{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:3SWVY2ZAVLHJNBSWPNGJ32ZI7Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bdc465bd8b8ab8b3bc77d81cccf48e3b225bdafec2502bae8fe0ba833176d43e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T16:06:50Z","title_canon_sha256":"86cee1137c821d540b3f2bd2cb1d8c3e91fe4e77b4a6f36c21a3b80baff0545c"},"schema_version":"1.0","source":{"id":"2305.19982","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19982","created_at":"2026-07-05T06:16:05Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19982v1","created_at":"2026-07-05T06:16:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19982","created_at":"2026-07-05T06:16:05Z"},{"alias_kind":"pith_short_12","alias_value":"3SWVY2ZAVLHJ","created_at":"2026-07-05T06:16:05Z"},{"alias_kind":"pith_short_16","alias_value":"3SWVY2ZAVLHJNBSW","created_at":"2026-07-05T06:16:05Z"},{"alias_kind":"pith_short_8","alias_value":"3SWVY2ZA","created_at":"2026-07-05T06:16:05Z"}],"graph_snapshots":[{"event_id":"sha256:693a632cd1c80cc859202aff5600cb80e4dc5ce4f457e68da4c770790966a4c2","target":"graph","created_at":"2026-07-05T06:16:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.19982/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Running out of GPU memory has become a main bottleneck for large-scale DNN training. How to reduce the memory footprint during training has received intensive research attention. We find that previous gradient accumulation reduces activation memory but fails to be compatible with gradient memory reduction due to a contradiction between preserving gradients and releasing gradients. To address this issue, we propose a novel optimizer accumulation method for Adam, named Adam Accumulation (AdamA), which enables reducing both activation and gradient memory. Specifically, AdamA directly integrates g","authors_text":"Fan Yang, Guohao Dai, Ningyi Xu, Shijie Cao, Ting Cao, Yibo Han, Yijia Zhang, Youshan Miao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T16:06:50Z","title":"Adam Accumulation to Reduce Memory Footprints of both Activations and Gradients for Large-scale DNN Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19982","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c582256ecb99f4d7a57f59ff4c66e567c9cc020e7fa38ba4d3bc96214b687e84","target":"record","created_at":"2026-07-05T06:16:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bdc465bd8b8ab8b3bc77d81cccf48e3b225bdafec2502bae8fe0ba833176d43e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T16:06:50Z","title_canon_sha256":"86cee1137c821d540b3f2bd2cb1d8c3e91fe4e77b4a6f36c21a3b80baff0545c"},"schema_version":"1.0","source":{"id":"2305.19982","kind":"arxiv","version":1}},"canonical_sha256":"dcad5c6b20aace9686567b4c9deb28fe4a9b3345931bc9642c897b4478b52db6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcad5c6b20aace9686567b4c9deb28fe4a9b3345931bc9642c897b4478b52db6","first_computed_at":"2026-07-05T06:16:05.601751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:05.601751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0OULKPcdUNoUuZnckV+G00slPYKVmQTkDColJbmcLQMxuBAuFg6S2xrJAGQlYPZ1TSbLl63uk0SVdJzDyf31DA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:05.602284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19982","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c582256ecb99f4d7a57f59ff4c66e567c9cc020e7fa38ba4d3bc96214b687e84","sha256:693a632cd1c80cc859202aff5600cb80e4dc5ce4f457e68da4c770790966a4c2"],"state_sha256":"9380dfb3c7cf067fa92d56b3532cfe0a8df794ffd68c22d82532743273aaba24"}