{"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/convolutional-gaussian-processes","title":"Convolutional Gaussian Processes","arxiv_id":"1709.01894","date":"2017-09-06","proceeding":"NeurIPS 2017 12","authors":["Mark van der Wilk","Carl Edward Rasmussen","James Hensman"],"abstract":"We present a practical way of introducing convolutional structure into\nGaussian processes, making them more suited to high-dimensional inputs like\nimages. The main contribution of our work is the construction of an\ninter-domain inducing point approximation that is well-tailored to the\nconvolutional kernel. This allows us to gain the generalisation benefit of a\nconvolutional kernel, together with fast but accurate posterior inference. We\ninvestigate several variations of the convolutional kernel, and apply it to\nMNIST and CIFAR-10, which have both been known to be challenging for Gaussian\nprocesses. We also show how the marginal likelihood can be used to find an\noptimal weighting between convolutional and RBF kernels to further improve\nperformance. We hope that this illustration of the usefulness of a marginal\nlikelihood will help automate discovering architectures in larger models.","url_abs":"http://arxiv.org/abs/1709.01894v1","url_pdf":"http://arxiv.org/pdf/1709.01894v1.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":"convolutional-gaussian-processes","repo_url":"https://github.com/markvdw/convgp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"convolutional-gaussian-processes","repo_url":"https://github.com/GPflow/GPflow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"convolutional-gaussian-processes","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":"convolutional-gaussian-processes","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"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.01894","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1709.01894"}},"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/GPflow/GPflow","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/pyro-ppl/pyro","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/markvdw/convgp","reach":null}],"summary":{"ran_fixture":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":"efd2ba28bf88ea04","entry":"reshape_patches_for_plot","repo":"markvdw/convgp","repo_kind":"official","path":"paper-plots.py","file_url":"https://github.com/markvdw/convgp/blob/HEAD/paper-plots.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"efd2ba28bf88ea04"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}