{"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/fundamental-limits-of-weak-learnability-in","title":"Fundamental computational limits of weak learnability in high-dimensional multi-index models","arxiv_id":"2405.15480","date":"2024-05-24","proceeding":null,"authors":["Emanuele Troiani","Yatin Dandi","Leonardo Defilippis","Lenka Zdeborová","Bruno Loureiro","Florent Krzakala"],"abstract":"Multi-index models - functions which only depend on the covariates through a non-linear transformation of their projection on a subspace - are a useful benchmark for investigating feature learning with neural nets. This paper examines the theoretical boundaries of efficient learnability in this hypothesis class, focusing on the minimum sample complexity required for weakly recovering their low-dimensional structure with first-order iterative algorithms, in the high-dimensional regime where the number of samples $n\\!=\\!\\alpha d$ is proportional to the covariate dimension $d$. Our findings unfold in three parts: (i) we identify under which conditions a trivial subspace can be learned with a single step of a first-order algorithm for any $\\alpha\\!>\\!0$; (ii) if the trivial subspace is empty, we provide necessary and sufficient conditions for the existence of an easy subspace where directions that can be learned only above a certain sample complexity $\\alpha\\!>\\!\\alpha_c$, where $\\alpha_{c}$ marks a computational phase transition. In a limited but interesting set of really hard directions -- akin to the parity problem -- $\\alpha_c$ is found to diverge. Finally, (iii) we show that interactions between different directions can result in an intricate hierarchical learning phenomenon, where directions can be learned sequentially when coupled to easier ones. We discuss in detail the grand staircase picture associated to these functions (and contrast it with the original staircase one). Our theory builds on the optimality of approximate message-passing among first-order iterative methods, delineating the fundamental learnability limit across a broad spectrum of algorithms, including neural networks trained with gradient descent, which we discuss in this context.","url_abs":"https://arxiv.org/abs/2405.15480v4","url_pdf":"https://arxiv.org/pdf/2405.15480v4.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":"fundamental-limits-of-weak-learnability-in","repo_url":"https://github.com/SPOC-group/FundamentalLimitsMultiIndex","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2405.15480","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.15480"}},"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/SPOC-group/FundamentalLimitsMultiIndex","reach":null}],"summary":{"ran_honours":1,"ran_draft_wrong":2},"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":3,"samples":[{"code_sha256_prefix":"69bd4b24c53c9770","entry":"get_estimate","repo":"SPOC-group/FundamentalLimitsMultiIndex","repo_kind":"official","path":"AMP_committee.py","file_url":"https://github.com/SPOC-group/FundamentalLimitsMultiIndex/blob/HEAD/AMP_committee.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"69bd4b24c53c9770"}},{"code_sha256_prefix":"804376176bc9dec5","entry":"sample_instance","repo":"SPOC-group/FundamentalLimitsMultiIndex","repo_kind":"official","path":"AMP_committee.py","file_url":"https://github.com/SPOC-group/FundamentalLimitsMultiIndex/blob/HEAD/AMP_committee.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"804376176bc9dec5"}},{"code_sha256_prefix":"392069fdf71693b5","entry":"sample_labels","repo":"SPOC-group/FundamentalLimitsMultiIndex","repo_kind":"official","path":"AMP_committee.py","file_url":"https://github.com/SPOC-group/FundamentalLimitsMultiIndex/blob/HEAD/AMP_committee.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"392069fdf71693b5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}