{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BMV5JSADXXNBQMTQMZFCKTIPMJ","short_pith_number":"pith:BMV5JSAD","schema_version":"1.0","canonical_sha256":"0b2bd4c803bdda183270664a254d0f62680127d8e1c2d9bc192f5e191cdbc33e","source":{"kind":"arxiv","id":"1902.09843","version":1},"attestation_state":"computed","paper":{"title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Liangchen Luo, Xu Sun, Yan Liu, Yuanhao Xiong","submitted_at":"2019-02-26T10:22:48Z","abstract_excerpt":"Adaptive optimization methods such as AdaGrad, RMSprop and Adam have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared with SGD or even fail to converge due to unstable and extreme learning rates. Recent work has put forward some algorithms such as AMSGrad to tackle this issue but they failed to achieve considerable improvement over existing methods. In our paper, we demonstrate that extreme learning rates can lead to poor performance. We provide new variants of Adam and AMSG"},"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":"1902.09843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-26T10:22:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"984eb6af418bd915c6e015202f11cc537596b896cc9a78e43291d01900164081","abstract_canon_sha256":"cbf784af20a4a9269a5dc1cae31bc7e537378d3603522cc0213c0acb7f372a7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:11.066046Z","signature_b64":"HjL4lPcyxJrHr9kvKIhGold4S5vpzLr4IO26BILU7Cr3V5Mt16LooHA9H7APKkWhseGnnaxtqXBa9NiTex/jBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b2bd4c803bdda183270664a254d0f62680127d8e1c2d9bc192f5e191cdbc33e","last_reissued_at":"2026-05-17T23:48:11.065409Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:11.065409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Gradient Methods with Dynamic Bound of Learning Rate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Liangchen Luo, Xu Sun, Yan Liu, Yuanhao Xiong","submitted_at":"2019-02-26T10:22:48Z","abstract_excerpt":"Adaptive optimization methods such as AdaGrad, RMSprop and Adam have been proposed to achieve a rapid training process with an element-wise scaling term on learning rates. Though prevailing, they are observed to generalize poorly compared with SGD or even fail to converge due to unstable and extreme learning rates. Recent work has put forward some algorithms such as AMSGrad to tackle this issue but they failed to achieve considerable improvement over existing methods. In our paper, we demonstrate that extreme learning rates can lead to poor performance. We provide new variants of Adam and AMSG"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09843","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1902.09843","created_at":"2026-05-17T23:48:11.065502+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.09843v1","created_at":"2026-05-17T23:48:11.065502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09843","created_at":"2026-05-17T23:48:11.065502+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMV5JSADXXNB","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMV5JSADXXNBQMTQ","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMV5JSAD","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2605.19811","citing_title":"LionMuon: Alternating Spectral and Sign Descent for Efficient Training","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.29273","citing_title":"A Theoretical and Experimental Study of a Novel Adaptive Learning Algorithm","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09008","citing_title":"signADAM: Learning Confidences for Deep Neural Networks","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2003.00295","citing_title":"Adaptive Federated Optimization","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19811","citing_title":"LionMuon: Alternating Spectral and Sign Descent for Efficient Training","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2509.15816","citing_title":"On the Convergence of Muon and Beyond","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03203","citing_title":"PR3DICTR: A modular AI framework for medical 3D image-based detection and outcome prediction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02317","citing_title":"Anon: Extrapolating Adaptivity Beyond SGD and Adam","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00650","citing_title":"AdaMeZO: Adam-style Zeroth-Order Optimizer for LLM Fine-tuning Without Maintaining the Moments","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08939","citing_title":"Delve into the Applicability of Advanced Optimizers for Multi-Task Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07841","citing_title":"\\mathsf{VISTA}: Decentralized Machine Learning in Adversary Dominated Environments","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22838","citing_title":"Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ","json":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ.json","graph_json":"https://pith.science/api/pith-number/BMV5JSADXXNBQMTQMZFCKTIPMJ/graph.json","events_json":"https://pith.science/api/pith-number/BMV5JSADXXNBQMTQMZFCKTIPMJ/events.json","paper":"https://pith.science/paper/BMV5JSAD"},"agent_actions":{"view_html":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ","download_json":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ.json","view_paper":"https://pith.science/paper/BMV5JSAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.09843&json=true","fetch_graph":"https://pith.science/api/pith-number/BMV5JSADXXNBQMTQMZFCKTIPMJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BMV5JSADXXNBQMTQMZFCKTIPMJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ/action/storage_attestation","attest_author":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ/action/author_attestation","sign_citation":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ/action/citation_signature","submit_replication":"https://pith.science/pith/BMV5JSADXXNBQMTQMZFCKTIPMJ/action/replication_record"}},"created_at":"2026-05-17T23:48:11.065502+00:00","updated_at":"2026-05-17T23:48:11.065502+00:00"}