Training energy-based models for time-series imputation

By Philemon Brakel, Dirk Stroobandt, Benjamin Schrauwen. 2013

41 citations recorded by the source corpus.

Subfields: Applied Mathematics, Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Applied Mathematics

In Artificial Intelligence

Citations in the corpus

OptNet: Differentiable Optimization as a Layer in Neural Networks (2017, background): “Among many other applications, these architectures are well-studied for generic classification and structured prediction tasks (Goodfellow et al., 2013; Stoyanov et al., 2011; Brakel et al., 2013; LeCun et al., 2006; Belanger & McCallum, 2016; Belanger et al., 2017; Amos et al., 2017); in vision for”
Iterative Neural Autoregressive Distribution Estimator NADE-k (2014, methodology): “In this paper we reinterpret the reconstruction procedure as a single iteration in a variational inference algorithm, and we propose a version where we use k iterations instead, inspired by (Goodfellow et al. , 2013; Brakel et al. , 2013).”
End-to-End Learning for Structured Prediction Energy Networks (2017, methodology): “End-to-end training for gradient-based prediction was introduced in Domke (2012) and applied to deep energy models by Brakel et al. (2013).”
A Two-Stage Pretraining Algorithm for Deep Boltzmann Machines (2013, background): “The authors of [15] and [6] proposed an alternative learning criterion based on the idea of generalized pseudo-likelihood [21].”
Differentiable Convex Optimization Layers (2019, background): “It is possible to differentiate through nonconvex problems, either analytically [37, 67, 5] or by unrolling SGD [33, 14, 61, 41, 70, 23, 38], Because convex programs can typically be solved efﬁciently and to high accuracy, it is preferable to use convex optimization layers over nonconvex…”
Multi-Prediction Deep Boltzmann Machines (2013, methodology): “[6] apply hard-coded loss functions such as mean squared error to the predictions of the missing values.”
Semi-Amortized Variational Autoencoders (2018, methodology): “…was initially explored by various researchers primarily outside the area of deep learning (Stoyanov et al., 2011; Domke, 2012; Brakel et al., 2013), they have more recently been explored in the context of hyperparameter optimization (Maclaurin et al., 2015) and as a…”
BRITS: Bidirectional Recurrent Imputation for Time Series (2018, background): “In a unidirectional recurrent dynamical system, each value in the time series can be derived by its predecessors with a fixed arbitrary function [9, 24, 3].”