{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UTOWH4HGJ77UO4XGNTXPIBUXC6","short_pith_number":"pith:UTOWH4HG","schema_version":"1.0","canonical_sha256":"a4dd63f0e64fff4772e66ceef40697179821241995b181e95b43d7d0a4667c72","source":{"kind":"arxiv","id":"2109.12504","version":2},"attestation_state":"computed","paper":{"title":"AdaInject: Injection Based Adaptive Gradient Descent Optimizers for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Bidyut Baran Chaudhuri, Satish Kumar Singh, Shiv Ram Dubey, S.H. Shabbeer Basha","submitted_at":"2021-09-26T06:24:14Z","abstract_excerpt":"The convolutional neural networks (CNNs) are generally trained using stochastic gradient descent (SGD) based optimization techniques. The existing SGD optimizers generally suffer with the overshooting of the minimum and oscillation near minimum. In this paper, we propose a new approach, hereafter referred as AdaInject, for the gradient descent optimizers by injecting the second order moment into the first order moment. Specifically, the short-term change in parameter is used as a weight to inject the second order moment in the update rule. The AdaInject optimizer controls the parameter update,"},"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":"2109.12504","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-26T06:24:14Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"e2ef6cf6285467335e154cd32f4abb18dc5b740ac94d074dd57c2eba90abb158","abstract_canon_sha256":"4a8b37e85f9f4a3bf68fa461a1ed8f8e763aab8c136e6b92979ce998d65fa37e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:58:32.980158Z","signature_b64":"4wZ36mKLkhgYnAkUr3AG+qGqY3pCI6/WkYGBwc4CLJ7zCcZdEo7qlbGEfpSTTiR2bdJ8kPkIwBHbSbLm2LYpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4dd63f0e64fff4772e66ceef40697179821241995b181e95b43d7d0a4667c72","last_reissued_at":"2026-07-05T04:58:32.979776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:58:32.979776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaInject: Injection Based Adaptive Gradient Descent Optimizers for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Bidyut Baran Chaudhuri, Satish Kumar Singh, Shiv Ram Dubey, S.H. Shabbeer Basha","submitted_at":"2021-09-26T06:24:14Z","abstract_excerpt":"The convolutional neural networks (CNNs) are generally trained using stochastic gradient descent (SGD) based optimization techniques. The existing SGD optimizers generally suffer with the overshooting of the minimum and oscillation near minimum. In this paper, we propose a new approach, hereafter referred as AdaInject, for the gradient descent optimizers by injecting the second order moment into the first order moment. Specifically, the short-term change in parameter is used as a weight to inject the second order moment in the update rule. The AdaInject optimizer controls the parameter update,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.12504","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/2109.12504/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":"2109.12504","created_at":"2026-07-05T04:58:32.979840+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.12504v2","created_at":"2026-07-05T04:58:32.979840+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.12504","created_at":"2026-07-05T04:58:32.979840+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTOWH4HGJ77U","created_at":"2026-07-05T04:58:32.979840+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTOWH4HGJ77UO4XG","created_at":"2026-07-05T04:58:32.979840+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTOWH4HG","created_at":"2026-07-05T04:58:32.979840+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/UTOWH4HGJ77UO4XGNTXPIBUXC6","json":"https://pith.science/pith/UTOWH4HGJ77UO4XGNTXPIBUXC6.json","graph_json":"https://pith.science/api/pith-number/UTOWH4HGJ77UO4XGNTXPIBUXC6/graph.json","events_json":"https://pith.science/api/pith-number/UTOWH4HGJ77UO4XGNTXPIBUXC6/events.json","paper":"https://pith.science/paper/UTOWH4HG"},"agent_actions":{"view_html":"https://pith.science/pith/UTOWH4HGJ77UO4XGNTXPIBUXC6","download_json":"https://pith.science/pith/UTOWH4HGJ77UO4XGNTXPIBUXC6.json","view_paper":"https://pith.science/paper/UTOWH4HG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.12504&json=true","fetch_graph":"https://pith.science/api/pith-number/UTOWH4HGJ77UO4XGNTXPIBUXC6/graph.json","fetch_events":"https://pith.science/api/pith-number/UTOWH4HGJ77UO4XGNTXPIBUXC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTOWH4HGJ77UO4XGNTXPIBUXC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTOWH4HGJ77UO4XGNTXPIBUXC6/action/storage_attestation","attest_author":"https://pith.science/pith/UTOWH4HGJ77UO4XGNTXPIBUXC6/action/author_attestation","sign_citation":"https://pith.science/pith/UTOWH4HGJ77UO4XGNTXPIBUXC6/action/citation_signature","submit_replication":"https://pith.science/pith/UTOWH4HGJ77UO4XGNTXPIBUXC6/action/replication_record"}},"created_at":"2026-07-05T04:58:32.979840+00:00","updated_at":"2026-07-05T04:58:32.979840+00:00"}