{"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/truncated-matrix-power-iteration-for","title":"Truncated Matrix Power Iteration for Differentiable DAG Learning","arxiv_id":"2208.14571","date":"2022-08-30","proceeding":null,"authors":["Zhen Zhang","Ignavier Ng","Dong Gong","Yuhang Liu","Ehsan M Abbasnejad","Mingming Gong","Kun Zhang","Javen Qinfeng Shi"],"abstract":"Recovering underlying Directed Acyclic Graph (DAG) structures from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization problem. Recently, DAG learning has been cast as a continuous optimization problem by characterizing the DAG constraint as a smooth equality one, generally based on polynomials over adjacency matrices. Existing methods place very small coefficients on high-order polynomial terms for stabilization, since they argue that large coefficients on the higher-order terms are harmful due to numeric exploding. On the contrary, we discover that large coefficients on higher-order terms are beneficial for DAG learning, when the spectral radiuses of the adjacency matrices are small, and that larger coefficients for higher-order terms can approximate the DAG constraints much better than the small counterparts. Based on this, we propose a novel DAG learning method with efficient truncated matrix power iteration to approximate geometric series based DAG constraints. Empirically, our DAG learning method outperforms the previous state-of-the-arts in various settings, often by a factor of $3$ or more in terms of structural Hamming distance.","url_abs":"https://arxiv.org/abs/2208.14571v2","url_pdf":"https://arxiv.org/pdf/2208.14571v2.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":"truncated-matrix-power-iteration-for","repo_url":"https://github.com/zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.14571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.14571"}},"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/zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning","reach":null}],"summary":{"ran_fixture":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"9a9ab3f32d45c48d","entry":"h_fast_tmpi","repo":"zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning","repo_kind":"official","path":"dag/tmpi.py","file_url":"https://github.com/zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning/blob/HEAD/dag/tmpi.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a9ab3f32d45c48d"}},{"code_sha256_prefix":"c9fc8e4585882848","entry":"next_power_of_2","repo":"zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning","repo_kind":"official","path":"dag/tmpi.py","file_url":"https://github.com/zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning/blob/HEAD/dag/tmpi.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c9fc8e4585882848"}},{"code_sha256_prefix":"2c7c3b8071048f21","entry":"h_fast_tmpi","repo":"zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning","repo_kind":"official","path":"dag/tmpi.py","file_url":"https://github.com/zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning/blob/HEAD/dag/tmpi.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2c7c3b8071048f21"}},{"code_sha256_prefix":"931e413aa2667826","entry":"next_power_of_2","repo":"zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning","repo_kind":"official","path":"dag/tmpi.py","file_url":"https://github.com/zzhang1987/truncated-matrix-power-iteration-for-differentiable-dag-learning/blob/HEAD/dag/tmpi.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"931e413aa2667826"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}