
@@ 71,18 +71,18 @@

71

71

title = {Robust Learning from Demonstration Using Leveraged {{Gaussian}} Processes and SparseConstrained Optimization}

72

72

}

73

73


74


@article{damianou_deep_2012,

75


 abstract = {In this paper we introduce deep Gaussian process (GP) models. Deep GPs are a deep belief network based on Gaussian process mappings. The data is modeled as the output of a multivariate GP. The inputs to that Gaussian process are then governed by another GP. A single layer model is equivalent to a standard GP or the GP latent variable model (GPLVM). We perform inference in the model by approximate variational marginalization. This results in a strict lower bound on the marginal likelihood of the model which we use for model selection (number of layers and nodes per layer). Deep belief networks are typically applied to relatively large data sets using stochastic gradient descent for optimization. Our fully Bayesian treatment allows for the application of deep models even when data is scarce. Model selection by our variational bound shows that a five layer hierarchy is justified even when modelling a digit data set containing only 150 examples.},

76


 archivePrefix = {arXiv},

77


 author = {Damianou, Andreas C. and Lawrence, Neil D.},

78


 date = {20121101},

79


 eprint = {1211.0358},

80


 eprinttype = {arxiv},


74

+@inproceedings{damianou_deep_2013,


75

+ abstract = {In this paper we introduce deep Gaussian process (GP) models. Deep GPs are a deep belief network based on Gaussian process mappings. The data is modeled as the output of a multivariate GP. The inpu...},


76

+ author = {Damianou, Andreas and Lawrence, Neil},


77

+ booktitle = {Artificial {{Intelligence}} and {{Statistics}}},


78

+ date = {20130429},


79

+ eventtitle = {Artificial {{Intelligence}} and {{Statistics}}},

81

80

keywords = {60G15; 58E30,Computer Science  Learning,G.1.2,G.3,I.2.6,Mathematics  Probability,Statistics  Machine Learning},

82


 primaryClass = {cs, math, stat},


81

+ langid = {english},


82

+ pages = {207215},

83

83

title = {Deep {{Gaussian Processes}}},

84


 url = {http://arxiv.org/abs/1211.0358},

85


 urldate = {20160905}


84

+ url = {http://proceedings.mlr.press/v31/damianou13a.html},


85

+ urldate = {20181002}

86

86

}

87

87


88

88

@inproceedings{depeweg_decomposition_2018,


@@ 107,20 +107,6 @@

107

107

urldate = {20160606}

108

108

}

109

109


110


@article{hathaway_switching_1993,

111


 abstract = {A family of objective functions called fuzzy cregression models, which can be used too fit switching regression models to certain types of mixed data, is presented. Minimization of particular objective functions in the family yields simultaneous estimates for the parameters of c regression models, together with a fuzzy cpartitioning of the data. A general optimization approach for the family of objective functions is given and corresponding theoretical convergence results are discussed. The approach is illustrated by two numerical examples that show how it can be used to fit mixed data to coupled linear and nonlinear models},

112


 author = {Hathaway, R. J. and Bezdek, J. C.},

113


 date = {199308},

114


 doi = {10.1109/91.236552},

115


 issn = {10636706},

116


 journaltitle = {IEEE Transactions on Fuzzy Systems},

117


 keywords = {Clustering algorithms,Computer science,convergence,Convergence,convergence of numerical methods,Couplings,Covariance matrix,fuzzy cregression models,fuzzy clustering,fuzzy set theory,Fuzzy sets,Linear approximation,Marine animals,minimisation,mixed data,objective functions,parameter estimation,Parameter estimation,statistical analysis,switching regression models,Yield estimation},

118


 number = {3},

119


 pages = {195204},

120


 title = {Switching Regression Models and Fuzzy Clustering},

121


 volume = {1}

122


}

123




124

110

@inproceedings{hein_benchmark_2017,

125

111

abstract = {In the research area of reinforcement learning (RL), frequently novel and promising methods are developed and introduced to the RL community. However, although many researchers are keen to apply their methods on realworld problems, implementing such methods in real industry environments often is a frustrating and tedious process. Generally, academic research groups have only limited access to real industrial data and applications. For this reason, new methods are usually developed, evaluated and compared by using artificial software benchmarks. On one hand, these benchmarks are designed to provide interpretable RL training scenarios and detailed insight into the learning process of the method on hand. On the other hand, they usually do not share much similarity with industrial realworld applications. For this reason we used our industry experience to design a benchmark which bridges the gap between freely available, documented, and motivated artificial benchmarks and properties of real industrial problems. The resulting industrial benchmark (IB) has been made publicly available to the RL community by publishing its Java and Python code, including an OpenAI Gym wrapper, on Github. In this paper we motivate and describe in detail the IB's dynamics and identify prototypic experimental settings that capture common situations in realworld industry control problems.},

126

112

author = {Hein, D. and Depeweg, S. and Tokic, M. and Udluft, S. and Hentschel, A. and Runkler, T. A. and Sterzing, V.},


@@ 133,18 +119,14 @@

133

119

title = {A Benchmark Environment Motivated by Industrial Control Problems}

134

120

}

135

121


136


@article{hensman_gaussian_2013,

137


 abstract = {We introduce stochastic variational inference for Gaussian process models. This enables the application of Gaussian process (GP) models to data sets containing millions of data points. We show how GPs can be vari ationally decomposed to depend on a set of globally relevant inducing variables which factorize the model in the necessary manner to perform variational inference. Our ap proach is readily extended to models with nonGaussian likelihoods and latent variable models based around Gaussian processes. We demonstrate the approach on a simple toy problem and two real world data sets.},

138


 archivePrefix = {arXiv},


122

+@inproceedings{hensman_gaussian_2013,

139

123

author = {Hensman, James and Fusi, Nicolo and Lawrence, Neil D.},

140


 date = {20130926},

141


 eprint = {1309.6835},

142


 eprinttype = {arxiv},


124

+ booktitle = {Uncertainty in {{Artificial Intelligence}}},


125

+ date = {2013},

143

126

keywords = {Computer Science  Learning,Statistics  Machine Learning},

144


 primaryClass = {cs, stat},

145


 title = {Gaussian {{Processes}} for {{Big Data}}},

146


 url = {http://arxiv.org/abs/1309.6835},

147


 urldate = {20160706}


127

+ pages = {282},


128

+ publisher = {{Citeseer}},


129

+ title = {Gaussian {{Processes}} for {{Big Data}}}

148

130

}

149

131


150

132

@article{hensman_scalable_2015,


@@ 192,7 +174,7 @@

192

174

urldate = {20180608}

193

175

}

194

176


195


@incollection{kingma_variational_2015,


177

+@inproceedings{kingma_variational_2015,

196

178

author = {Kingma, Diederik P and Salimans, Tim and Welling, Max},

197

179

booktitle = {Advances in {{Neural Information Processing Systems}} 28},

198

180

date = {2015},


@@ 204,18 +186,15 @@

204

186

urldate = {20180912}

205

187

}

206

188


207


@article{lazarogredilla_overlapping_2011,

208


 abstract = {In this work we introduce a mixture of GPs to address the data association problem, i.e. to label a group of observations according to the sources that generated them. Unlike several previously proposed GP mixtures, the novel mixture has the distinct characteristic of using no gating function to determine the association of samples and mixture components. Instead, all the GPs in the mixture are global and samples are clustered following "trajectories" across input space. We use a nonstandard variational Bayesian algorithm to efficiently recover sample labels and learn the hyperparameters. We show how multiobject tracking problems can be disambiguated and also explore the characteristics of the model in traditional regression settings.},

209


 archivePrefix = {arXiv},

210


 author = {LázaroGredilla, Miguel and Van Vaerenbergh, Steven and Lawrence, Neil},

211


 date = {20110816},

212


 eprint = {1108.3372},

213


 eprinttype = {arxiv},


189

+@article{lazarogredilla_overlapping_2012,


190

+ author = {LázaroGredilla, Miguel and Van Vaerenbergh, Steven and Lawrence, Neil D.},


191

+ date = {2012},


192

+ journaltitle = {Pattern Recognition},

214

193

keywords = {Computer Science  Artificial Intelligence,Computer Science  Machine Learning,Statistics  Machine Learning},

215


 primaryClass = {cs, stat},

216


 title = {Overlapping {{Mixtures}} of {{Gaussian Processes}} for the {{Data Association Problem}}},

217


 url = {http://arxiv.org/abs/1108.3372},

218


 urldate = {20180806}


194

+ number = {4},


195

+ pages = {13861395},


196

+ title = {Overlapping Mixtures of {{Gaussian}} Processes for the Data Association Problem},


197

+ volume = {45}

219

198

}

220

199


221

200

@article{maddison_concrete_2016,


@@ 276,18 +255,17 @@

276

255

volume = {589}

277

256

}

278

257


279


@article{salimbeni_doubly_2017,

280


 abstract = {Gaussian processes (GPs) are a good choice for function approximation as they are flexible, robust to overfitting, and provide wellcalibrated predictive uncertainty. Deep Gaussian processes (DGPs) are multilayer generalisations of GPs, but inference in these models has proved challenging. Existing approaches to inference in DGP models assume approximate posteriors that force independence between the layers, and do not work well in practice. We present a doubly stochastic variational inference algorithm, which does not force independence between layers. With our method of inference we demonstrate that a DGP model can be used effectively on data ranging in size from hundreds to a billion points. We provide strong empirical evidence that our inference scheme for DGPs works well in practice in both classification and regression.},

281


 archivePrefix = {arXiv},


258

+@inproceedings{salimbeni_doubly_2017,

282

259

author = {Salimbeni, Hugh and Deisenroth, Marc},

283


 date = {20170524},

284


 eprint = {1705.08933},

285


 eprinttype = {arxiv},


260

+ booktitle = {Advances in {{Neural Information Processing Systems}} 30},


261

+ date = {2017},


262

+ editor = {Guyon, I. and Luxburg, U. V. and Bengio, S. and Wallach, H. and Fergus, R. and Vishwanathan, S. and Garnett, R.},

286

263

keywords = {Statistics  Machine Learning},

287


 primaryClass = {stat},


264

+ pages = {45884599},


265

+ publisher = {{Curran Associates, Inc.}},

288

266

title = {Doubly {{Stochastic Variational Inference}} for {{Deep Gaussian Processes}}},

289


 url = {http://arxiv.org/abs/1705.08933},

290


 urldate = {20170602}


267

+ url = {http://papers.nips.cc/paper/7045doublystochasticvariationalinferencefordeepgaussianprocesses.pdf},


268

+ urldate = {20181002}

291

269

}

292

270


293

271

@article{tensorflow2015whitepaper,
