{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:JGYCICRTCPUQJJEW4ZBXJSBKPV","short_pith_number":"pith:JGYCICRT","canonical_record":{"source":{"id":"2006.15815","kind":"arxiv","version":11},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T05:21:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"09f6355009cd512fa30c83528e82e11f8379b2f4b7e4245e5c538c6aef012135","abstract_canon_sha256":"97aeca93568f7bee0fe603c3d736b9a0342a950948b0b764d9079e1a4d0301cc"},"schema_version":"1.0"},"canonical_sha256":"49b0240a3313e904a496e64374c82a7d6b7c1ec7172fbd7e51cc88891aca76de","source":{"kind":"arxiv","id":"2006.15815","version":11},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15815","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15815v11","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15815","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"JGYCICRTCPUQ","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_16","alias_value":"JGYCICRTCPUQJJEW","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_8","alias_value":"JGYCICRT","created_at":"2026-07-05T04:31:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:JGYCICRTCPUQJJEW4ZBXJSBKPV","target":"record","payload":{"canonical_record":{"source":{"id":"2006.15815","kind":"arxiv","version":11},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T05:21:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"09f6355009cd512fa30c83528e82e11f8379b2f4b7e4245e5c538c6aef012135","abstract_canon_sha256":"97aeca93568f7bee0fe603c3d736b9a0342a950948b0b764d9079e1a4d0301cc"},"schema_version":"1.0"},"canonical_sha256":"49b0240a3313e904a496e64374c82a7d6b7c1ec7172fbd7e51cc88891aca76de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:19.918395Z","signature_b64":"0N8gU51hpkeC9pugWnNyNSnEIZyaf/0a771/A7OHQpbbEo1s5hkxaxLwStaGdDWGXbFUcoIr3j16+zqR2i67AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49b0240a3313e904a496e64374c82a7d6b7c1ec7172fbd7e51cc88891aca76de","last_reissued_at":"2026-07-05T04:31:19.917882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:19.917882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.15815","source_version":11,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IfssK5z+pYxUfovw2bL5a4es5vm4ZvgFZdVLOw+72h/IU8ImYmRIecmKbQ8idbTNPuNCWLme0IeTmEzC7yg3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:40:27.903504Z"},"content_sha256":"39a9260593462e444ea924d5385283e8e87045850f58ba67b99260f46885b6dd","schema_version":"1.0","event_id":"sha256:39a9260593462e444ea924d5385283e8e87045850f58ba67b99260f46885b6dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:JGYCICRTCPUQJJEW4ZBXJSBKPV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Huishuai Zhang, Issei Sato, Masashi Sugiyama, Xinrui Wang, Zeke Xie","submitted_at":"2020-06-29T05:21:02Z","abstract_excerpt":"Adaptive Moment Estimation (Adam), which combines Adaptive Learning Rate and Momentum, would be the most popular stochastic optimizer for accelerating the training of deep neural networks. However, it is empirically known that Adam often generalizes worse than Stochastic Gradient Descent (SGD). The purpose of this paper is to unveil the mystery of this behavior in the diffusion theoretical framework. Specifically, we disentangle the effects of Adaptive Learning Rate and Momentum of the Adam dynamics on saddle-point escaping and flat minima selection. We prove that Adaptive Learning Rate can es"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15815","kind":"arxiv","version":11},"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/2006.15815/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:31:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wi8IcyGgNJfEa9NOR+jyC1BWaHGFPUmudjYFitgoq7DdUoSI4q76NszEUqe5JTfnerN+Ux3+m2yfGNTn14qnCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:40:27.904169Z"},"content_sha256":"62091f5b35f8723d7923f099b45d01bc225d6ec44a9b1d29d25fccb244d5d62e","schema_version":"1.0","event_id":"sha256:62091f5b35f8723d7923f099b45d01bc225d6ec44a9b1d29d25fccb244d5d62e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JGYCICRTCPUQJJEW4ZBXJSBKPV/bundle.json","state_url":"https://pith.science/pith/JGYCICRTCPUQJJEW4ZBXJSBKPV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JGYCICRTCPUQJJEW4ZBXJSBKPV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T15:40:27Z","links":{"resolver":"https://pith.science/pith/JGYCICRTCPUQJJEW4ZBXJSBKPV","bundle":"https://pith.science/pith/JGYCICRTCPUQJJEW4ZBXJSBKPV/bundle.json","state":"https://pith.science/pith/JGYCICRTCPUQJJEW4ZBXJSBKPV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JGYCICRTCPUQJJEW4ZBXJSBKPV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JGYCICRTCPUQJJEW4ZBXJSBKPV","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":"97aeca93568f7bee0fe603c3d736b9a0342a950948b0b764d9079e1a4d0301cc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T05:21:02Z","title_canon_sha256":"09f6355009cd512fa30c83528e82e11f8379b2f4b7e4245e5c538c6aef012135"},"schema_version":"1.0","source":{"id":"2006.15815","kind":"arxiv","version":11}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.15815","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"arxiv_version","alias_value":"2006.15815v11","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.15815","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_12","alias_value":"JGYCICRTCPUQ","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_16","alias_value":"JGYCICRTCPUQJJEW","created_at":"2026-07-05T04:31:19Z"},{"alias_kind":"pith_short_8","alias_value":"JGYCICRT","created_at":"2026-07-05T04:31:19Z"}],"graph_snapshots":[{"event_id":"sha256:62091f5b35f8723d7923f099b45d01bc225d6ec44a9b1d29d25fccb244d5d62e","target":"graph","created_at":"2026-07-05T04:31:19Z","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/2006.15815/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adaptive Moment Estimation (Adam), which combines Adaptive Learning Rate and Momentum, would be the most popular stochastic optimizer for accelerating the training of deep neural networks. However, it is empirically known that Adam often generalizes worse than Stochastic Gradient Descent (SGD). The purpose of this paper is to unveil the mystery of this behavior in the diffusion theoretical framework. Specifically, we disentangle the effects of Adaptive Learning Rate and Momentum of the Adam dynamics on saddle-point escaping and flat minima selection. We prove that Adaptive Learning Rate can es","authors_text":"Huishuai Zhang, Issei Sato, Masashi Sugiyama, Xinrui Wang, Zeke Xie","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T05:21:02Z","title":"Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.15815","kind":"arxiv","version":11},"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":"sha256:39a9260593462e444ea924d5385283e8e87045850f58ba67b99260f46885b6dd","target":"record","created_at":"2026-07-05T04:31:19Z","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":"97aeca93568f7bee0fe603c3d736b9a0342a950948b0b764d9079e1a4d0301cc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-29T05:21:02Z","title_canon_sha256":"09f6355009cd512fa30c83528e82e11f8379b2f4b7e4245e5c538c6aef012135"},"schema_version":"1.0","source":{"id":"2006.15815","kind":"arxiv","version":11}},"canonical_sha256":"49b0240a3313e904a496e64374c82a7d6b7c1ec7172fbd7e51cc88891aca76de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49b0240a3313e904a496e64374c82a7d6b7c1ec7172fbd7e51cc88891aca76de","first_computed_at":"2026-07-05T04:31:19.917882Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:31:19.917882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0N8gU51hpkeC9pugWnNyNSnEIZyaf/0a771/A7OHQpbbEo1s5hkxaxLwStaGdDWGXbFUcoIr3j16+zqR2i67AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:31:19.918395Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.15815","source_kind":"arxiv","source_version":11}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39a9260593462e444ea924d5385283e8e87045850f58ba67b99260f46885b6dd","sha256:62091f5b35f8723d7923f099b45d01bc225d6ec44a9b1d29d25fccb244d5d62e"],"state_sha256":"a0a809650fe6ab53fc384333f6e5b23d89c7c374bbf5043dc6347a31e33a5a47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cQKJzKXwWVP0AUDqbCvRwGMLL7mdiN2oko0tA44IoJspW/VfP+FE5wuQh8xMVZOpBJBDivLuz3vhDGQ6uFmQDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:40:27.906091Z","bundle_sha256":"b5c545d3bbda3090cbc1370cc44fa590c49469d970f8ac1a14e56a6bc457494d"}}