English
Related papers

Related papers: Globally Convergent Variational Inference

200 papers

This paper studies the Variational Inference (VI) used for training Bayesian Neural Networks (BNN) in the overparameterized regime, i.e., when the number of neurons tends to infinity. More specifically, we consider overparameterized…

Machine Learning · Statistics 2022-07-11 Tom Huix , Szymon Majewski , Alain Durmus , Eric Moulines , Anna Korba

Variational Autoencoder (VAE) is widely used as a generative model to approximate a model's posterior on latent variables by combining the amortized variational inference and deep neural networks. However, when paired with strong…

Machine Learning · Computer Science 2020-06-02 Qile Zhu , Jianlin Su , Wei Bi , Xiaojiang Liu , Xiyao Ma , Xiaolin Li , Dapeng Wu

Semi-implicit variational inference (SIVI) enriches the expressiveness of variational families by utilizing a kernel and a mixing distribution to hierarchically define the variational distribution. Existing SIVI methods parameterize the…

Machine Learning · Statistics 2025-01-16 Jen Ning Lim , Adam M. Johansen

We extend several recent results providing symmetry-based guarantees for variational inference (VI) with location-scale families. VI approximates a target density $p$ by the best match $q^*$ in a family $Q$ of tractable distributions that…

Machine Learning · Statistics 2025-12-11 Charles C. Margossian , Lawrence K. Saul

Weight space symmetries in neural network architectures, such as permutation symmetries in MLPs, give rise to Bayesian neural network (BNN) posteriors with many equivalent modes. This multimodality poses a challenge for variational…

Machine Learning · Computer Science 2024-08-13 Yoav Gelberg , Tycho F. A. van der Ouderaa , Mark van der Wilk , Yarin Gal

Unnormalised latent variable models are a broad and flexible class of statistical models. However, learning their parameters from data is intractable, and few estimation techniques are currently available for such models. To increase the…

Machine Learning · Statistics 2019-02-26 Benjamin Rhodes , Michael Gutmann

This paper tackles the challenge of multi-sensor multi-object tracking by proposing various decentralised Variational Inference (VI) schemes that match the tracking performance of centralised sensor fusion with only local message exchanges…

Machine Learning · Computer Science 2024-11-26 Qing Li , Runze Gan , Simon Godsill

Stein variational gradient descent (SVGD) [Liu and Wang, 2016] performs approximate Bayesian inference by representing the posterior with a set of particles. However, SVGD suffers from variance collapse, i.e. poor predictions due to…

Machine Learning · Computer Science 2025-01-27 Ola Rønning , Eric Nalisnick , Christophe Ley , Padhraic Smyth , Thomas Hamelryck

We advocate an optimization-centric view on and introduce a novel generalization of Bayesian inference. Our inspiration is the representation of Bayes' rule as infinite-dimensional optimization problem (Csiszar, 1975; Donsker and Varadhan;…

Machine Learning · Statistics 2019-12-13 Jeremias Knoblauch , Jack Jewson , Theodoros Damoulas

Bayesian Neural Networks (BNNs) are trained to optimize an entire distribution over their weights instead of a single set, having significant advantages in terms of, e.g., interpretability, multi-task learning, and calibration. Because of…

Machine Learning · Computer Science 2022-10-07 Jary Pomponi , Simone Scardapane , Aurelio Uncini

Variational inference methods for latent variable statistical models have gained popularity because they are relatively fast, can handle large data sets, and have deterministic convergence guarantees. However, in practice it is unclear…

Methodology · Statistics 2017-03-22 Hachem Saddiki , Andrew C. Trapp , Patrick Flaherty

In this paper, we bridge Variational Autoencoders (VAEs) and kernel density estimations (KDEs) by approximating the posterior by KDEs and deriving an upper bound of the Kullback-Leibler (KL) divergence in the evidence lower bound (ELBO).…

Machine Learning · Statistics 2025-05-13 Tian Qin , Wei-Min Huang

Variational inference (VI) is a popular approach in Bayesian inference, that looks for the best approximation of the posterior distribution within a parametric family, minimizing a loss that is typically the (reverse) Kullback-Leibler (KL)…

Machine Learning · Statistics 2025-11-18 Marguerite Petit-Talamon , Marc Lambert , Anna Korba

We introduce the neural tangent kernel (NTK) regime for two-layer neural operators and analyze their generalization properties. For early-stopped gradient descent (GD), we derive fast convergence rates that are known to be minimax optimal…

Machine Learning · Statistics 2024-12-24 Mike Nguyen , Nicole Mücke

Developing efficient solutions for inference problems in intelligent sensor networks is crucial for the next generation of location, tracking, and mapping services. This paper develops a scalable distributed probabilistic inference…

Machine Learning · Computer Science 2023-10-24 Parth Paritosh , Nikolay Atanasov , Sonia Martinez

Traditional neural networks are simple to train but they typically produce overconfident predictions. In contrast, Bayesian neural networks provide good uncertainty quantification but optimizing them is time consuming due to the large…

Machine Learning · Computer Science 2024-11-07 Yadi Wei , Roni Khardon

We propose stepwise variational inference (VI) with vine copulas: a universal VI procedure that combines vine copulas with a novel stepwise estimation procedure of the variational parameters. Vine copulas consist of a nested sequence of…

Machine Learning · Statistics 2026-03-25 Elisabeth Griesbauer , Leiv Rønneberg , Arnoldo Frigessi , Claudia Czado , Ingrid Hobæk Haff

One of the core problems of modern statistics is to approximate difficult-to-compute probability densities. This problem is especially important in Bayesian statistics, which frames all inference about unknown quantities as a calculation…

Computation · Statistics 2018-05-11 David M. Blei , Alp Kucukelbir , Jon D. McAuliffe

In variational inference (VI), the marginal log-likelihood is estimated using the standard evidence lower bound (ELBO), or improved versions as the importance weighted ELBO (IWELBO). We propose the multiple importance sampling ELBO…

Machine Learning · Computer Science 2022-02-23 Oskar Kviman , Harald Melin , Hazal Koptagel , Víctor Elvira , Jens Lagergren

Posterior inference in directed graphical models is commonly done using a probabilistic encoder (a.k.a inference model) conditioned on the input. Often this inference model is trained jointly with the probabilistic decoder (a.k.a generator…

Machine Learning · Computer Science 2019-12-21 Amir Zadeh , Smon Hessner , Yao-Chong Lim , Louis-Phlippe Morency