{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FSBQTME54LUL6HFT53SMR7CCVK","short_pith_number":"pith:FSBQTME5","schema_version":"1.0","canonical_sha256":"2c8309b09de2e8bf1cb3eee4c8fc42aaada8a78652cf32d52f6386790a0e3283","source":{"kind":"arxiv","id":"2307.10053","version":4},"attestation_state":"computed","paper":{"title":"Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Kim-Chuan Toh, Nachuan Xiao, Xiaoyin Hu","submitted_at":"2023-07-19T15:26:18Z","abstract_excerpt":"In this paper, we focus on providing convergence guarantees for stochastic subgradient methods in minimizing nonsmooth nonconvex functions. We first investigate the global stability of a general framework for stochastic subgradient methods, where the corresponding differential inclusion admits a coercive Lyapunov function. We prove that, for any sequence of sufficiently small stepsizes and approximation parameters, coupled with sufficiently controlled noises, the iterates are uniformly bounded and asymptotically stabilize around the stable set of its corresponding differential inclusion. Moreo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.10053","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2023-07-19T15:26:18Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"a64dea41590afe0a8d95afe1ae82f544d6936597e52df85fe91d24dbfb25347e","abstract_canon_sha256":"94d5c1fe0397489a06ef1dc45eba57c1596c499c0be08ec3466f0a3eba639e30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:23.923537Z","signature_b64":"3KRD9qYMUQ44ZcTraQZpEZlOT7C1UivIX7JBzNq+3yQejxAmINq4PQa/H6fbsB8DGcFIrR/TYUxc8sFQEaPADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c8309b09de2e8bf1cb3eee4c8fc42aaada8a78652cf32d52f6386790a0e3283","last_reissued_at":"2026-07-05T09:19:23.923059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:23.923059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Subgradient Methods with Guaranteed Global Stability in Nonsmooth Nonconvex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Kim-Chuan Toh, Nachuan Xiao, Xiaoyin Hu","submitted_at":"2023-07-19T15:26:18Z","abstract_excerpt":"In this paper, we focus on providing convergence guarantees for stochastic subgradient methods in minimizing nonsmooth nonconvex functions. We first investigate the global stability of a general framework for stochastic subgradient methods, where the corresponding differential inclusion admits a coercive Lyapunov function. We prove that, for any sequence of sufficiently small stepsizes and approximation parameters, coupled with sufficiently controlled noises, the iterates are uniformly bounded and asymptotically stabilize around the stable set of its corresponding differential inclusion. Moreo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.10053","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2307.10053/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.10053","created_at":"2026-07-05T09:19:23.923117+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.10053v4","created_at":"2026-07-05T09:19:23.923117+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.10053","created_at":"2026-07-05T09:19:23.923117+00:00"},{"alias_kind":"pith_short_12","alias_value":"FSBQTME54LUL","created_at":"2026-07-05T09:19:23.923117+00:00"},{"alias_kind":"pith_short_16","alias_value":"FSBQTME54LUL6HFT","created_at":"2026-07-05T09:19:23.923117+00:00"},{"alias_kind":"pith_short_8","alias_value":"FSBQTME5","created_at":"2026-07-05T09:19:23.923117+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2607.01755","citing_title":"Decentralized Stochastic Subgradient-type Methods with Communication Compression for Nonsmooth Nonconvex Optimization","ref_index":67,"is_internal_anchor":true},{"citing_arxiv_id":"2409.04777","citing_title":"Optimization Hyper-parameter Laws for Large Language Models","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14345","citing_title":"Convergence of difference inclusions via a diameter criterion","ref_index":114,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06615","citing_title":"When and Why SignSGD Outperforms SGD: A Theoretical Study Based on $\\ell_1$-norm Lower Bounds","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15416","citing_title":"StoSignSGD: Unbiased Structural Stochasticity Fixes SignSGD for Training Large Language Models","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK","json":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK.json","graph_json":"https://pith.science/api/pith-number/FSBQTME54LUL6HFT53SMR7CCVK/graph.json","events_json":"https://pith.science/api/pith-number/FSBQTME54LUL6HFT53SMR7CCVK/events.json","paper":"https://pith.science/paper/FSBQTME5"},"agent_actions":{"view_html":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK","download_json":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK.json","view_paper":"https://pith.science/paper/FSBQTME5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.10053&json=true","fetch_graph":"https://pith.science/api/pith-number/FSBQTME54LUL6HFT53SMR7CCVK/graph.json","fetch_events":"https://pith.science/api/pith-number/FSBQTME54LUL6HFT53SMR7CCVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK/action/storage_attestation","attest_author":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK/action/author_attestation","sign_citation":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK/action/citation_signature","submit_replication":"https://pith.science/pith/FSBQTME54LUL6HFT53SMR7CCVK/action/replication_record"}},"created_at":"2026-07-05T09:19:23.923117+00:00","updated_at":"2026-07-05T09:19:23.923117+00:00"}