{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:CLGHGYKS7LO2J3IX3FTVZJSWM3","short_pith_number":"pith:CLGHGYKS","schema_version":"1.0","canonical_sha256":"12cc736152fadda4ed17d9675ca65666f6bafb4a91c34c61e9cbd33044ad5b1b","source":{"kind":"arxiv","id":"2012.02387","version":2},"attestation_state":"computed","paper":{"title":"A Variant of Gradient Descent Algorithm Based on Gradient Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Saugata Purkayastha, Sukannya Purkayastha","submitted_at":"2020-12-04T03:43:12Z","abstract_excerpt":"In this work, we study an optimizer, Grad-Avg to optimize error functions. We establish the convergence of the sequence of iterates of Grad-Avg mathematically to a minimizer (under boundedness assumption). We apply Grad-Avg along with some of the popular optimizers on regression as well as classification tasks. In regression tasks, it is observed that the behaviour of Grad-Avg is almost identical with Stochastic Gradient Descent (SGD). We present a mathematical justification of this fact. In case of classification tasks, it is observed that the performance of Grad-Avg can be enhanced by suitab"},"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":"2012.02387","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-12-04T03:43:12Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"5e6c5c8bbff62b0e939b1eca8d05ae7d3ad2a0aa10ceb665b932ffe08e289ec6","abstract_canon_sha256":"5483076db200d85fd9d3d5f7181b6bd5eaa9da122a17f9e77bf5f38c4461b5bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:32.904966Z","signature_b64":"+FaNtuaZcIjV96I2OToJIaMCEZXvjVn+s/yDEUGTSULt2C2TfieZ3Jvv4uIOOObwaov2PvuS0o+mO/0bssKhCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12cc736152fadda4ed17d9675ca65666f6bafb4a91c34c61e9cbd33044ad5b1b","last_reissued_at":"2026-07-05T01:58:32.904558Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:32.904558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Variant of Gradient Descent Algorithm Based on Gradient Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Saugata Purkayastha, Sukannya Purkayastha","submitted_at":"2020-12-04T03:43:12Z","abstract_excerpt":"In this work, we study an optimizer, Grad-Avg to optimize error functions. We establish the convergence of the sequence of iterates of Grad-Avg mathematically to a minimizer (under boundedness assumption). We apply Grad-Avg along with some of the popular optimizers on regression as well as classification tasks. In regression tasks, it is observed that the behaviour of Grad-Avg is almost identical with Stochastic Gradient Descent (SGD). We present a mathematical justification of this fact. In case of classification tasks, it is observed that the performance of Grad-Avg can be enhanced by suitab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02387","kind":"arxiv","version":2},"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/2012.02387/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":"2012.02387","created_at":"2026-07-05T01:58:32.904615+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02387v2","created_at":"2026-07-05T01:58:32.904615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02387","created_at":"2026-07-05T01:58:32.904615+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLGHGYKS7LO2","created_at":"2026-07-05T01:58:32.904615+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLGHGYKS7LO2J3IX","created_at":"2026-07-05T01:58:32.904615+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLGHGYKS","created_at":"2026-07-05T01:58:32.904615+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3","json":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3.json","graph_json":"https://pith.science/api/pith-number/CLGHGYKS7LO2J3IX3FTVZJSWM3/graph.json","events_json":"https://pith.science/api/pith-number/CLGHGYKS7LO2J3IX3FTVZJSWM3/events.json","paper":"https://pith.science/paper/CLGHGYKS"},"agent_actions":{"view_html":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3","download_json":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3.json","view_paper":"https://pith.science/paper/CLGHGYKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02387&json=true","fetch_graph":"https://pith.science/api/pith-number/CLGHGYKS7LO2J3IX3FTVZJSWM3/graph.json","fetch_events":"https://pith.science/api/pith-number/CLGHGYKS7LO2J3IX3FTVZJSWM3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3/action/storage_attestation","attest_author":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3/action/author_attestation","sign_citation":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3/action/citation_signature","submit_replication":"https://pith.science/pith/CLGHGYKS7LO2J3IX3FTVZJSWM3/action/replication_record"}},"created_at":"2026-07-05T01:58:32.904615+00:00","updated_at":"2026-07-05T01:58:32.904615+00:00"}