{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DDD3BF63IH3UHHVY5DIKSSNRI6","short_pith_number":"pith:DDD3BF63","schema_version":"1.0","canonical_sha256":"18c7b097db41f7439eb8e8d0a949b147a1db5a2730198a2e1574808435cddabb","source":{"kind":"arxiv","id":"2103.02770","version":1},"attestation_state":"computed","paper":{"title":"SVMax: A Feature Embedding Regularizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ahmed Taha, Alex Hanson, Larry Davis","submitted_at":"2021-03-04T00:29:47Z","abstract_excerpt":"A neural network regularizer (e.g., weight decay) boosts performance by explicitly penalizing the complexity of a network. In this paper, we penalize inferior network activations -- feature embeddings -- which in turn regularize the network's weights implicitly. We propose singular value maximization (SVMax) to learn a more uniform feature embedding. The SVMax regularizer supports both supervised and unsupervised learning. Our formulation mitigates model collapse and enables larger learning rates. We evaluate the SVMax regularizer using both retrieval and generative adversarial networks. We le"},"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":"2103.02770","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-04T00:29:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b064ff7f956a6e3bb3d7be007e899157e52d270f59ecd56e22a655ec87c347d","abstract_canon_sha256":"d46a83fee083ca1d3b77b7264d71a8fe4196753f26188957ca9da467561af366"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:21.010806Z","signature_b64":"3qKKZrQOEG5gom9EuUjbqoaOO0/7VjN9hmWEi7a77whwkq0HAZzLJwJrf2p2uKD812rBL5VMDA/WcitL1xKXBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18c7b097db41f7439eb8e8d0a949b147a1db5a2730198a2e1574808435cddabb","last_reissued_at":"2026-07-05T02:20:21.010385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:21.010385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SVMax: A Feature Embedding Regularizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Ahmed Taha, Alex Hanson, Larry Davis","submitted_at":"2021-03-04T00:29:47Z","abstract_excerpt":"A neural network regularizer (e.g., weight decay) boosts performance by explicitly penalizing the complexity of a network. In this paper, we penalize inferior network activations -- feature embeddings -- which in turn regularize the network's weights implicitly. We propose singular value maximization (SVMax) to learn a more uniform feature embedding. The SVMax regularizer supports both supervised and unsupervised learning. Our formulation mitigates model collapse and enables larger learning rates. We evaluate the SVMax regularizer using both retrieval and generative adversarial networks. We le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.02770","kind":"arxiv","version":1},"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/2103.02770/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2103.02770","created_at":"2026-07-05T02:20:21.010445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.02770v1","created_at":"2026-07-05T02:20:21.010445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.02770","created_at":"2026-07-05T02:20:21.010445+00:00"},{"alias_kind":"pith_short_12","alias_value":"DDD3BF63IH3U","created_at":"2026-07-05T02:20:21.010445+00:00"},{"alias_kind":"pith_short_16","alias_value":"DDD3BF63IH3UHHVY","created_at":"2026-07-05T02:20:21.010445+00:00"},{"alias_kind":"pith_short_8","alias_value":"DDD3BF63","created_at":"2026-07-05T02:20:21.010445+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/DDD3BF63IH3UHHVY5DIKSSNRI6","json":"https://pith.science/pith/DDD3BF63IH3UHHVY5DIKSSNRI6.json","graph_json":"https://pith.science/api/pith-number/DDD3BF63IH3UHHVY5DIKSSNRI6/graph.json","events_json":"https://pith.science/api/pith-number/DDD3BF63IH3UHHVY5DIKSSNRI6/events.json","paper":"https://pith.science/paper/DDD3BF63"},"agent_actions":{"view_html":"https://pith.science/pith/DDD3BF63IH3UHHVY5DIKSSNRI6","download_json":"https://pith.science/pith/DDD3BF63IH3UHHVY5DIKSSNRI6.json","view_paper":"https://pith.science/paper/DDD3BF63","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.02770&json=true","fetch_graph":"https://pith.science/api/pith-number/DDD3BF63IH3UHHVY5DIKSSNRI6/graph.json","fetch_events":"https://pith.science/api/pith-number/DDD3BF63IH3UHHVY5DIKSSNRI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DDD3BF63IH3UHHVY5DIKSSNRI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DDD3BF63IH3UHHVY5DIKSSNRI6/action/storage_attestation","attest_author":"https://pith.science/pith/DDD3BF63IH3UHHVY5DIKSSNRI6/action/author_attestation","sign_citation":"https://pith.science/pith/DDD3BF63IH3UHHVY5DIKSSNRI6/action/citation_signature","submit_replication":"https://pith.science/pith/DDD3BF63IH3UHHVY5DIKSSNRI6/action/replication_record"}},"created_at":"2026-07-05T02:20:21.010445+00:00","updated_at":"2026-07-05T02:20:21.010445+00:00"}