2000 character limit reached
Tamed Langevin sampling under weaker conditions (2405.17693v1)
Published 27 May 2024 in stat.ML, cs.LG, cs.NA, math.NA, math.OC, and math.PR
Abstract: Motivated by applications to deep learning which often fail standard Lipschitz smoothness requirements, we examine the problem of sampling from distributions that are not log-concave and are only weakly dissipative, with log-gradients allowed to grow superlinearly at infinity. In terms of structure, we only assume that the target distribution satisfies either a log-Sobolev or a Poincar\'e inequality and a local Lipschitz smoothness assumption with modulus growing possibly polynomially at infinity. This set of assumptions greatly exceeds the operational limits of the "vanilla" unadjusted Langevin algorithm (ULA), making sampling from such distributions a highly involved affair. To account for this, we introduce a taming scheme which is tailored to the growth and decay properties of the target distribution, and we provide explicit non-asymptotic guarantees for the proposed sampler in terms of the Kullback-Leibler (KL) divergence, total variation, and Wasserstein distance to the target distribution.
- Diffusions hypercontractives. In Séminaire de Probabilités XIX 1983/84: Proceedings, pp. 177–206. Springer, 2006.
- A simple proof of the poincaré inequality for a large class of probability measures. Electronic Communications in Probability, 13:60–66, 2008.
- Analysis and geometry of Markov diffusion operators, volume 103. Springer, 2014.
- Towards a theory of non-log-concave sampling: first-order stationarity guarantees for langevin monte carlo. In Conference on Learning Theory, pp. 2896–2923. PMLR, 2022.
- On stochastic gradient langevin dynamics with dependent data streams in the logconcave case. Bernoulli, 27(1):1–33, 2021.
- Weighted csiszár-kullback-pinsker inequalities and applications to transportation inequalities. In Annales de la Faculté des sciences de Toulouse: Mathématiques, volume 14, pp. 331–352, 2005.
- The tamed unadjusted Langevin algorithm. Stochastic Processes and their Applications, 129(10):3638–3663, 2019.
- Poincaré inequalities and hitting times. In Annales de l’IHP Probabilités et statistiques, volume 49, pp. 95–118, 2013.
- On stochastic gradient langevin dynamics with dependent data streams: The fully nonconvex case. SIAM Journal on Mathematics of Data Science, 3(3):959–986, 2021.
- Sharp convergence rates for Langevin dynamics in the nonconvex setting. arXiv preprint arXiv:1805.01648, 2018.
- Analysis of langevin monte carlo from poincar\\\backslash\’e to log-sobolev. arXiv preprint arXiv:2112.12662, 2021.
- Dalalyan, A. S. Theoretical guarantees for approximate sampling from smooth and log-concave densities. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 79(3):651–676, 2017.
- Nonasymptotic convergence analysis for the unadjusted Langevin algorithm. The Annals of Applied Probability, 27(3):1551–1587, 2017.
- High-dimensional Bayesian inference via the unadjusted Langevin algorithm. Bernoulli, 25(4A):2854–2882, 2019.
- On the convergence of langevin monte carlo: The interplay between tail growth and smoothness. In Conference on Learning Theory, pp. 1776–1822. PMLR, 2021.
- Convergence of langevin monte carlo in chi-squared and rényi divergence. In International Conference on Artificial Intelligence and Statistics, pp. 8151–8175. PMLR, 2022.
- Strong and weak divergence in finite time of euler’s method for stochastic differential equations with non-globally lipschitz continuous coefficients. Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences, 467(2130):1563–1576, 2011. ISSN 1364-5021.
- Strong convergence of an explicit numerical method for sdes with nonglobally lipschitz continuous coefficients. Ann. Appl. Probab., 22(4):1611–1641, 08 2012.
- Kinetic langevin mcmc sampling without gradient lipschitz continuity–the strongly convex case. arXiv preprint arXiv:2301.08039, 2023.
- Riemannian langevin algorithm for solving semidefinite programs. arXiv preprint arXiv:2010.11176, 2020.
- Taming neural networks with tusla: Nonconvex learning via adaptive stochastic gradient langevin algorithms. SIAM Journal on Mathematics of Data Science, 5(2):323–345, 2023.
- Taming under isoperimetry. arXiv preprint arXiv:2311.09003, 2023.
- Nonasymptotic bounds for sampling algorithms without log-concavity. The Annals of Applied Probability, 30(4):1534–1581, 2020.
- McNabb, A. Comparison theorems for differential equations. Journal of mathematical analysis and applications, 119(1-2):417–428, 1986.
- Poincaré and logarithmic sobolev inequalities by decomposition of the energy landscape. The Annals of Probability, 42(5):1809–1884, 2014.
- Improved bounds for discretization of langevin diffusions: Near-optimal rates without convexity. Bernoulli, 28(3):1577–1601, 2022.
- Towards a complete analysis of langevin monte carlo: Beyond poincaré inequality. In The Thirty Sixth Annual Conference on Learning Theory, pp. 1–35. PMLR, 2023.
- Non-asymptotic convergence bounds for modified tamed unadjusted langevin algorithm in non-convex setting. arXiv preprint arXiv:2207.02600, 2022.
- Unadjusted langevin algorithm for non-convex weakly smooth potentials. arXiv preprint arXiv:2101.06369, 2021.
- Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis. In Conference on Learning Theory, pp. 1674–1703, 2017.
- Sabanis, S. A note on tamed euler approximations. Electron. Commun. Probab., 18(47):1–10, 2013.
- Sabanis, S. Euler approximations with varying coefficients: the case of superlinearly growing diffusion coefficients. Ann. Appl. Probab., 26(4):2083–2105, 2016.
- Rapid convergence of the unadjusted langevin algorithm: Isoperimetry suffices. Advances in neural information processing systems, 32, 2019.
- Nonasymptotic estimates for stochastic gradient langevin dynamics under local conditions in nonconvex optimization. Applied Mathematics & Optimization, 87(2):25, 2023.