Filters








17,692 Hits in 4.3 sec

Probabilistic Forecasting using Deep Generative Models [article]

Alessandro Fanfarillo, Behrooz Roozitalab, Weiming Hu, Guido Cervone
<span title="2019-09-26">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we investigate an alternative way to implement the AnEn method using deep generative models.  ...  By doing so, a generative model can entirely or partially replace the dataset of pairs of predictions and observations, reducing the amount of memory required to produce the probabilistic forecast by several  ...  Alessandrini for providing his code to generate the confidence intervals for the verification statistics.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.11865v1">arXiv:1909.11865v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vpnokm4ujrgixkzs4cm6eawqhu">fatcat:vpnokm4ujrgixkzs4cm6eawqhu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828074307/https://arxiv.org/pdf/1909.11865v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/23/38/23380657b2661f284b773d6eec3ea5da858aa28c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.11865v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A VAE-Based Bayesian Bidirectional LSTM for Renewable Energy Forecasting [article]

Devinder Kaur, Shama Naz Islam, Md. Apel Mahmud
<span title="2021-03-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper proposes a novel Bayesian probabilistic technique for forecasting renewable power generation by addressing data and model uncertainties by integrating bidirectional long short-term memory (BiLSTM  ...  It is inferred from the numerical results that VAE-Bayesian BiLSTM outperforms other probabilistic deep learning methods in terms of forecasting accuracy and computational efficiency for different sizes  ...  Finally, the trained model is used to obtain probabilistic forecasts of the renewable energy generation. The predictive mean and standard deviation of the predicted distribution is then computed.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.12969v1">arXiv:2103.12969v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kaocuj2aizflfmyonp5apwudpe">fatcat:kaocuj2aizflfmyonp5apwudpe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210328082719/https://arxiv.org/pdf/2103.12969v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c1/e8/c1e8cea80ba144da518bf692f4d5913957116965.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.12969v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Stanza: A Nonlinear State Space Model for Probabilistic Inference in Non-Stationary Time Series [article]

Anna K. Yanchenko, Sayan Mukherjee
<span title="2020-06-11">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Stanza strikes a balance between competitive forecasting accuracy and probabilistic, interpretable inference for highly structured time series.  ...  In particular, Stanza achieves forecasting accuracy competitive with deep LSTMs on real-world datasets, especially for multi-step ahead forecasting.  ...  Stanza is a step towards a powerful, general framework of incorporating deep learning ideas directly into traditional probabilistic models.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.06553v1">arXiv:2006.06553v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/exz7imft2zeizimaowywxq5z2e">fatcat:exz7imft2zeizimaowywxq5z2e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200623133856/https://arxiv.org/pdf/2006.06553v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.06553v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Quantile Regression Random Forest-Based Short-Term Load Probabilistic Forecasting Method

Sanlei Dang, Long Peng, Jingming Zhao, Jiajie Li, Zhengmin Kong
<span title="2022-01-17">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/a2yvk5xhdnhpxjnk6yd33uudqq" style="color: black;">Energies</a> </i> &nbsp;
Secondly, by exploiting multimodal deep neural networks (DNN), three short-term load point forecasting models are conceived.  ...  Thirdly, relying on quantile regression random forest, the probabilistic forecasting method is proposed, which exploits the results from the above three short-term load point forecasting models.  ...  [9] integrated widely used technologies in deep learning and proposed a short-term load probabilistic forecasting model based on an improved quantile regression neural network. Fan et al.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/en15020663">doi:10.3390/en15020663</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wmk3gzmibrarpgm3x6d456isme">fatcat:wmk3gzmibrarpgm3x6d456isme</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220126212229/https://mdpi-res.com/d_attachment/energies/energies-15-00663/article_deploy/energies-15-00663-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/62/85/6285ff57c559a030d748682099a019c0c78396c2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/en15020663"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Deep Distributional Time Series Models and the Probabilistic Forecasting of Intraday Electricity Prices [article]

Nadja Klein, Michael Stanley Smith, David J. Nott
<span title="2021-05-27">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Using data from the Australian National Electricity Market, we show that our deep time series models provide accurate short term probabilistic price forecasts, with the copula model dominating.  ...  In both approaches, Bayesian Markov chain Monte Carlo methods are used to estimate the models and compute forecasts.  ...  However, only the deep copula model allows for all three, producing the most accurate probabilistic forecasts.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01844v2">arXiv:2010.01844v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/xrgap65ntbbnvpxngog6ulfk3q">fatcat:xrgap65ntbbnvpxngog6ulfk3q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210531041905/https://arxiv.org/pdf/2010.01844v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2a/f8/2af8e75bc7a61d25849168d21ab6848b473dcb5e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.01844v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

KPF-AE-LSTM: A Deep Probabilistic Model for Net-Load Forecasting in High Solar Scenarios [article]

Deepthi Sen, Indrasis Chakraborty, Soumya Kundu, Andrew P. Reiman, Ian Beil, Andy Eiden
<span title="2022-03-05">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a deep learning method to generate probabilistic forecasts of day-ahead net-load at 15-min resolution, at various solar penetration levels.  ...  The models are shown to deliver superior forecast performance (as per several metrics), as well as maintain superior training efficiency, in comparison to existing benchmark models.  ...  In [27] , the authors used Bayesian deep learning to generate probabilistic residential net-load forecasts using LSTMs.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.04401v1">arXiv:2203.04401v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sobixonjrbc7jna2xco2exguym">fatcat:sobixonjrbc7jna2xco2exguym</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220313035604/https://arxiv.org/pdf/2203.04401v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/06/22/06226bbccb57639b52baca534376a06a1dfdc49a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.04401v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Energy Forecasting in Smart Grid Systems: A Review of the State-of-the-art Techniques [article]

Devinder Kaur, Shama Naz Islam, Md. Apel Mahmud, Md. Enamul Haque, ZhaoYang Dong
<span title="2022-05-23">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A comparative case study using the Victorian electricity consumption and American electric power (AEP) datasets is conducted to analyze the performance of point and probabilistic forecasting methods.  ...  This paper presents a comprehensive and application-oriented review of state-of-the-art forecasting methods for SG systems along with recent developments in probabilistic deep learning (PDL) considering  ...  Probabilistic deep learning (PDL) Bayesian probability incorporated with DL methods can be used to provide forecasting results in the form of PIs, contrary to traditional deep neural networks that are  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.12598v3">arXiv:2011.12598v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oxdx7u6we5aa7b3gqfpnpgrh7m">fatcat:oxdx7u6we5aa7b3gqfpnpgrh7m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220526132956/https://arxiv.org/pdf/2011.12598v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fa/93/fa93644c5784d76dd3034331921aa3c5032fd9dd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.12598v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Aggregating distribution forecasts from deep ensembles [article]

Benedikt Schulz, Sebastian Lerch
<span title="2022-04-05">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a general quantile aggregation framework for deep ensembles that shows superior performance compared to a linear combination of the forecast densities.  ...  These neural network-based methods are often used in the form of an ensemble based on multiple model runs from different random initializations, resulting in a collection of forecast distributions that  ...  Sebastian Lerch gratefully acknowledges support by the Vector Stiftung through the Young Investigator Group "Artificial Intelligence for Probabilistic Weather Forecasting".  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.02291v1">arXiv:2204.02291v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nbbrmo47yrcgzahejir5gs2aum">fatcat:nbbrmo47yrcgzahejir5gs2aum</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220519095419/https://arxiv.org/pdf/2204.02291v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/59/d6/59d6baf190087deca1314276d836c1d270dc758b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.02291v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Short-term Load Forecasting with Deep Residual Networks [article]

Kunjin Chen, Kunlong Chen, Qin Wang, Ziyu He, Jun Hu, Jinliang He
<span title="2018-05-30">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We also apply the proposed model to probabilistic load forecasting using Monte Carlo dropout. Three public datasets are used to prove the effectiveness of the proposed model.  ...  We present in this paper a model for forecasting short-term power loads based on deep residual networks.  ...  This indicates that the proposed model have the potential to be used for probabilistic load forecasting.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.11956v1">arXiv:1805.11956v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2s5albqmbbedfj6lnvfyr55f4y">fatcat:2s5albqmbbedfj6lnvfyr55f4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902052439/https://arxiv.org/pdf/1805.11956v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/8b/86/8b868e0f2930f8acdd6267be42bcec7ec80cae92.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1805.11956v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Probabilistic Deep Learning to Quantify Uncertainty in Air Quality Forecasting

Abdulmajid Murad, Frank Alexander Kraemer, Kerstin Bach, Gavin Taylor
<span title="2021-11-30">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/taedaf6aozg7vitz5dpgkojane" style="color: black;">Sensors</a> </i> &nbsp;
Recently, several practical tools to estimate uncertainty have been developed in probabilistic deep learning.  ...  We also propose improving these models using "free" adversarial training and exploiting temporal and spatial correlation inherent in air quality data.  ...  It is a widely used metric to evaluate probabilistic forecasts that generalizes the MAE to a probabilistic setting.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s21238009">doi:10.3390/s21238009</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34884011">pmid:34884011</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eijybkmemrfvdcm2sjnawfcng4">fatcat:eijybkmemrfvdcm2sjnawfcng4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220429170944/https://mdpi-res.com/d_attachment/sensors/sensors-21-08009/article_deploy/sensors-21-08009-v3.pdf?version=1638946867" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/15/4a/154acf2926fd053b78fdb65bd7fc6ce86f84ad9b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/s21238009"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Using the Residual Network Module to Correct the Sub-Seasonal High Temperature Forecast

Wei Jin, Wei Zhang, Jie Hu, Bin Weng, Tianqiang Huang, Jiazhen Chen
<span title="2022-01-12">2022</span> <i title="Frontiers Media SA"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/6lrazeiea5fp7mqpz4ogs5j7se" style="color: black;">Frontiers in Earth Science</a> </i> &nbsp;
Here, we develop multi-module daily deterministic and probabilistic forecast models by the residual structure and finally establish a complete set of sub-seasonal high temperature forecasting system in  ...  The high temperature forecast of the sub-season is a severe challenge.  ...  The data generated from the training and test sets of the deterministic forecasts after the network revise are used as the training and test sets of the revised probabilistic forecasts, respectively.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/feart.2021.760766">doi:10.3389/feart.2021.760766</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l3zwiv4hezewfap2zyjewwh5ra">fatcat:l3zwiv4hezewfap2zyjewwh5ra</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220113100618/https://fjfsdata01prod.blob.core.windows.net/articles/files/760766/pubmed-zip/.versions/1/.package-entries/feart-09-760766/feart-09-760766.pdf?sv=2018-03-28&amp;sr=b&amp;sig=2z%2B9q2hVeMbTEVXNeCG9BVjFkXV9HeGfMy7dfQZbFEo%3D&amp;se=2022-01-13T10%3A06%3A47Z&amp;sp=r&amp;rscd=attachment%3B%20filename%2A%3DUTF-8%27%27feart-09-760766.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/67/1c/671cd565cc515b9c26c5535e0da789fc30f286b8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3389/feart.2021.760766"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> frontiersin.org </button> </a>

Assessing the performance of deep learning models for multivariate probabilistic energy forecasting

Aleksei Mashlakov, Toni Kuronen, Lasse Lensu, Arto Kaarna, Samuli Honkapuro
<span title="">2021</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/qukv3edgarbe7mj7wawmy4skw4" style="color: black;">Applied Energy</a> </i> &nbsp;
of novel global deep learning models for forecasting wind and solar generation, electricity load, and wholesale electricity price for intraday and day-ahead time horizons.  ...  ) [12], multivariate generalized autoregressive conditional heteroskedasticity (MGARCH) models [13], linear ridge (LRidge) regression [14] and Gaussian processes (GP) [15] have been used for such problems  ...  the use of novel global deep learning models.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.apenergy.2020.116405">doi:10.1016/j.apenergy.2020.116405</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rtotx52vgzcqljij2lysllazcq">fatcat:rtotx52vgzcqljij2lysllazcq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210715234018/https://lutpub.lut.fi/bitstream/handle/10024/162154/mashlakov_et_al_assessing_the_performance_publishers_version.pdf;jsessionid=6EBB668D9AF2A8A8894E44A508A028AA?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e4/8d/e48d9d809e8e638911e933b0d223c37b00d70347.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.apenergy.2020.116405"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> elsevier.com </button> </a>

Accurate Uncertainties for Deep Learning Using Calibrated Regression [article]

Volodymyr Kuleshov, Nathan Fenner, Stefano Ermon
<span title="2018-07-01">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Bayesian methods provide a general framework to quantify uncertainty.  ...  However, because of model misspecification and the use of approximate inference, Bayesian uncertainty estimates are often inaccurate -- for example, a 90% credible interval may not contain the true outcome  ...  Probabilistic Forecasting.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.00263v1">arXiv:1807.00263v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ult3omqijbb5vfwkyrk7x4wiei">fatcat:ult3omqijbb5vfwkyrk7x4wiei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191014035342/https://arxiv.org/pdf/1807.00263v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2f/e7/2fe72e40c761606791d41d33dbbf7312b68b6e1e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1807.00263v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Graph Deep Factors for Forecasting [article]

Hongjie Chen, Ryan A. Rossi, Kanak Mahadik, Sungchul Kim, Hoda Eldardiry
<span title="2020-10-14">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Deep probabilistic forecasting techniques have recently been proposed for modeling large collections of time-series.  ...  In this work, we propose a deep hybrid probabilistic graph-based forecasting framework called Graph Deep Factors (GraphDF) that goes beyond these two extremes by allowing nodes and their time-series to  ...  Our model generates probabilistic CPU usage forecasts on compute machines, and we use them to schedule batch workloads on machines with low predicted CPU usage.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.07373v1">arXiv:2010.07373v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mkgsi3botfba5eoyclfojqfneu">fatcat:mkgsi3botfba5eoyclfojqfneu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201017000838/https://arxiv.org/pdf/2010.07373v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.07373v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Probabilistic Time Series Forecasting with Implicit Quantile Networks [article]

Adèle Gouttes, Kashif Rasul, Mateusz Koren, Johannes Stephan, Tofigh Naghibi
<span title="2021-07-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Here, we propose a general method for probabilistic time series forecasting.  ...  When compared to other probabilistic neural forecasting models on real- and simulated data, our approach is favorable in terms of point-wise prediction accuracy as well as on estimating the underlying  ...  Conclusion In this work, we proposed a general method of probabilistic time series forecasting by using IQNs to learn the quantile function of the next time point.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.03743v1">arXiv:2107.03743v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wa2ls7hf3zdg3bpmwgb6bxbrii">fatcat:wa2ls7hf3zdg3bpmwgb6bxbrii</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210712162423/https://arxiv.org/pdf/2107.03743v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d5/1e/d51e574afe057309dc7aa785d77224aed2ab2f38.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.03743v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 17,692 results