{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/physical-gradients-for-deep-learning","title":"Scale-invariant Learning by Physics Inversion","arxiv_id":"2109.15048","date":"2021-09-30","proceeding":null,"authors":["Philipp Holl","Vladlen Koltun","Nils Thuerey"],"abstract":"Solving inverse problems, such as parameter estimation and optimal control, is a vital part of science. Many experiments repeatedly collect data and rely on machine learning algorithms to quickly infer solutions to the associated inverse problems. We find that state-of-the-art training techniques are not well-suited to many problems that involve physical processes. The highly nonlinear behavior, common in physical processes, results in strongly varying gradients that lead first-order optimizers like SGD or Adam to compute suboptimal optimization directions. We propose a novel hybrid training approach that combines higher-order optimization methods with machine learning techniques. We take updates from a scale-invariant inverse problem solver and embed them into the gradient-descent-based learning pipeline, replacing the regular gradient of the physical process. We demonstrate the capabilities of our method on a variety of canonical physical systems, showing that it yields significant improvements on a wide range of optimization and learning problems.","url_abs":"https://arxiv.org/abs/2109.15048v3","url_pdf":"https://arxiv.org/pdf/2109.15048v3.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":"physical-gradients-for-deep-learning","repo_url":"https://github.com/tum-pbs/sip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"physical-gradients-for-deep-learning","repo_url":"https://github.com/tum-pbs/PhiFlow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"parameter-estimation","task_name":"parameter estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2109.15048","atlas_url":"https://app.syntology.ai/?focus=2109.15048","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.15048"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2109.15048"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2109.15048"},"call":"get_harvested_code_for_paper(arxiv_id=\"2109.15048\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2109.15048"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2109.15048\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2109.15048"},"call":"get_concepts_for_paper(arxiv_id=\"2109.15048\")"}],"by_repo":[{"repo":"tum-pbs/sip","kind":"official","samples":1,"ran":0,"instrument":0,"unverified":1},{"repo":"tum-pbs/PhiFlow","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2203.10131"],"harvested_for_calls":[{"arxiv_id":"2203.10131","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2203.10131"},"call":"get_harvested_code_for_paper(arxiv_id=\"2203.10131\")"}]},{"repo":"ltatzel/PyTorchHessianFree","kind":"found_in_text","samples":7,"ran":7,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2109.15048.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2109.15048.svg"},"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/tum-pbs/PhiFlow","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/tum-pbs/SIP","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/ltatzel/PyTorchHessianFree","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tum-pbs/sip","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":1},"n_samples":8,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":1,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":1,"ran":0,"n_ran_checked":0,"n_instrument":0,"repositories":1},"found_in_text":{"samples":7,"ran":7,"n_ran_checked":7,"n_instrument":0,"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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":7,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-24","last":"2026-09-24","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"5d32fc50353666d3","code_sha256_prefix":"5d32fc50353666d3","entry":"cg","repo":"ltatzel/PyTorchHessianFree","repo_kind":"found_in_text","path":"hessianfree/cg.py","file_url":"https://github.com/ltatzel/PyTorchHessianFree/blob/HEAD/hessianfree/cg.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"A:callable/0/?, b:Tensor/1/float, x0:Tensor/1/float, M:callable/0/?, max_iter:int/0/int, tol:float/0/float, atol:float/0/float, martens_conv_crit:bool/0/bool, store_x_at_iters:list/1/int, verbose:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":"/code/cg","census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5d32fc50353666d3"}},{"code_sha256":"5c693bdebbbf88c8","code_sha256_prefix":"5c693bdebbbf88c8","entry":"cg_backtracking","repo":"ltatzel/PyTorchHessianFree","repo_kind":"found_in_text","path":"hessianfree/cg_backtracking.py","file_url":"https://github.com/ltatzel/PyTorchHessianFree/blob/HEAD/hessianfree/cg_backtracking.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:callable/0/?, steps_list:list/1/Tensor, verbose:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"5c693bdebbbf88c8"}},{"code_sha256":"7407e7097201614c","code_sha256_prefix":"7407e7097201614c","entry":"cg_efficient_backtracking","repo":"ltatzel/PyTorchHessianFree","repo_kind":"found_in_text","path":"hessianfree/cg_backtracking.py","file_url":"https://github.com/ltatzel/PyTorchHessianFree/blob/HEAD/hessianfree/cg_backtracking.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:callable/0/?, steps_list:list/1/NoneType, verbose:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7407e7097201614c"}},{"code_sha256":"24b644f7a82e7733","code_sha256_prefix":"24b644f7a82e7733","entry":"diag_EF_autograd","repo":"ltatzel/PyTorchHessianFree","repo_kind":"found_in_text","path":"hessianfree/preconditioners.py","file_url":"https://github.com/ltatzel/PyTorchHessianFree/blob/HEAD/hessianfree/preconditioners.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, loss_function:callable/0/?, inputs:Tensor/2/float, targets:Tensor/2/float, reduction:str/0/str","fixture_out_type":"Tensor","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"24b644f7a82e7733"}},{"code_sha256":"3a0ede3d2c75311a","code_sha256_prefix":"3a0ede3d2c75311a","entry":"diag_to_preconditioner","repo":"ltatzel/PyTorchHessianFree","repo_kind":"found_in_text","path":"hessianfree/preconditioners.py","file_url":"https://github.com/ltatzel/PyTorchHessianFree/blob/HEAD/hessianfree/preconditioners.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"diag_vec:Tensor/1/float, damping:float/0/float, exponent:float/0/float","fixture_out_type":"function","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"3a0ede3d2c75311a"}},{"code_sha256":"22f0d7fc2e2bc7dc","code_sha256_prefix":"22f0d7fc2e2bc7dc","entry":"simple_linesearch","repo":"ltatzel/PyTorchHessianFree","repo_kind":"found_in_text","path":"hessianfree/linesearch.py","file_url":"https://github.com/ltatzel/PyTorchHessianFree/blob/HEAD/hessianfree/linesearch.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:callable/0/?, f_grad_0:Tensor/1/float, step:Tensor/1/float, init_alpha:float/0/float, beta:float/0/float, c:float/0/float, max_iter:int/0/int, verbose:bool/0/bool","fixture_out_type":"tuple","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"22f0d7fc2e2bc7dc"}},{"code_sha256":"95baf3dc76ee0697","code_sha256_prefix":"95baf3dc76ee0697","entry":"vector_to_parameter_list","repo":"ltatzel/PyTorchHessianFree","repo_kind":"found_in_text","path":"hessianfree/utils.py","file_url":"https://github.com/ltatzel/PyTorchHessianFree/blob/HEAD/hessianfree/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"vec:Tensor/1/float, parameters:list/1/Tensor","fixture_out_type":"list","level_recorded_at":"2026-09-24T21:23:57.672461+00:00","code_page":null,"census":null,"licence":"BSD-3-Clause","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"95baf3dc76ee0697"}},{"code_sha256":"09664ea4315cbbb6","code_sha256_prefix":"09664ea4315cbbb6","entry":"exp_loss","repo":"tum-pbs/sip","repo_kind":"official","path":"exp/train_exp.py","file_url":"https://github.com/tum-pbs/sip/blob/HEAD/exp/train_exp.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"09664ea4315cbbb6"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d6cd711b0a180ed3f9e9b07e78399a866a60c6dde75e2ddde3300e9c85594b83","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}