{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:MLHUP6LBMZ6UEGU5IGROHPAWSR","short_pith_number":"pith:MLHUP6LB","canonical_record":{"source":{"id":"1806.06317","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T00:42:09Z","cross_cats_sorted":["math.NA","stat.ML"],"title_canon_sha256":"287e68eb1ea0006f8eaf363c83332da05b229de9c80004e9e4c5376e23b6ae29","abstract_canon_sha256":"2d309200c7a70a924514eeba58a2b066dd580b700f0696b47571d277f9a1db0e"},"schema_version":"1.0"},"canonical_sha256":"62cf47f961667d421a9d41a2e3bc1694668ca29d7984d39e3f7aaa885a576747","source":{"kind":"arxiv","id":"1806.06317","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06317","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06317v5","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06317","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"MLHUP6LBMZ6U","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MLHUP6LBMZ6UEGU5","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MLHUP6LB","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:MLHUP6LBMZ6UEGU5IGROHPAWSR","target":"record","payload":{"canonical_record":{"source":{"id":"1806.06317","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T00:42:09Z","cross_cats_sorted":["math.NA","stat.ML"],"title_canon_sha256":"287e68eb1ea0006f8eaf363c83332da05b229de9c80004e9e4c5376e23b6ae29","abstract_canon_sha256":"2d309200c7a70a924514eeba58a2b066dd580b700f0696b47571d277f9a1db0e"},"schema_version":"1.0"},"canonical_sha256":"62cf47f961667d421a9d41a2e3bc1694668ca29d7984d39e3f7aaa885a576747","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:39.969040Z","signature_b64":"vKv+zUH1b+Gt+ax21pyoegSVYiOSV+1M30Ps6cuCv7iqPpeJ3ADAb9+ckUP1pxI/6E/r96q6Jxqtc4IU3nKJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62cf47f961667d421a9d41a2e3bc1694668ca29d7984d39e3f7aaa885a576747","last_reissued_at":"2026-05-17T23:47:39.968638Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:39.968638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.06317","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FEiFJWYQApyEIC0B3RjVilEzxF9ODh6UEP8bVPbQ31i6F6SULEh7ZAJ1YFP6NlzzqnLq1kCFu22jhyCqvj2mAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:29:48.981533Z"},"content_sha256":"b12afa58e347d802c3ab82cd3ea82f2d4222cc06c2c31f2d70f5ad19d057fc0b","schema_version":"1.0","event_id":"sha256:b12afa58e347d802c3ab82cd3ea82f2d4222cc06c2c31f2d70f5ad19d057fc0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:MLHUP6LBMZ6UEGU5IGROHPAWSR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Laplacian Smoothing Gradient Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.NA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Lin, Bao Wang, Farzin Barekat, Minh Pham, Penghang Yin, Stanley Osher, Xiyang Luo","submitted_at":"2018-06-17T00:42:09Z","abstract_excerpt":"We propose a class of very simple modifications of gradient descent and stochastic gradient descent. We show that when applied to a large variety of machine learning problems, ranging from logistic regression to deep neural nets, the proposed surrogates can dramatically reduce the variance, allow to take a larger step size, and improve the generalization accuracy. The methods only involve multiplying the usual (stochastic) gradient by the inverse of a positive definitive matrix (which can be computed efficiently by FFT) with a low condition number coming from a one-dimensional discrete Laplaci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06317","kind":"arxiv","version":5},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FOnxGgjGKMB2hpIjOVkLNni5r9EACzFUpkCZYCQRh8uHE7gQ/xzRsXQ18J0jxXTOwJZ8WQUxXgH1FPQQ2rY3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T19:29:48.982213Z"},"content_sha256":"e44939d40bd98bac23c4f6791f3d57ddc7976ee5713055f2f6bc27b53df3c69f","schema_version":"1.0","event_id":"sha256:e44939d40bd98bac23c4f6791f3d57ddc7976ee5713055f2f6bc27b53df3c69f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLHUP6LBMZ6UEGU5IGROHPAWSR/bundle.json","state_url":"https://pith.science/pith/MLHUP6LBMZ6UEGU5IGROHPAWSR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLHUP6LBMZ6UEGU5IGROHPAWSR/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":"2026-05-29T19:29:48Z","links":{"resolver":"https://pith.science/pith/MLHUP6LBMZ6UEGU5IGROHPAWSR","bundle":"https://pith.science/pith/MLHUP6LBMZ6UEGU5IGROHPAWSR/bundle.json","state":"https://pith.science/pith/MLHUP6LBMZ6UEGU5IGROHPAWSR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLHUP6LBMZ6UEGU5IGROHPAWSR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:MLHUP6LBMZ6UEGU5IGROHPAWSR","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":"2d309200c7a70a924514eeba58a2b066dd580b700f0696b47571d277f9a1db0e","cross_cats_sorted":["math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T00:42:09Z","title_canon_sha256":"287e68eb1ea0006f8eaf363c83332da05b229de9c80004e9e4c5376e23b6ae29"},"schema_version":"1.0","source":{"id":"1806.06317","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06317","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06317v5","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06317","created_at":"2026-05-17T23:47:39Z"},{"alias_kind":"pith_short_12","alias_value":"MLHUP6LBMZ6U","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"MLHUP6LBMZ6UEGU5","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"MLHUP6LB","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:e44939d40bd98bac23c4f6791f3d57ddc7976ee5713055f2f6bc27b53df3c69f","target":"graph","created_at":"2026-05-17T23:47:39Z","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"},"paper":{"abstract_excerpt":"We propose a class of very simple modifications of gradient descent and stochastic gradient descent. We show that when applied to a large variety of machine learning problems, ranging from logistic regression to deep neural nets, the proposed surrogates can dramatically reduce the variance, allow to take a larger step size, and improve the generalization accuracy. The methods only involve multiplying the usual (stochastic) gradient by the inverse of a positive definitive matrix (which can be computed efficiently by FFT) with a low condition number coming from a one-dimensional discrete Laplaci","authors_text":"Alex Lin, Bao Wang, Farzin Barekat, Minh Pham, Penghang Yin, Stanley Osher, Xiyang Luo","cross_cats":["math.NA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T00:42:09Z","title":"Laplacian Smoothing Gradient Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06317","kind":"arxiv","version":5},"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:b12afa58e347d802c3ab82cd3ea82f2d4222cc06c2c31f2d70f5ad19d057fc0b","target":"record","created_at":"2026-05-17T23:47:39Z","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":"2d309200c7a70a924514eeba58a2b066dd580b700f0696b47571d277f9a1db0e","cross_cats_sorted":["math.NA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-17T00:42:09Z","title_canon_sha256":"287e68eb1ea0006f8eaf363c83332da05b229de9c80004e9e4c5376e23b6ae29"},"schema_version":"1.0","source":{"id":"1806.06317","kind":"arxiv","version":5}},"canonical_sha256":"62cf47f961667d421a9d41a2e3bc1694668ca29d7984d39e3f7aaa885a576747","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62cf47f961667d421a9d41a2e3bc1694668ca29d7984d39e3f7aaa885a576747","first_computed_at":"2026-05-17T23:47:39.968638Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:39.968638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vKv+zUH1b+Gt+ax21pyoegSVYiOSV+1M30Ps6cuCv7iqPpeJ3ADAb9+ckUP1pxI/6E/r96q6Jxqtc4IU3nKJDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:39.969040Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06317","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b12afa58e347d802c3ab82cd3ea82f2d4222cc06c2c31f2d70f5ad19d057fc0b","sha256:e44939d40bd98bac23c4f6791f3d57ddc7976ee5713055f2f6bc27b53df3c69f"],"state_sha256":"bb51d33a19de953e20fca8cd519eb2f26a6dd19271df264ad34de038cdc1eae6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MRgKl9VurQUo4bXNEqwwS7RFJROZy0ZB5OEo42y+p8G4cofKCVLSiQJZm0n+tkD+zOvktCS+H6wWEHfmUJPIBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T19:29:48.986018Z","bundle_sha256":"422a50e760ed1d1528e18c9c3c2b1b45cb1f41532964bda521091dc8dc8222e8"}}