{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:GQQEXPUK6V6AADPHIVF3XA373T","short_pith_number":"pith:GQQEXPUK","schema_version":"1.0","canonical_sha256":"34204bbe8af57c000de7454bbb837fdcd4830188397bf0c20d155ca2812f5916","source":{"kind":"arxiv","id":"1507.04254","version":2},"attestation_state":"computed","paper":{"title":"Learning Maximum Entropy Models from finite size datasets: a fast Data-Driven algorithm allows sampling from the posterior distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","q-bio.QM"],"primary_cat":"cond-mat.dis-nn","authors_text":"Ulisse Ferrari","submitted_at":"2015-07-15T15:19:24Z","abstract_excerpt":"Maximum entropy models provide the least constrained probability distributions that reproduce statistical properties of experimental datasets. In this work we characterize the learning dynamics that maximizes the log-likelihood in the case of large but finite datasets. We first show how the steepest descent dynamics is not optimal as it is slowed down by the inhomogeneous curvature of the model parameters space. We then provide a way for rectifying this space which relies only on dataset properties and does not require large computational efforts. We conclude by solving the long-time limit of "},"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":"1507.04254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2015-07-15T15:19:24Z","cross_cats_sorted":["cond-mat.stat-mech","q-bio.QM"],"title_canon_sha256":"5e0295bcfe12ed72eb7c6d0af76fe8c8f60777763be3abb235a55dbfbad11ddc","abstract_canon_sha256":"8548d5841fc96a9ea587df507f49289c9b19eb904fda081ecbc555c4b321fe7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:22.669426Z","signature_b64":"91ad4qfCxcPc3ygoDbR8Z0xXliNhm/MPUIt2wJQ0DERUtMsIPk7c9Ac3rS9Wlx/+sy6mJ9eEtevWfXoj15oOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34204bbe8af57c000de7454bbb837fdcd4830188397bf0c20d155ca2812f5916","last_reissued_at":"2026-05-18T01:04:22.668662Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:22.668662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Maximum Entropy Models from finite size datasets: a fast Data-Driven algorithm allows sampling from the posterior distribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","q-bio.QM"],"primary_cat":"cond-mat.dis-nn","authors_text":"Ulisse Ferrari","submitted_at":"2015-07-15T15:19:24Z","abstract_excerpt":"Maximum entropy models provide the least constrained probability distributions that reproduce statistical properties of experimental datasets. In this work we characterize the learning dynamics that maximizes the log-likelihood in the case of large but finite datasets. We first show how the steepest descent dynamics is not optimal as it is slowed down by the inhomogeneous curvature of the model parameters space. We then provide a way for rectifying this space which relies only on dataset properties and does not require large computational efforts. We conclude by solving the long-time limit of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.04254","kind":"arxiv","version":2},"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":"1507.04254","created_at":"2026-05-18T01:04:22.668780+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.04254v2","created_at":"2026-05-18T01:04:22.668780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.04254","created_at":"2026-05-18T01:04:22.668780+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQQEXPUK6V6A","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQQEXPUK6V6AADPH","created_at":"2026-05-18T12:29:22.688609+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQQEXPUK","created_at":"2026-05-18T12:29:22.688609+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T","json":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T.json","graph_json":"https://pith.science/api/pith-number/GQQEXPUK6V6AADPHIVF3XA373T/graph.json","events_json":"https://pith.science/api/pith-number/GQQEXPUK6V6AADPHIVF3XA373T/events.json","paper":"https://pith.science/paper/GQQEXPUK"},"agent_actions":{"view_html":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T","download_json":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T.json","view_paper":"https://pith.science/paper/GQQEXPUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.04254&json=true","fetch_graph":"https://pith.science/api/pith-number/GQQEXPUK6V6AADPHIVF3XA373T/graph.json","fetch_events":"https://pith.science/api/pith-number/GQQEXPUK6V6AADPHIVF3XA373T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T/action/storage_attestation","attest_author":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T/action/author_attestation","sign_citation":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T/action/citation_signature","submit_replication":"https://pith.science/pith/GQQEXPUK6V6AADPHIVF3XA373T/action/replication_record"}},"created_at":"2026-05-18T01:04:22.668780+00:00","updated_at":"2026-05-18T01:04:22.668780+00:00"}