paper-with-me

Papers

On Unifying Deep Generative Models

2017-06-02 · ICLR 2018 1 · Zhiting Hu, Zichao Yang, Ruslan Salakhutdinov, Eric P. Xing

Deep generative models have achieved impressive success in recent years. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for generative model learning, have largely been considered as two distinct paradigms and received extensive independent studies respectively. This paper aims to establish formal connections between GANs and VAEs through a new formulation of them. We interpret sample generation in GANs as performing posterior inference, and show that GANs and VAEs involve minimizing KL divergences of respective posterior and inference distributions with opposite directions, extending the two learning phases of classic wake-sleep algorithm, respectively. The unified view provides a powerful tool to analyze a diverse set of existing model variants, and enables to transfer techniques across research lines in a principled way. For example, we apply the importance weighting method in VAE literatures for improved GAN learning, and enhance VAEs with an adversarial mechanism that leverages generated samples. Experiments show generality and effectiveness of the transferred techniques.

📄 PDF Abstract BibTeX arXiv:1706.00550

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
USD Coin Customer Service Number +1-833-534-1729 설명 없음
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

Unifying Generative Models with GFlowNets and Beyond

2022-09-06 · Dinghuai Zhang, Ricky T. Q. Chen, Nikolay Malkin, Yoshua Bengio

There are many frameworks for deep generative modeling, each often presented with their own specific training algorithms and inference methods. Here, we demonstrate the connections between existing deep generative models…

Decision Making

Unifying Search and Recommendation: A Generative Paradigm Inspired by Information Theory

2025-04-09 · Jujia Zhao, Wenjie Wang, Chen Xu, Xiuying Wang 외

Recommender systems and search engines serve as foundational elements of online platforms, with the former delivering information proactively and the latter enabling users to seek information actively. Unifying both task…

Contrastive LearningRecommendation SystemsRepresentation Learning

Probability Functional Descent: A Unifying Perspective on GANs, Variational Inference, and Reinforcement Learning

2019-01-30 · Casey Chu, Jose Blanchet, Peter Glynn

This paper provides a unifying view of a wide range of problems of interest in machine learning by framing them as the minimization of functionals defined on the space of probability measures. In particular, we show that…

BIG-bench Machine Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

New Losses for Generative Adversarial Learning

2018-07-03 · Victor Berger, Michèle Sebag

Generative Adversarial Networks (Goodfellow et al., 2014), a major breakthrough in the field of generative modeling, learn a discriminator to estimate some distance between the target and the candidate distributions. T…

Killing Two Birds with One Stone: Unifying Retrieval and Ranking with a Single Generative Recommendation Model

2025-04-23 · Luankang Zhang, Kenan Song, Yi Quan Lee, Wei Guo 외

In recommendation systems, the traditional multi-stage paradigm, which includes retrieval and ranking, often suffers from information loss between stages and diminishes performance. Recent advances in generative models, …

Recommendation SystemsRetrieval