{"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/doubly-stochastic-variational-inference-for","title":"Doubly Stochastic Variational Inference for Deep Gaussian Processes","arxiv_id":"1705.08933","date":"2017-05-24","proceeding":"NeurIPS 2017 12","authors":["Hugh Salimbeni","Marc Deisenroth"],"abstract":"Gaussian processes (GPs) are a good choice for function approximation as they\nare flexible, robust to over-fitting, and provide well-calibrated predictive\nuncertainty. Deep Gaussian processes (DGPs) are multi-layer generalisations of\nGPs, but inference in these models has proved challenging. Existing approaches\nto inference in DGP models assume approximate posteriors that force\nindependence between the layers, and do not work well in practice. We present a\ndoubly stochastic variational inference algorithm, which does not force\nindependence between layers. With our method of inference we demonstrate that a\nDGP model can be used effectively on data ranging in size from hundreds to a\nbillion points. We provide strong empirical evidence that our inference scheme\nfor DGPs works well in practice in both classification and regression.","url_abs":"http://arxiv.org/abs/1705.08933v2","url_pdf":"http://arxiv.org/pdf/1705.08933v2.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":"doubly-stochastic-variational-inference-for","repo_url":"https://github.com/ICL-SML/Doubly-Stochastic-DGP","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"doubly-stochastic-variational-inference-for","repo_url":"https://github.com/SourangshuGhosh/Doubly-Stochastic-DGP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"doubly-stochastic-variational-inference-for","repo_url":"https://github.com/SourangshuGhosh/Doubly-Stochastic-Deep-Gaussian-Process","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"doubly-stochastic-variational-inference-for","repo_url":"https://github.com/felixopolka/deep-gaussian-process","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"doubly-stochastic-variational-inference-for","repo_url":"https://github.com/thomaspinder/Doubly-Stochastic-GPs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"doubly-stochastic-variational-inference-for","repo_url":"https://github.com/ucl-sml/doubly-stochastic-dgp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"doubly-stochastic-variational-inference-for","repo_url":"https://github.com/cornellius-gp/gpytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"doubly-stochastic-variational-inference-for","repo_url":"https://github.com/pyro-ppl/pyro","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1705.08933","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1705.08933"}},"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/ICL-SML/Doubly-Stochastic-DGP","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cornellius-gp/gpytorch","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ucl-sml/doubly-stochastic-dgp","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pyro-ppl/pyro","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thomaspinder/Doubly-Stochastic-GPs","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/felixopolka/deep-gaussian-process","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SourangshuGhosh/Doubly-Stochastic-DGP","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SourangshuGhosh/Doubly-Stochastic-Deep-Gaussian-Process","reach":{"status":"unanswered"}}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"5490a61ec6a2c6c2","entry":"batch_assess","repo":"thomaspinder/Doubly-Stochastic-GPs","repo_kind":"listed","path":"demos/demo_regression_UCI.py","file_url":"https://github.com/thomaspinder/Doubly-Stochastic-GPs/blob/HEAD/demos/demo_regression_UCI.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5490a61ec6a2c6c2"}},{"code_sha256_prefix":"6030066b9787bf99","entry":"evaluation_step","repo":"felixopolka/deep-gaussian-process","repo_kind":"listed","path":"src/demos/mnist.py","file_url":"https://github.com/felixopolka/deep-gaussian-process/blob/HEAD/src/demos/mnist.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6030066b9787bf99"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}