{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XLFMLSPPZSXJLUZ6IFRZNNXV7Z","short_pith_number":"pith:XLFMLSPP","schema_version":"1.0","canonical_sha256":"bacac5c9efccae95d33e416396b6f5fe6e82a82e8a16949a521fd39d73d125f1","source":{"kind":"arxiv","id":"1802.08770","version":4},"attestation_state":"computed","paper":{"title":"A Walk with SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chen Xing, Christos Tsirigotis, Devansh Arpit, Yoshua Bengio","submitted_at":"2018-02-24T00:21:10Z","abstract_excerpt":"We present novel empirical observations regarding how stochastic gradient descent (SGD) navigates the loss landscape of over-parametrized deep neural networks (DNNs). These observations expose the qualitatively different roles of learning rate and batch-size in DNN optimization and generalization. Specifically we study the DNN loss surface along the trajectory of SGD by interpolating the loss surface between parameters from consecutive \\textit{iterations} and tracking various metrics during training. We find that the loss interpolation between parameters before and after each training iteratio"},"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":"1802.08770","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-24T00:21:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d1ff5716651889c85dd3a29c44da3d3be801e39744c53508f5f9d3e23d372d6d","abstract_canon_sha256":"037f6ef1b71059a669954b27021e605596de8f3db5b3a1b18364f4281e9e89b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:40.266908Z","signature_b64":"sZNdqPic9A0EEq9xfdi16X2MHG/sKWJYL4GBnZgVRL0zmHTutN+Jj/6zjPXIWsQCloNCkzEmwtxTA0jZYEl2CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bacac5c9efccae95d33e416396b6f5fe6e82a82e8a16949a521fd39d73d125f1","last_reissued_at":"2026-05-18T00:14:40.266377Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:40.266377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Walk with SGD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chen Xing, Christos Tsirigotis, Devansh Arpit, Yoshua Bengio","submitted_at":"2018-02-24T00:21:10Z","abstract_excerpt":"We present novel empirical observations regarding how stochastic gradient descent (SGD) navigates the loss landscape of over-parametrized deep neural networks (DNNs). These observations expose the qualitatively different roles of learning rate and batch-size in DNN optimization and generalization. Specifically we study the DNN loss surface along the trajectory of SGD by interpolating the loss surface between parameters from consecutive \\textit{iterations} and tracking various metrics during training. We find that the loss interpolation between parameters before and after each training iteratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08770","kind":"arxiv","version":4},"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":"1802.08770","created_at":"2026-05-18T00:14:40.266455+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08770v4","created_at":"2026-05-18T00:14:40.266455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08770","created_at":"2026-05-18T00:14:40.266455+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLFMLSPPZSXJ","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLFMLSPPZSXJLUZ6","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLFMLSPP","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"1907.10732","citing_title":"Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization","ref_index":77,"is_internal_anchor":true},{"citing_arxiv_id":"2212.08989","citing_title":"Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics","ref_index":212,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16622","citing_title":"Does Weight Decay Enhance Training Stability?","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2412.13663","citing_title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","ref_index":202,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15416","citing_title":"Margin-Adaptive Confidence Ranking for Reliable LLM Judgement","ref_index":182,"is_internal_anchor":true},{"citing_arxiv_id":"2510.04800","citing_title":"Hybrid Architectures for Language Models: Systematic Analysis and Design Insights","ref_index":59,"is_internal_anchor":true},{"citing_arxiv_id":"2603.10079","citing_title":"Large Spikes in Stochastic Gradient Descent: A Large-Deviations View","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20446","citing_title":"The Origin of Edge of Stability","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13627","citing_title":"(How) Learning Rates Regulate Catastrophic Overtraining","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14108","citing_title":"Momentum Further Constrains Sharpness at the Edge of Stochastic Stability","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19740","citing_title":"Generalization at the Edge of Stability","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21016","citing_title":"SGD at the Edge of Stability: The Stochastic Sharpness Gap","ref_index":65,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z","json":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z.json","graph_json":"https://pith.science/api/pith-number/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/graph.json","events_json":"https://pith.science/api/pith-number/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/events.json","paper":"https://pith.science/paper/XLFMLSPP"},"agent_actions":{"view_html":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z","download_json":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z.json","view_paper":"https://pith.science/paper/XLFMLSPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08770&json=true","fetch_graph":"https://pith.science/api/pith-number/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/action/storage_attestation","attest_author":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/action/author_attestation","sign_citation":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/action/citation_signature","submit_replication":"https://pith.science/pith/XLFMLSPPZSXJLUZ6IFRZNNXV7Z/action/replication_record"}},"created_at":"2026-05-18T00:14:40.266455+00:00","updated_at":"2026-05-18T00:14:40.266455+00:00"}