paper-with-me

홈 › Papers

Noise Contrastive Estimation and Negative Sampling for Conditional Models: Consistency and Statistical Efficiency

2018-09-06 · EMNLP 2018 10 · Zhuang Ma, Michael Collins

Noise Contrastive Estimation (NCE) is a powerful parameter estimation method for log-linear models, which avoids calculation of the partition function or its derivatives at each training step, a computationally demanding step in many cases. It is closely related to negative sampling methods, now widely used in NLP. This paper considers NCE-based estimation of conditional models. Conditional models are frequently encountered in practice; however there has not been a rigorous theoretical analysis of NCE in this setting, and we will argue there are subtle but important questions when generalizing NCE to the conditional case. In particular, we analyze two variants of NCE for conditional models: one based on a classification objective, the other based on a ranking objective. We show that the ranking-based variant of NCE gives consistent parameter estimates under weaker assumptions than the classification-based method; we analyze the statistical efficiency of the ranking-based and classification-based variants of NCE; finally we describe experiments on synthetic data and language modeling showing the effectiveness and trade-offs of both methods.

📄 PDF Abstract BibTeX arXiv:1809.01812

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationLanguage ModelingLanguage Modellingparameter estimationQuestion Answering

Similar Papers 제목 키워드 기반

Conditional Negative Sampling for Contrastive Learning of Visual Representations

2020-10-05 · ICLR 2021 1 · Mike Wu, Milan Mosse, Chengxu Zhuang, Daniel Yamins 외

Recent methods for learning unsupervised visual representations, dubbed contrastive learning, optimize the noise-contrastive estimation (NCE) bound on mutual information between two views of an image. NCE uses randomly s…

Contrastive LearningInstance SegmentationKeypoint DetectionLinear evaluation+3

On the connection between Noise-Contrastive Estimation and Contrastive Divergence

2024-02-26 · Amanda Olmin, Jakob Lindqvist, Lennart Svensson, Fredrik Lindsten

Noise-contrastive estimation (NCE) is a popular method for estimating unnormalised probabilistic models, such as energy-based models, which are effective for modelling complex data distributions. Unlike classical maximum…

Mutual Information Estimation as a Difference of Entropies for Unsupervised Representation Learning

2021-09-29 · Jaeill Kim, Wonjong Rhee

Contrastive loss has been successfully exploited in the latest visual unsupervised representation learning methods. Contrastive loss is based on a lower-bound estimation of mutual information where its known limitations …

Mutual Information EstimationRepresentation Learning

Notes on Noise Contrastive Estimation and Negative Sampling

2014-10-30 · Chris Dyer

Estimating the parameters of probabilistic models of language such as maxent models and probabilistic neural models is computationally difficult since it involves evaluating partition functions by summing over an entire …

Binary Classificationparameter estimation

Do More Negative Samples Necessarily Hurt in Contrastive Learning?

2022-05-03 · Pranjal Awasthi, Nishanth Dikkala, Pritish Kamath

Recent investigations in noise contrastive estimation suggest, both empirically as well as theoretically, that while having more "negative samples" in the contrastive loss improves downstream classification performance i…

Contrastive Learning