paper-with-me

홈 › Papers

Pseudo-Spherical Contrastive Divergence

2021-11-01 · NeurIPS 2021 12 · Lantao Yu, Jiaming Song, Yang song, Stefano Ermon

Energy-based models (EBMs) offer flexible distribution parametrization. However, due to the intractable partition function, they are typically trained via contrastive divergence for maximum likelihood estimation. In this paper, we propose pseudo-spherical contrastive divergence (PS-CD) to generalize maximum likelihood learning of EBMs. PS-CD is derived from the maximization of a family of strictly proper homogeneous scoring rules, which avoids the computation of the intractable partition function and provides a generalized family of learning objectives that include contrastive divergence as a special case. Moreover, PS-CD allows us to flexibly choose various learning objectives to train EBMs without additional computational cost or variational minimax optimization. Theoretical analysis on the proposed method and extensive experiments on both synthetic data and commonly used image datasets demonstrate the effectiveness and modeling flexibility of PS-CD, as well as its robustness to data contamination, thus showing its superiority over maximum likelihood and $f$-EBMs.

📄 PDF Abstract BibTeX arXiv:2111.00780

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bayesian Pseudo-Coresets via Contrastive Divergence

2023-03-20 · Piyush Tiwary, Kumar Shubham, Vivek V. Kashyap, Prathosh A. P

Bayesian methods provide an elegant framework for estimating parameter posteriors and quantification of uncertainty associated with probabilistic models. However, they often suffer from slow inference times. To address t…

Dataset Condensation

Spherical Space Domain Adaptation With Robust Pseudo-Label Loss

2020-06-01 · CVPR 2020 6 · Xiang Gu, Jian Sun, Zongben Xu

Adversarial domain adaptation (DA) has been an effective approach for learning domain-invariant features by adversarial training. In this paper, we propose a novel adversarial DA approach completely defined in spherical …

Domain AdaptationPseudo Label

Deep Spherical Manifold Gaussian Kernel for Unsupervised Domain Adaptation

2021-05-05 · Youshan Zhang, Brian D. Davison

Unsupervised Domain adaptation is an effective method in addressing the domain shift issue when transferring knowledge from an existing richly labeled domain to a new domain. Existing manifold-based methods either are ba…

Domain AdaptationPseudo LabelUnsupervised Domain Adaptation

Robust Semi-supervised Learning via $f$-Divergence and $α$-Rényi Divergence

2024-05-01 · Gholamali Aminian, Amirhossien Bagheri, Mahyar JafariNodeh, Radmehr Karimian 외

This paper investigates a range of empirical risk functions and regularization methods suitable for self-training methods in semi-supervised learning. These approaches draw inspiration from various divergence measures, s…

Pseudo Label

Unifying Non-Maximum Likelihood Learning Objectives with Minimum KL Contraction

2011-12-01 · NeurIPS 2011 12 · Siwei Lyu

When used to learn high dimensional parametric probabilistic models, the clas- sical maximum likelihood (ML) learning often suffers from computational in- tractability, which motivates the active developments of non-ML l…