{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/inference-in-deep-gaussian-processes-using","title":"Inference in Deep Gaussian Processes using Stochastic Gradient Hamiltonian Monte Carlo","arxiv_id":"1806.05490","date":"2018-06-14","proceeding":"NeurIPS 2018 12","authors":["Marton Havasi","José Miguel Hernández-Lobato","Juan José Murillo-Fuentes"],"abstract":"Deep Gaussian Processes (DGPs) are hierarchical generalizations of Gaussian\nProcesses that combine well calibrated uncertainty estimates with the high\nflexibility of multilayer models. One of the biggest challenges with these\nmodels is that exact inference is intractable. The current state-of-the-art\ninference method, Variational Inference (VI), employs a Gaussian approximation\nto the posterior distribution. This can be a potentially poor unimodal\napproximation of the generally multimodal posterior. In this work, we provide\nevidence for the non-Gaussian nature of the posterior and we apply the\nStochastic Gradient Hamiltonian Monte Carlo method to generate samples. To\nefficiently optimize the hyperparameters, we introduce the Moving Window MCEM\nalgorithm. This results in significantly better predictions at a lower\ncomputational cost than its VI counterpart. Thus our method establishes a new\nstate-of-the-art for inference in DGPs.","url_abs":"http://arxiv.org/abs/1806.05490v3","url_pdf":"http://arxiv.org/pdf/1806.05490v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"inference-in-deep-gaussian-processes-using","repo_url":"https://github.com/cambridge-mlg/sghmc_dgp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"inference-in-deep-gaussian-processes-using","repo_url":"https://github.com/hughsalimbeni/bayesian_benchmarks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"inference-in-deep-gaussian-processes-using","repo_url":"https://github.com/secondmind-labs/bayesian_benchmarks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.05490","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.05490"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/secondmind-labs/bayesian_benchmarks","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cambridge-mlg/sghmc_dgp","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hughsalimbeni/bayesian_benchmarks","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e357c2bcbcc44f6e","entry":"base_conditional","repo":"cambridge-mlg/sghmc_dgp","repo_kind":"official","path":"conditionals.py","file_url":"https://github.com/cambridge-mlg/sghmc_dgp/blob/HEAD/conditionals.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e357c2bcbcc44f6e"}},{"code_sha256_prefix":"5ed7eae7d81be455","entry":"conditional","repo":"cambridge-mlg/sghmc_dgp","repo_kind":"official","path":"conditionals.py","file_url":"https://github.com/cambridge-mlg/sghmc_dgp/blob/HEAD/conditionals.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ed7eae7d81be455"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}