution when $M=\mathtt{poly}(d)$. Their algorithm works under the stronger condition that all distributions along the trajectory of the Ornstein-Uhlenbeck process, starting from the target distribution, are $\mathcal O(1)$-log-smooth. We investigate this condition and prove that it is strictly stronger than requiring the target distribution to be $\mathcal O(1)$-log-smooth. Additionally, we study this condition in the context of mixtures of Gaussians. Finally, we place our results within the broader theme of ``sampling versus optimization'', as studied in Ma et al. (PNAS'19). We show that for a wide range of parameters, sampling is strictly easier than optimization by a super-exponential factor in the dimension $d$.

Related papers

• On the sampling complexity of coherent superpositions [0.4972323953932129]
  We consider the problem of sampling from the distribution of measurement outcomes when applying a POVM to a superposition. We give an algorithm which $-$ given $O(chi |c|2 log1/delta)$ such samples and calls to oracles to evaluate the probability density functions.
  arXiv  Detail & Related papers  (2025-01-28T16:56:49Z)
• Polynomial time sampling from log-smooth distributions in fixed dimension under semi-log-concavity of the forward diffusion with application to strongly dissipative distributions [9.48556659249574]
  We provide a sampling algorithm with complexity in fixed dimension. We prove that our algorithm achieves an expected $epsilon$ error in $KL$ divergence. As an application, we derive an exponential complexity improvement for the problem of sampling from an $L$-log-smooth distribution.
  arXiv  Detail & Related papers  (2024-12-31T17:51:39Z)
• Statistical-Computational Trade-offs for Density Estimation [60.81548752871115]
  We show that for a broad class of data structures their bounds cannot be significantly improved. This is a novel emphstatistical-computational trade-off for density estimation.
  arXiv  Detail & Related papers  (2024-10-30T15:03:33Z)
• Simple and Nearly-Optimal Sampling for Rank-1 Tensor Completion via Gauss-Jordan [49.1574468325115]
  We revisit the sample and computational complexity of completing a rank-1 tensor in $otimes_i=1N mathbbRd$. We present a characterization of the problem which admits an algorithm amounting to Gauss-Jordan on a pair of random linear systems.
  arXiv  Detail & Related papers  (2024-08-10T04:26:19Z)
• Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise [50.64137465792738]
  We show that any efficient SQ algorithm for the problem requires sample complexity at least $Omega(d1/2/(maxp, epsilon)2)$. Our lower bound suggests that this quadratic dependence on $1/epsilon$ is inherent for efficient algorithms.
  arXiv  Detail & Related papers  (2023-07-13T18:59:28Z)
• Perfect Sampling from Pairwise Comparisons [26.396901523831534]
  We study how to efficiently obtain perfect samples from a discrete distribution $mathcalD$ given access only to pairwise comparisons of elements of its support. We design a Markov chain whose stationary distribution coincides with $mathcalD$ and give an algorithm to obtain exact samples using the technique of Coupling from the Past.
  arXiv  Detail & Related papers  (2022-11-23T11:20:30Z)
• Robust Sparse Mean Estimation via Sum of Squares [42.526664955704746]
  We study the problem of high-dimensional sparse mean estimation in the presence of an $epsilon$-fraction of adversarial outliers. Our algorithms follow the Sum-of-Squares based, to algorithms approach.
  arXiv  Detail & Related papers  (2022-06-07T16:49:54Z)
• Optimal Gradient Sliding and its Application to Distributed Optimization Under Similarity [121.83085611327654]
  We structured convex optimization problems with additive objective $r:=p + q$, where $r$ is $mu$-strong convex similarity. We proposed a method to solve problems master to agents' communication and local calls. The proposed method is much sharper than the $mathcalO(sqrtL_q/mu)$ method.
  arXiv  Detail & Related papers  (2022-05-30T14:28:02Z)
• Statistically Near-Optimal Hypothesis Selection [33.83129262033921]
  We derive an optimal $2$-approximation learning strategy for the Hypothesis Selection problem. This is the first algorithm that simultaneously achieves the best approximation factor and sample complexity.
  arXiv  Detail & Related papers  (2021-08-17T21:11:20Z)
• Streaming Complexity of SVMs [110.63976030971106]
  We study the space complexity of solving the bias-regularized SVM problem in the streaming model. We show that for both problems, for dimensions of $frac1lambdaepsilon$, one can obtain streaming algorithms with spacely smaller than $frac1lambdaepsilon$.
  arXiv  Detail & Related papers  (2020-07-07T17:10:00Z)
• Locally Private Hypothesis Selection [96.06118559817057]
  We output a distribution from $mathcalQ$ whose total variation distance to $p$ is comparable to the best such distribution. We show that the constraint of local differential privacy incurs an exponential increase in cost. Our algorithms result in exponential improvements on the round complexity of previous methods.
  arXiv  Detail & Related papers  (2020-02-21T18:30:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.