paper-with-me

홈 › Papers

Variational Inference with Holder Bounds

2021-11-04 · Junya Chen, Danni Lu, Zidi Xiu, Ke Bai, Lawrence Carin, Chenyang Tao

The recent introduction of thermodynamic integration techniques has provided a new framework for understanding and improving variational inference (VI). In this work, we present a careful analysis of the thermodynamic variational objective (TVO), bridging the gap between existing variational objectives and shedding new insights to advance the field. In particular, we elucidate how the TVO naturally connects the three key variational schemes, namely the importance-weighted VI, Renyi-VI, and MCMC-VI, which subsumes most VI objectives employed in practice. To explain the performance gap between theory and practice, we reveal how the pathological geometry of thermodynamic curves negatively affects TVO. By generalizing the integration path from the geometric mean to the weighted Holder mean, we extend the theory of TVO and identify new opportunities for improving VI. This motivates our new VI objectives, named the Holder bounds, which flatten the thermodynamic curves and promise to achieve a one-step approximation of the exact marginal log-likelihood. A comprehensive discussion on the choices of numerical estimators is provided. We present strong empirical evidence on both synthetic and real-world datasets to support our claims.

📄 PDF Abstract BibTeX arXiv:2111.02947

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음

Similar Papers 제목 키워드 기반

Approximate Inference with the Variational Holder Bound

2015-06-19 · Guillaume Bouchard, Balaji Lakshminarayanan

We introduce the Variational Holder (VH) bound as an alternative to Variational Bayes (VB) for approximate Bayesian inference. Unlike VB which typically involves maximization of a non-convex lower bound with respect to t…

Bayesian InferenceNumerical Integration

Validated Variational Inference via Practical Posterior Error Bounds

2019-10-09 · Jonathan H. Huggins, Mikołaj Kasprzak, Trevor Campbell, Tamara Broderick

Variational inference has become an increasingly attractive fast alternative to Markov chain Monte Carlo methods for approximate Bayesian inference. However, a major obstacle to the widespread use of variational methods …

Bayesian InferenceVariational Inference

Learning with Importance Weighted Variational Inference: Asymptotics for Gradient Estimators of the VR-IWAE Bound

2024-10-15 · Kamélia Daudel, François Roueff

Several popular variational bounds involving importance weighting ideas have been proposed to generalize and improve on the Evidence Lower BOund (ELBO) in the context of maximum likelihood optimization, such as the Impor…

Variational Inference

Debiasing Evidence Approximations: On Importance-weighted Autoencoders and Jackknife Variational Inference

2018-01-01 · ICLR 2018 1 · Sebastian Nowozin

The importance-weighted autoencoder (IWAE) approach of Burda et al. defines a sequence of increasingly tighter bounds on the marginal likelihood of latent variable models. Recently, Cremer et al. reinterpreted the IWAE b…

Computational EfficiencyVariational Inference

Few Shot Activity Recognition Using Variational Inference

2021-08-20 · Neeraj Kumar, Siddhansh Narang

There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of…

Action RecognitionActivity RecognitionFew-Shot LearningHuman Activity Recognition+1