{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:YLRHEWRYPDGOE4RUDFE3H3DRCH","short_pith_number":"pith:YLRHEWRY","schema_version":"1.0","canonical_sha256":"c2e2725a3878cce272341949b3ec7111f812c468b2f8f3d8d0e2b52d7037fdf8","source":{"kind":"arxiv","id":"1505.05401","version":2},"attestation_state":"computed","paper":{"title":"A Max-Sum algorithm for training discrete neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cond-mat.dis-nn","authors_text":"Alfredo Braunstein, Carlo Baldassi","submitted_at":"2015-05-20T14:34:23Z","abstract_excerpt":"We present an efficient learning algorithm for the problem of training neural networks with discrete synapses, a well-known hard (NP-complete) discrete optimization problem. The algorithm is a variant of the so-called Max-Sum (MS) algorithm. In particular, we show how, for bounded integer weights with $q$ distinct states and independent concave a priori distribution (e.g. $l_{1}$ regularization), the algorithm's time complexity can be made to scale as $O\\left(N\\log N\\right)$ per node update, thus putting it on par with alternative schemes, such as Belief Propagation (BP), without resorting to "},"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":"1505.05401","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2015-05-20T14:34:23Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"7df78dbe10e513ffafe21bcea39af6c800be17e06cc64d8c2ac58b7c38651109","abstract_canon_sha256":"6eb39b5050aa813cde3f1a7686800dc5ef36b2bb239e1cfe6ac327cbb6d3cd56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:22.253389Z","signature_b64":"eNUv5VkrXwEBdLEp9cq+v2PAFmYXrYb5e/jkvBa39ZZGQA6iFzo6O9Ax8D6JqWFj2vhGPNxMtm0lqOjKmUeJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2e2725a3878cce272341949b3ec7111f812c468b2f8f3d8d0e2b52d7037fdf8","last_reissued_at":"2026-05-18T01:35:22.252654Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:22.252654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Max-Sum algorithm for training discrete neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"cond-mat.dis-nn","authors_text":"Alfredo Braunstein, Carlo Baldassi","submitted_at":"2015-05-20T14:34:23Z","abstract_excerpt":"We present an efficient learning algorithm for the problem of training neural networks with discrete synapses, a well-known hard (NP-complete) discrete optimization problem. The algorithm is a variant of the so-called Max-Sum (MS) algorithm. In particular, we show how, for bounded integer weights with $q$ distinct states and independent concave a priori distribution (e.g. $l_{1}$ regularization), the algorithm's time complexity can be made to scale as $O\\left(N\\log N\\right)$ per node update, thus putting it on par with alternative schemes, such as Belief Propagation (BP), without resorting to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1505.05401","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":"1505.05401","created_at":"2026-05-18T01:35:22.252774+00:00"},{"alias_kind":"arxiv_version","alias_value":"1505.05401v2","created_at":"2026-05-18T01:35:22.252774+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1505.05401","created_at":"2026-05-18T01:35:22.252774+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLRHEWRYPDGO","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLRHEWRYPDGOE4RU","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLRHEWRY","created_at":"2026-05-18T12:29:50.041715+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/YLRHEWRYPDGOE4RUDFE3H3DRCH","json":"https://pith.science/pith/YLRHEWRYPDGOE4RUDFE3H3DRCH.json","graph_json":"https://pith.science/api/pith-number/YLRHEWRYPDGOE4RUDFE3H3DRCH/graph.json","events_json":"https://pith.science/api/pith-number/YLRHEWRYPDGOE4RUDFE3H3DRCH/events.json","paper":"https://pith.science/paper/YLRHEWRY"},"agent_actions":{"view_html":"https://pith.science/pith/YLRHEWRYPDGOE4RUDFE3H3DRCH","download_json":"https://pith.science/pith/YLRHEWRYPDGOE4RUDFE3H3DRCH.json","view_paper":"https://pith.science/paper/YLRHEWRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1505.05401&json=true","fetch_graph":"https://pith.science/api/pith-number/YLRHEWRYPDGOE4RUDFE3H3DRCH/graph.json","fetch_events":"https://pith.science/api/pith-number/YLRHEWRYPDGOE4RUDFE3H3DRCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLRHEWRYPDGOE4RUDFE3H3DRCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLRHEWRYPDGOE4RUDFE3H3DRCH/action/storage_attestation","attest_author":"https://pith.science/pith/YLRHEWRYPDGOE4RUDFE3H3DRCH/action/author_attestation","sign_citation":"https://pith.science/pith/YLRHEWRYPDGOE4RUDFE3H3DRCH/action/citation_signature","submit_replication":"https://pith.science/pith/YLRHEWRYPDGOE4RUDFE3H3DRCH/action/replication_record"}},"created_at":"2026-05-18T01:35:22.252774+00:00","updated_at":"2026-05-18T01:35:22.252774+00:00"}