English
Related papers

Related papers: Refined $\alpha$-Divergence Variational Inference …

200 papers

Variational inference consists in finding the best approximation of a target distribution within a certain family, where `best' means (typically) smallest Kullback-Leiber divergence. We show that, when the approximation family is…

Computation · Statistics 2025-09-24 Yvann Le Fay , Nicolas Chopin , Simon Barthelmé

In this paper, we introduce a novel family of iterative algorithms which carry out $\alpha$-divergence minimisation in a Variational Inference context. They do so by ensuring a systematic decrease at each step in the $\alpha$-divergence…

Computation · Statistics 2023-04-12 Kamélia Daudel , Randal Douc , François Roueff

With the rising number of machine learning competitions, the world has witnessed an exciting race for the best algorithms. However, the involved data selection process may fundamentally suffer from evidence ambiguity and concept drift…

Machine Learning · Computer Science 2020-06-15 Hoang D. Nguyen , Xuan-Son Vu , Quoc-Tuan Truong , Duc-Trong Le

A key design constraint when implementing Monte Carlo and variational inference algorithms is that it must be possible to cheaply and exactly evaluate the marginal densities of proposal distributions and variational families. This takes…

Machine Learning · Computer Science 2022-11-22 Alexander K. Lew , Marco Cusumano-Towner , Vikash K. Mansinghka

Generalized variational inference (GVI) provides an optimization-theoretic framework for statistical estimation that encapsulates many traditional estimation procedures. The typical GVI problem is to compute a distribution of parameters…

Optimization and Control · Mathematics 2023-10-27 Aurya S. Javeed , Drew P. Kouri , Thomas M. Surowiec

Variational inference is a scalable technique for approximate Bayesian inference. Deriving variational inference algorithms requires tedious model-specific calculations; this makes it difficult to automate. We propose an automatic…

Machine Learning · Statistics 2015-06-15 Alp Kucukelbir , Rajesh Ranganath , Andrew Gelman , David M. Blei

In this work, we develop a novel Bayesian estimation method for the Dirichlet process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very flexible for modeling vectors with positive elements. The recently…

Machine Learning · Computer Science 2020-02-04 Zhanyu Ma , Yuping Lai

This dissertation investigates relative entropies, also called generalized divergences, and how they can be used to characterize information-theoretic tasks in quantum information theory. The main goal is to further refine characterizations…

Quantum Physics · Physics 2016-11-29 Felix Leditzky

This paper analyzes reinforcement learning (RL) algorithms for Markov decision processes (MDPs) under the average-reward criterion. We focus on Q-learning algorithms based on relative value iteration (RVI), which are model-free stochastic…

Machine Learning · Computer Science 2024-08-30 Yi Wan , Huizhen Yu , Richard S. Sutton

We propose new nonparametric accordance R\'enyi-$\alpha$ and $\alpha$-Tsallis divergence estimators for continuous distributions. We discuss this approach with a view to the selection model (on al\'etoire and autoregressive AR (1)). We…

Methodology · Statistics 2014-01-22 Hamza Dhaker , Papa Ngom , Pierre Mendy

Channel simulation is to simulate a noisy channel using noiseless channels with unlimited shared randomness. This can be interpreted as the reverse problem to Shannon's noisy coding theorem. In contrast to previous works, our approach…

Information Theory · Computer Science 2025-06-06 Shi-Bing Li , Ke Li , Lei Yu

Respondent-Driven Sampling (RDS) employs a variant of a link-tracing network sampling strategy to collect data from hard-to-reach populations. By tracing the links in the underlying social network, the process exploits the social structure…

Applications · Statistics 2009-04-14 Krista J. Gile , Mark S. Handcock

We develop a divergence-minimization (DM) framework for robust and efficient inference in latent-mixture models. By optimizing a residual-adjusted divergence, the DM approach recovers EM as a special case and yields robust alternatives…

Statistics Theory · Mathematics 2025-11-25 Lei Li , Anand N. Vidyashankar

Neural networks are popular state-of-the-art models for many different tasks.They are often trained via back-propagation to find a value of the weights that correctly predicts the observed data. Although back-propagation has shown good…

Machine Learning · Statistics 2020-12-29 Simón Rodríguez Santana , Daniel Hernández-Lobato

Variance estimation is a fundamental problem in statistical modeling. In ultrahigh dimensional linear regressions where the dimensionality is much larger than sample size, traditional variance estimation techniques are not applicable.…

Methodology · Statistics 2010-12-27 Jianqing Fan , Shaojun Guo , Ning Hao

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs),…

Machine Learning · Computer Science 2024-02-26 Zhishuai Liu , Pan Xu

We study risk-sensitive reinforcement learning in episodic Markov decision processes with unknown transition kernels, where the goal is to optimize the total reward under the risk measure of exponential utility. We propose two provably…

Machine Learning · Computer Science 2020-06-25 Yingjie Fei , Zhuoran Yang , Yudong Chen , Zhaoran Wang , Qiaomin Xie

Although the diffusion model has achieved remarkable performance in the field of image generation, its high inference delay hinders its wide application in edge devices with scarce computing resources. Therefore, many training-free sampling…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Weilun Feng , Chuanguang Yang , Zhulin An , Libo Huang , Boyu Diao , Fei Wang , Yongjun Xu

Respondent-Driven Sampling (RDS) is a chain-referral design used for collecting data from hidden or hard-to-reach populations through their social networks. In RDS, respondents recruit their peers from the population of interest. As such,…

Methodology · Statistics 2026-04-14 Vanesa Reinoso , Danilo Alvares , Jonathan Acosta , Isabelle S. Beaudry

The Robust Regularized Markov Decision Process (RRMDP) is proposed to learn policies robust to dynamics shifts by adding regularization to the transition dynamics in the value function. Existing methods mostly use unstructured…

Machine Learning · Computer Science 2025-11-03 Cheng Tang , Zhishuai Liu , Pan Xu