Black Box Variational Inference with a Deterministic Objective: Faster, More Accurate, and Even More Black Box

• URL: http://arxiv.org/abs/2304.05527v4
• Date: Wed, 17 Jan 2024 20:16:04 GMT
• Title: Black Box Variational Inference with a Deterministic Objective: Faster, More Accurate, and Even More Black Box
• Authors: Ryan Giordano, Martin Ingram, Tamara Broderick
• Abstract summary: We introduce "deterministic ADVI" (DADVI) to address issues with ADVI. DADVI replaces the intractable MFVB objective with a fixed Monte Carlo approximation. We show that DADVI and the SAA can perform well with relatively few samples even in very high dimensions.
• Score: 14.362625828893654
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Automatic differentiation variational inference (ADVI) offers fast and easy-to-use posterior approximation in multiple modern probabilistic programming languages. However, its stochastic optimizer lacks clear convergence criteria and requires tuning parameters. Moreover, ADVI inherits the poor posterior uncertainty estimates of mean-field variational Bayes (MFVB). We introduce "deterministic ADVI" (DADVI) to address these issues. DADVI replaces the intractable MFVB objective with a fixed Monte Carlo approximation, a technique known in the stochastic optimization literature as the "sample average approximation" (SAA). By optimizing an approximate but deterministic objective, DADVI can use off-the-shelf second-order optimization, and, unlike standard mean-field ADVI, is amenable to more accurate posterior covariances via linear response (LR). In contrast to existing worst-case theory, we show that, on certain classes of common statistical problems, DADVI and the SAA can perform well with relatively few samples even in very high dimensions, though we also show that such favorable results cannot extend to variational approximations that are too expressive relative to mean-field ADVI. We show on a variety of real-world problems that DADVI reliably finds good solutions with default settings (unlike ADVI) and, together with LR covariances, is typically faster and more accurate than standard ADVI.

Related papers

• Batch and match: black-box variational inference with a score-based divergence [26.873037094654826]
  We propose batch and match (BaM) as an alternative approach to blackbox variational inference (BBVI) based on a score-based divergence. We show that BaM converges in fewer evaluations than leading implementations of BBVI based on ELBO.
  arXiv  Detail & Related papers  (2024-02-22T18:20:22Z)
• Amortized Variational Inference: When and Why? [17.1222896154385]
  Amortized variational inference (A-VI) learns a common inference function, which maps each observation to its corresponding latent variable's approximate posterior. We derive conditions on a latent variable model which are necessary, sufficient, and verifiable under which A-VI can attain F-VI's optimal solution.
  arXiv  Detail & Related papers  (2023-07-20T16:45:22Z)
• On the Convergence of Black-Box Variational Inference [16.895490556279647]
  We provide the first convergence guarantee for full black-box variational inference (BBVI) Our results hold for log-smooth posterior densities with and without strong log-concavity and the location-scale variational family.
  arXiv  Detail & Related papers  (2023-05-24T16:59:50Z)
• Manifold Gaussian Variational Bayes on the Precision Matrix [70.44024861252554]
  We propose an optimization algorithm for Variational Inference (VI) in complex models. We develop an efficient algorithm for Gaussian Variational Inference whose updates satisfy the positive definite constraint on the variational covariance matrix. Due to its black-box nature, MGVBP stands as a ready-to-use solution for VI in complex models.
  arXiv  Detail & Related papers  (2022-10-26T10:12:31Z)
• Asymptotically Unbiased Instance-wise Regularized Partial AUC Optimization: Theory and Algorithm [101.44676036551537]
  One-way Partial AUC (OPAUC) and Two-way Partial AUC (TPAUC) measures the average performance of a binary classifier. Most of the existing methods could only optimize PAUC approximately, leading to inevitable biases that are not controllable. We present a simpler reformulation of the PAUC problem via distributional robust optimization AUC.
  arXiv  Detail & Related papers  (2022-10-08T08:26:22Z)
• Amortized Variational Inference: A Systematic Review [0.0]
  The core principle of Variational Inference (VI) is to convert the statistical inference problem of computing complex posterior probability densities into a tractable optimization problem. The traditional VI algorithm is not scalable to large data sets and is unable to readily infer out-of-bounds data points. Recent developments in the field, like black box-, and amortized-VI, have helped address these issues.
  arXiv  Detail & Related papers  (2022-09-22T09:45:10Z)
• BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery [97.79015388276483]
  A structural equation model (SEM) is an effective framework to reason over causal relationships represented via a directed acyclic graph (DAG) Recent advances enabled effective maximum-likelihood point estimation of DAGs from observational data. We propose BCD Nets, a variational framework for estimating a distribution over DAGs characterizing a linear-Gaussian SEM.
  arXiv  Detail & Related papers  (2021-12-06T03:35:21Z)
• Regularizing Variational Autoencoder with Diversity and Uncertainty Awareness [61.827054365139645]
  Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. We propose an alternative model, DU-VAE, for learning a more Diverse and less Uncertain latent space.
  arXiv  Detail & Related papers  (2021-10-24T07:58:13Z)
• Efficient Semi-Implicit Variational Inference [65.07058307271329]
  We propose an efficient and scalable semi-implicit extrapolational (SIVI) Our method maps SIVI's evidence to a rigorous inference of lower gradient values.
  arXiv  Detail & Related papers  (2021-01-15T11:39:09Z)
• Cauchy-Schwarz Regularized Autoencoder [68.80569889599434]
  Variational autoencoders (VAE) are a powerful and widely-used class of generative models. We introduce a new constrained objective based on the Cauchy-Schwarz divergence, which can be computed analytically for GMMs. Our objective improves upon variational auto-encoding models in density estimation, unsupervised clustering, semi-supervised learning, and face analysis.
  arXiv  Detail & Related papers  (2021-01-06T17:36:26Z)

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.