paper-with-me

홈 › Papers

Autoregressive Models: What Are They Good For?

2019-10-17 · Murtaza Dalal, Alexander C. Li, Rohan Taori

Autoregressive (AR) models have become a popular tool for unsupervised learning, achieving state-of-the-art log likelihood estimates. We investigate the use of AR models as density estimators in two settings -- as a learning signal for image translation, and as an outlier detector -- and find that these density estimates are much less reliable than previously thought. We examine the underlying optimization issues from both an empirical and theoretical perspective, and provide a toy example that illustrates the problem. Overwhelmingly, we find that density estimates do not correlate with perceptual quality and are unhelpful for downstream tasks.

📄 PDF Abstract BibTeX arXiv:1910.07737

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Similar Papers 제목 키워드 기반

Lformer: Text-to-Image Generation with L-shape Block Parallel Decoding

2023-03-07 · Jiacheng Li, Longhui Wei, Zongyuan Zhan, Xin He 외

Generative transformers have shown their superiority in synthesizing high-fidelity and high-resolution images, such as good diversity and training stability. However, they suffer from the problem of slow generation since…

DiversityImage GenerationText to Image GenerationText-to-Image Generation

Semi-Autoregressive Transformer for Image Captioning

2021-06-17 · Yuanen Zhou, Yong Zhang, Zhenzhen Hu, Meng Wang

Current state-of-the-art image captioning models adopt autoregressive decoders, \ie they generate each word by conditioning on previously generated words, which leads to heavy latency during inference. To tackle this iss…

Image Captioning

Neural Autoregressive Distribution Estimation

2016-05-07 · Benigno Uria, Marc-Alexandre Côté, Karol Gregor, Iain Murray 외

We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estimation. They leverage the probability pro…

Density EstimationImage Generation

AI for the Common Good?! Pitfalls, challenges, and Ethics Pen-Testing

2018-10-30 · Bettina Berendt

Recently, many AI researchers and practitioners have embarked on research visions that involve doing AI for "Good". This is part of a general drive towards infusing AI research and practice with ethical thinking. One fre…

Ethics

Probability Distributions Computed by Autoregressive Transformers

2025-10-31 · Andy Yang, Anej Svete, Jiaoda Li, Anthony Widjaja Lin 외 arxiv

Most expressivity results for transformers treat them as language recognizers -- devices that accept or reject strings -- rather than as they are used in practice: as language models that generate strings autoregressivel…