{"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/fast-convex-optimization-for-two-layer-relu","title":"Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone Decompositions","arxiv_id":"2202.01331","date":"2022-02-02","proceeding":null,"authors":["Aaron Mishkin","Arda Sahiner","Mert Pilanci"],"abstract":"We develop fast algorithms and robust software for convex optimization of two-layer neural networks with ReLU activation functions. Our work leverages a convex reformulation of the standard weight-decay penalized training problem as a set of group-$\\ell_1$-regularized data-local models, where locality is enforced by polyhedral cone constraints. In the special case of zero-regularization, we show that this problem is exactly equivalent to unconstrained optimization of a convex \"gated ReLU\" network. For problems with non-zero regularization, we show that convex gated ReLU models obtain data-dependent approximation bounds for the ReLU training problem. To optimize the convex reformulations, we develop an accelerated proximal gradient method and a practical augmented Lagrangian solver. We show that these approaches are faster than standard training heuristics for the non-convex problem, such as SGD, and outperform commercial interior-point solvers. Experimentally, we verify our theoretical results, explore the group-$\\ell_1$ regularization path, and scale convex optimization for neural networks to image classification on MNIST and CIFAR-10.","url_abs":"https://arxiv.org/abs/2202.01331v3","url_pdf":"https://arxiv.org/pdf/2202.01331v3.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":"fast-convex-optimization-for-two-layer-relu","repo_url":"https://github.com/pilancilab/scnn","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"fast-convex-optimization-for-two-layer-relu","repo_url":"https://github.com/MindCode-4/code-13/tree/main/Two-Layer-ReLU-Network-Analytically","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2202.01331","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.01331"}},"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/pilancilab/scnn","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindCode-4/code-13/tree/main/Two-Layer-ReLU-Network-Analytically","reach":null}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"ran":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,"samples":[{"code_sha256_prefix":"fbb92bd2ce42c951","entry":"as_list","repo":"pilancilab/scnn","repo_kind":"official","path":"src/scnn/private/metrics.py","file_url":"https://github.com/pilancilab/scnn/blob/HEAD/src/scnn/private/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fbb92bd2ce42c951"}},{"code_sha256_prefix":"47f4fb6c7ed4492b","entry":"format_recent_metrics","repo":"pilancilab/scnn","repo_kind":"official","path":"src/scnn/private/metrics.py","file_url":"https://github.com/pilancilab/scnn/blob/HEAD/src/scnn/private/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"47f4fb6c7ed4492b"}},{"code_sha256_prefix":"67f2c4b39f8a84c3","entry":"input_into_normalized_space","repo":"pilancilab/scnn","repo_kind":"official","path":"src/scnn/private/interface/data.py","file_url":"https://github.com/pilancilab/scnn/blob/HEAD/src/scnn/private/interface/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67f2c4b39f8a84c3"}},{"code_sha256_prefix":"9696ab727fb33da9","entry":"merge_metric_lists","repo":"pilancilab/scnn","repo_kind":"official","path":"src/scnn/private/metrics.py","file_url":"https://github.com/pilancilab/scnn/blob/HEAD/src/scnn/private/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9696ab727fb33da9"}},{"code_sha256_prefix":"b09a9155dbd71322","entry":"sample_dense_gates","repo":"pilancilab/scnn","repo_kind":"official","path":"src/scnn/activations.py","file_url":"https://github.com/pilancilab/scnn/blob/HEAD/src/scnn/activations.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b09a9155dbd71322"}},{"code_sha256_prefix":"1e897d214dde5930","entry":"sample_gate_vectors","repo":"pilancilab/scnn","repo_kind":"official","path":"src/scnn/activations.py","file_url":"https://github.com/pilancilab/scnn/blob/HEAD/src/scnn/activations.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1e897d214dde5930"}},{"code_sha256_prefix":"389f85fd284a2aba","entry":"sample_sparse_gates","repo":"pilancilab/scnn","repo_kind":"official","path":"src/scnn/activations.py","file_url":"https://github.com/pilancilab/scnn/blob/HEAD/src/scnn/activations.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"389f85fd284a2aba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}