paper-with-me

Papers

FlowVAT: Normalizing Flow Variational Inference with Affine-Invariant Tempering

2025-05-15 · Juehang Qin, Shixiao Liang, Christopher Tunnell

Multi-modal and high-dimensional posteriors present significant challenges for variational inference, causing mode-seeking behavior and collapse despite the theoretical expressiveness of normalizing flows. Traditional annealing methods require temperature schedules and hyperparameter tuning, falling short of the goal of truly black-box variational inference. We introduce FlowVAT, a conditional tempering approach for normalizing flow variational inference that addresses these limitations. Our method tempers both the base and target distributions simultaneously, maintaining affine-invariance under tempering. By conditioning the normalizing flow on temperature, we leverage overparameterized neural networks' generalization capabilities to train a single flow representing the posterior across a range of temperatures. This preserves modes identified at higher temperatures when sampling from the variational posterior at $T = 1$, mitigating standard variational methods' mode-seeking behavior. In experiments with 2, 10, and 20 dimensional multi-modal distributions, FlowVAT outperforms traditional and adaptive annealing methods, finding more modes and achieving better ELBO values, particularly in higher dimensions where existing approaches fail. Our method requires minimal hyperparameter tuning and does not require an annealing schedule, advancing toward fully-automatic black-box variational inference for complicated posteriors.

📄 PDF Abstract BibTeX arXiv:2505.10466

Code (0)

등록된 구현이 없습니다.

Tasks

Variational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음
BASE 설명 없음

Similar Papers 제목 키워드 기반

Sylvester Normalizing Flows for Variational Inference

2018-03-15 · Rianne van den Berg, Leonard Hasenclever, Jakub M. Tomczak, Max Welling

Variational inference relies on flexible approximate posterior distributions. Normalizing flows provide a general recipe to construct flexible variational posteriors. We introduce Sylvester normalizing flows, which can b…

Variational Inference

Automatic variational inference with cascading flows

2021-02-09 · Luca Ambrogioni, Gianluigi Silvestri, Marcel van Gerven

The automation of probabilistic reasoning is one of the primary aims of machine learning. Recently, the confluence of variational inference and deep learning has led to powerful and flexible automatic inference methods t…

Variational Inference

Tensorizing flows: a tool for variational inference

2023-05-03 · Yuehaw Khoo, Michael Lindsey, Hongli Zhao

Fueled by the expressive power of deep neural networks, normalizing flows have achieved spectacular success in generative modeling, or learning to draw new samples from a distribution given a finite dataset of training s…

Tensor NetworksVariational Inference

Convolutional Normalizing Flows

2017-11-07 · ICLR 2018 1 · Guoqing Zheng, Yiming Yang, Jaime Carbonell

Bayesian posterior inference is prevalent in various machine learning problems. Variational inference provides one way to approximate the posterior distribution, however its expressive power is limited and so is the accu…

Variational Inference

Variational Inference with Normalizing Flows

2015-05-21 · Danilo Jimenez Rezende, Shakir Mohamed

The choice of approximate posterior distribution is one of the core problems in variational inference. Most applications of variational inference employ simple families of posterior approximations in order to allow for e…

Variational Inference