More Like this

1. Estimating Convergence of Markov chains with L-Lag Couplings

   Biswas, Niloy; Jacob, Pierre E; Vanetti, Paul (January 2019, Advances in neural information processing systems)

   Markov chain Monte Carlo (MCMC) methods generate samples that are asymptotically distributed from a target distribution of interest as the number of iterations goes to infinity. Various theoretical results provide upper bounds on the distance between the target and marginal distribution after a fixed number of iterations. These upper bounds are on a case by case basis and typically involve intractable quantities, which limits their use for practitioners. We introduce L-lag couplings to generate computable, non-asymptotic upper bound estimates for the total variation or the Wasserstein distance of general Markov chains. We apply L-lag couplings to the tasks of (i) determining MCMC burn-in, (ii) comparing different MCMC algorithms with the same target, and (iii) comparing exact and approximate MCMC. Lastly, we (iv) assess the bias of sequential Monte Carlo and self-normalized importance samplers. 

   more » « less
2. Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space

   Jiang, Yiheng; Chewi, Sinho; Pooladian, Aram-Alexandre (June 2024, Conference on Learning Theory (COLT) 2024)

   We develop a theory of finite-dimensional polyhedral subsets over the Wasserstein space and optimization of functionals over them via first-order methods. Our main application is to the problem of mean-field variational inference, which seeks to approximate a distribution π over ℝd by a product measure π⋆. When π is strongly log-concave and log-smooth, we provide (1) approximation rates certifying that π⋆ is close to the minimizer π⋆⋄ of the KL divergence over a \emph{polyhedral} set ⋄, and (2) an algorithm for minimizing KL(⋅‖π) over ⋄ with accelerated complexity O(κ√log(κd/ε2)), where κ is the condition number of π. 

   more » « less
3. Stochastic Variance-Reduced Hamilton Monte Carlo Methods

   Zou, Difan; Xu, Pan; Gu, Quanquan (July 2018, International Conference on Machine Learning)

   We propose a fast stochastic Hamilton Monte Carlo (HMC) method, for sampling from a smooth and strongly log-concave distribution. At the core of our proposed method is a variance reduction technique inspired by the recent advance in stochastic optimization. We show that, to achieve $$\epsilon$$ accuracy in 2-Wasserstein distance, our algorithm achieves $$\tilde O\big(n+\kappa^{2}d^{1/2}/\epsilon+\kappa^{4/3}d^{1/3}n^{2/3}/\epsilon^{2/3}%\wedge\frac{\kappa^2L^{-2}d\sigma^2}{\epsilon^2} \big)$$ gradient complexity (i.e., number of component gradient evaluations), which outperforms the state-of-the-art HMC and stochastic gradient HMC methods in a wide regime. We also extend our algorithm for sampling from smooth and general log-concave distributions, and prove the corresponding gradient complexity as well. Experiments on both synthetic and real data demonstrate the superior performance of our algorithm. 

   more » « less
4. Scalable Gaussian Process Inference with Finite-data Mean and Variance Guarantees

   Huggins, Jonathan H.; Campbell, Trevor; Kasprzak, Mikolaj; Broderick, Tamara (April 2019, Proceedings of Machine Learning Research)

   Gaussian processes (GPs) offer a flexible class of priors for nonparametric Bayesian regression, but popular GP posterior inference methods are typically prohibitively slow or lack desirable finite-data guarantees on quality. We develop a scalable approach to approximate GP regression, with finite-data guarantees on the accuracy of our pointwise posterior mean and variance estimates. Our main contribution is a novel objective for approximate inference in the nonparametric setting: the preconditioned Fisher (pF) divergence. We show that unlike the Kullback–Leibler divergence (used in variational inference), the pF divergence bounds bounds the 2-Wasserstein distance, which in turn provides tight bounds on the pointwise error of mean and variance estimates. We demonstrate that, for sparse GP likelihood approximations, we can minimize the pF divergence bounds efficiently. Our experiments show that optimizing the pF divergence bounds has the same computational requirements as variational sparse GPs while providing comparable empirical performance—in addition to our novel finite-data quality guarantees. 

   more » « less
5. Stratification and optimal resampling for sequential Monte Carlo

   https://doi.org/10.1093/biomet/asab004  

   Li, Yichao; Wang, Wenshuo; Deng, K E; Liu, Jun S (February 2021, Biometrika)

   Summary Sequential Monte Carlo algorithms are widely accepted as powerful computational tools for making inference with dynamical systems. A key step in sequential Monte Carlo is resampling, which plays the role of steering the algorithm towards the future dynamics. Several strategies have been used in practice, including multinomial resampling, residual resampling, optimal resampling, stratified resampling and optimal transport resampling. In one-dimensional cases, we show that optimal transport resampling is equivalent to stratified resampling on the sorted particles, and both strategies minimize the resampling variance as well as the expected squared energy distance between the original and resampled empirical distributions. For general $$d$$-dimensional cases, we show that if the particles are first sorted using the Hilbert curve, the variance of stratified resampling is $$O(m^{-(1+2/d)})$$, an improvement over the best previously known rate of $$O(m^{-(1+1/d)})$$, where $$m$$ is the number of resampled particles. We show that this improved rate is optimal for ordered stratified resampling schemes, as conjectured in Gerber et al. (2019). We also present an almost-sure bound on the Wasserstein distance between the original and Hilbert-curve-resampled empirical distributions. In light of these results, we show that for dimension $d>1$ the mean square error of sequential quasi-Monte Carlo with $$n$$ particles can be $$O(n^{-1-4/\{d(d+4)\}})$$ if Hilbert curve resampling is used and a specific low-discrepancy set is chosen. To our knowledge, this is the first known convergence rate lower than $$o(n^{-1})$$. 

   more » « less