{"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/hypersolvers-toward-fast-continuous-depth","title":"Hypersolvers: Toward Fast Continuous-Depth Models","arxiv_id":"2007.09601","date":"2020-07-19","proceeding":"NeurIPS 2020 12","authors":["Michael Poli","Stefano Massaroli","Atsushi Yamashita","Hajime Asama","Jinkyoo Park"],"abstract":"The infinite-depth paradigm pioneered by Neural ODEs has launched a renaissance in the search for novel dynamical system-inspired deep learning primitives; however, their utilization in problems of non-trivial size has often proved impossible due to poor computational scalability. This work paves the way for scalable Neural ODEs with time-to-prediction comparable to traditional discrete networks. We introduce hypersolvers, neural networks designed to solve ODEs with low overhead and theoretical guarantees on accuracy. The synergistic combination of hypersolvers and Neural ODEs allows for cheap inference and unlocks a new frontier for practical application of continuous-depth models. Experimental evaluations on standard benchmarks, such as sampling for continuous normalizing flows, reveal consistent pareto efficiency over classical numerical methods.","url_abs":"https://arxiv.org/abs/2007.09601v2","url_pdf":"https://arxiv.org/pdf/2007.09601v2.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":"hypersolvers-toward-fast-continuous-depth","repo_url":"https://github.com/DiffEqML/diffeqml-research/tree/master/hypersolver","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.09601","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.09601"}},"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/DiffEqML/diffeqml-research/tree/master/hypersolver","reach":null}],"summary":{"ran_honours":1,"ran":1,"unverified":13},"by_repo_kind":{"official":{"samples":15,"ran":2,"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":"6993cad8937592ca","entry":"get_mgrid","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/activations.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/activations.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":2,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6993cad8937592ca"}},{"code_sha256_prefix":"754f3e0cdb026116","entry":"divergence","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/activations.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/activations.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"754f3e0cdb026116"}},{"code_sha256_prefix":"53b4a26700518185","entry":"autograd_trace","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolver/src/models.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolver/src/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"53b4a26700518185"}},{"code_sha256_prefix":"de23a0d8342f36d6","entry":"circle_loss","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/cost.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/cost.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"de23a0d8342f36d6"}},{"code_sha256_prefix":"e8e6e7289ccb550b","entry":"circus_loss","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/cost.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/cost.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e8e6e7289ccb550b"}},{"code_sha256_prefix":"503b76247e05ecc8","entry":"continuous_lqr","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/controllers.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/controllers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"503b76247e05ecc8"}},{"code_sha256_prefix":"ed8adea15e61e3bc","entry":"density_scatter","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolver/src/utils.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolver/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed8adea15e61e3bc"}},{"code_sha256_prefix":"efd45a3ed6ab2f76","entry":"discrete_lqr","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/controllers.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/controllers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"efd45a3ed6ab2f76"}},{"code_sha256_prefix":"fdae332b7c150576","entry":"get_cifar_dloaders","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"dissecting-neural-odes/image_classification/utils.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/dissecting-neural-odes/image_classification/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fdae332b7c150576"}},{"code_sha256_prefix":"f4b106b4f1fbbe33","entry":"grid_apply","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolver/src/utils.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolver/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f4b106b4f1fbbe33"}},{"code_sha256_prefix":"c43fd3e765748d8b","entry":"jagged_fixed_odeint","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"neural-hybrid-automata/src/odeint.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/neural-hybrid-automata/src/odeint.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c43fd3e765748d8b"}},{"code_sha256_prefix":"5719cf26510d50ea","entry":"laplace","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/activations.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/activations.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5719cf26510d50ea"}},{"code_sha256_prefix":"036472db72b08a56","entry":"mape","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/utils.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"036472db72b08a56"}},{"code_sha256_prefix":"c6a6548ef8385b9a","entry":"one_hot","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"neural-hybrid-automata/src/nn.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/neural-hybrid-automata/src/nn.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6a6548ef8385b9a"}},{"code_sha256_prefix":"dc53a4c9f0d50895","entry":"smape","repo":"DiffEqML/diffeqml-research","repo_kind":"official","path":"hypersolvers-control/src/utils.py","file_url":"https://github.com/DiffEqML/diffeqml-research/blob/HEAD/hypersolvers-control/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc53a4c9f0d50895"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}