paper-with-me

홈 › Papers

Deep equilibrium models as estimators for continuous latent variables

2022-11-11 · Russell Tsuchida, Cheng Soon Ong

Principal Component Analysis (PCA) and its exponential family extensions have three components: observations, latents and parameters of a linear transformation. We consider a generalised setting where the canonical parameters of the exponential family are a nonlinear transformation of the latents. We show explicit relationships between particular neural network architectures and the corresponding statistical models. We find that deep equilibrium models -- a recently introduced class of implicit neural networks -- solve maximum a-posteriori (MAP) estimates for the latents and parameters of the transformation. Our analysis provides a systematic way to relate activation functions, dropout, and layer structure, to statistical assumptions about the observations, thus providing foundational principles for unsupervised DEQs. For hierarchical latents, individual neurons can be interpreted as nodes in a deep graphical model. Our DEQ feature maps are end-to-end differentiable, enabling fine-tuning for downstream tasks.

📄 PDF Abstract BibTeX arXiv:2211.05943

Code (1)

russelltsuchida/ped 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

DEQ A new kind of implicit models, where the output of the network is defined as the solution to an "infinite-level" fixed point equation. Thanks to this we can compute the gradient…

Similar Papers 제목 키워드 기반

Coupled Gradient Estimators for Discrete Latent Variables

2021-06-15 · NeurIPS 2021 12 · Zhe Dong, andriy mnih, George Tucker

Training models with discrete latent variables is challenging due to the high variance of unbiased gradient estimators. While low-variance reparameterization gradients of a continuous relaxation can provide an effective …

Counterfactual Sensitivity and Robustness

2019-04-01 · Timothy Christensen, Benjamin Connault

We propose a framework for analyzing the sensitivity of counterfactuals to parametric assumptions about the distribution of latent variables in structural models. In particular, we derive bounds on counterfactuals as the…

counterfactualDiscrete Choice ModelsSensitivity

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

2020-07-03 · NeurIPS 2020 12 · Gonçalo M. Correia, Vlad Niculae, Wilker Aziz, André F. T. Martins

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue…

REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models

2017-03-21 · NeurIPS 2017 12 · George Tucker, andriy mnih, Chris J. Maddison, Dieterich Lawson 외

Learning in models with discrete latent variables is challenging due to high variance gradient estimators. Generally, approaches have relied on control variates to reduce the variance of the REINFORCE estimator. Recent w…

Estimating Mutual Information for Discrete-Continuous Mixtures

2017-09-19 · NeurIPS 2017 12 · Weihao Gao, Sreeram Kannan, Sewoong Oh, Pramod Viswanath

Estimating mutual information from observed samples is a basic primitive, useful in several machine learning tasks including correlation mining, information bottleneck clustering, learning a Chow-Liu tree, and conditiona…

ClusteringMutual Information Estimation