{"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/residual-pathway-priors-for-soft-equivariance-1","title":"Residual Pathway Priors for Soft Equivariance Constraints","arxiv_id":"2112.01388","date":"2021-12-02","proceeding":"NeurIPS 2021 12","authors":["Marc Finzi","Gregory Benton","Andrew Gordon Wilson"],"abstract":"There is often a trade-off between building deep learning systems that are expressive enough to capture the nuances of the reality, and having the right inductive biases for efficient learning. We introduce Residual Pathway Priors (RPPs) as a method for converting hard architectural constraints into soft priors, guiding models towards structured solutions, while retaining the ability to capture additional complexity. Using RPPs, we construct neural network priors with inductive biases for equivariances, but without limiting flexibility. We show that RPPs are resilient to approximate or misspecified symmetries, and are as effective as fully constrained models even when symmetries are exact. We showcase the broad applicability of RPPs with dynamical systems, tabular data, and reinforcement learning. In Mujoco locomotion tasks, where contact forces and directional rewards violate strict equivariance assumptions, the RPP outperforms baseline model-free RL agents, and also improves the learned transition models for model-based RL.","url_abs":"https://arxiv.org/abs/2112.01388v1","url_pdf":"https://arxiv.org/pdf/2112.01388v1.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":"residual-pathway-priors-for-soft-equivariance-1","repo_url":"https://github.com/mfinzi/residual-pathway-priors","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"mujoco","task_name":"MuJoCo"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2112.01388","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2112.01388"}},"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":"deterministic:regex_extraction","url":"https://github.com/mfinzi/residual-pathway-priors","reach":null}],"summary":{"ran":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"dcf51d274d000ca6","entry":"LinearConvBlock","repo":"mfinzi/residual-pathway-priors","repo_kind":"official","path":"rpp/rpp_conv.py","file_url":"https://github.com/mfinzi/residual-pathway-priors/blob/HEAD/rpp/rpp_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dcf51d274d000ca6"}},{"code_sha256_prefix":"bf72def9a84dba1f","entry":"RPPConv","repo":"mfinzi/residual-pathway-priors","repo_kind":"official","path":"rpp/rpp_conv.py","file_url":"https://github.com/mfinzi/residual-pathway-priors/blob/HEAD/rpp/rpp_conv.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"bf72def9a84dba1f"}},{"code_sha256_prefix":"a5fc7bb9d6fad00b","entry":"compute_mse","repo":"mfinzi/residual-pathway-priors","repo_kind":"official","path":"experiments/UCI/train_uci.py","file_url":"https://github.com/mfinzi/residual-pathway-priors/blob/HEAD/experiments/UCI/train_uci.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a5fc7bb9d6fad00b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}