{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:VBOESTYOD6VL7HIYSWYCFP4IQF","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":"a7aa69d99113d33fe0e0f04e93dc5f6f582d692ac12335134ecf6b4c785b9692","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T00:12:07Z","title_canon_sha256":"1b258c29afff2420a03313f09566c87aa80ceab1024dbd250516e6371b854dd6"},"schema_version":"1.0","source":{"id":"1905.05895","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.05895","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.05895v1","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.05895","created_at":"2026-05-17T23:46:08Z"},{"alias_kind":"pith_short_12","alias_value":"VBOESTYOD6VL","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"VBOESTYOD6VL7HIY","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"VBOESTYO","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:faa718c3b407b9441175632552bcfe1173770152e4c49e1be1dd51bcf00f47aa","target":"graph","created_at":"2026-05-17T23:46:08Z","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":"In most machine learning training paradigms a fixed, often handcrafted, loss function is assumed to be a good proxy for an underlying evaluation metric. In this work we assess this assumption by meta-learning an adaptive loss function to directly optimize the evaluation metric. We propose a sample efficient reinforcement learning approach for adapting the loss dynamically during training. We empirically show how this formulation improves performance by simultaneously optimizing the evaluation metric and smoothing the loss landscape. We verify our method in metric learning and classification sc","authors_text":"Carlos Guestrin, Chen Huang, Josh Susskind, Miguel Angel Bautista, Shih-Yu Sun, Shuangfei Zhai, Walter Talbott","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T00:12:07Z","title":"Addressing the Loss-Metric Mismatch with Adaptive Loss Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.05895","kind":"arxiv","version":1},"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":"sha256:735218764172b42a353d2eef91080535d03c1826a236c5ba240b10f7257a2416","target":"record","created_at":"2026-05-17T23:46:08Z","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":"a7aa69d99113d33fe0e0f04e93dc5f6f582d692ac12335134ecf6b4c785b9692","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-15T00:12:07Z","title_canon_sha256":"1b258c29afff2420a03313f09566c87aa80ceab1024dbd250516e6371b854dd6"},"schema_version":"1.0","source":{"id":"1905.05895","kind":"arxiv","version":1}},"canonical_sha256":"a85c494f0e1faabf9d1895b022bf88817cd7f41f36a7790c0de1590f4b63173f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a85c494f0e1faabf9d1895b022bf88817cd7f41f36a7790c0de1590f4b63173f","first_computed_at":"2026-05-17T23:46:08.184168Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:08.184168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v9uuE+NMHctNTR0Eb3bSu4Ey1AAxaI0fGPtBEAWcE39vNnfe5CebudNCwQLd5lH6LFyfwVMTaVxFu0UZnr5/Bw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:08.184815Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.05895","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:735218764172b42a353d2eef91080535d03c1826a236c5ba240b10f7257a2416","sha256:faa718c3b407b9441175632552bcfe1173770152e4c49e1be1dd51bcf00f47aa"],"state_sha256":"0da475f2735e577b1d0a1674dca1298526c89b4ad801d4c3f2cbdeaef10dd305"}