{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/robust-bi-tempered-logistic-loss-based-on","title":"Robust Bi-Tempered Logistic Loss Based on Bregman Divergences","arxiv_id":"1906.03361","date":"2019-06-08","proceeding":"NeurIPS 2019 12","authors":["Ehsan Amid","Manfred K. Warmuth","Rohan Anil","Tomer Koren"],"abstract":"We introduce a temperature into the exponential function and replace the softmax output layer of neural nets by a high temperature generalization. Similarly, the logarithm in the log loss we use for training is replaced by a low temperature logarithm. By tuning the two temperatures we create loss functions that are non-convex already in the single layer case. When replacing the last layer of the neural nets by our bi-temperature generalization of logistic loss, the training becomes more robust to noise. We visualize the effect of tuning the two temperatures in a simple setting and show the efficacy of our method on large data sets. Our methodology is based on Bregman divergences and is superior to a related two-temperature method using the Tsallis divergence.","url_abs":"https://arxiv.org/abs/1906.03361v3","url_pdf":"https://arxiv.org/pdf/1906.03361v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/google/bi-tempered-loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/Diulhio/bitemperedloss-tf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/NingAnMe/Bi-Tempered-Logistic-Loss-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/fhopfmueller/bi-tempered-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/mlpanda/bi-tempered-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/prakashsellathurai/cassava-leaf-disease-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/MindSpore-scientific-2/code-4/tree/main/bi-tempered-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/bi-tempered-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/MindSpore-scientific-2/code-9/tree/main/bi-tempered-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/MindSpore-scientific/code-4/tree/main/bi-tempered-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"robust-bi-tempered-logistic-loss-based-on","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/4/bi-tempered-loss-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.03361","atlas_url":"https://app.syntology.ai/?focus=1906.03361","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.03361"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mlpanda/bi-tempered-loss-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fhopfmueller/bi-tempered-loss-pytorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-5/tree/main/bi-tempered-loss-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/NingAnMe/Bi-Tempered-Logistic-Loss-PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-4/tree/main/bi-tempered-loss-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific-2/code-9/tree/main/bi-tempered-loss-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/4/bi-tempered-loss-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/google/bi-tempered-loss","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/prakashsellathurai/cassava-leaf-disease-classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Diulhio/bitemperedloss-tf","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MindSpore-scientific/code-4/tree/main/bi-tempered-loss-pytorch","reach":null}],"summary":{"ran_draft_wrong":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"50b56248cffe941d","entry":"compute_normalization_fixed_point","repo":"google/bi-tempered-loss","repo_kind":"official","path":"jax/loss.py","file_url":"https://github.com/google/bi-tempered-loss/blob/HEAD/jax/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"50b56248cffe941d"}},{"code_sha256_prefix":"7e4e198c7c72dbea","entry":"exp_t","repo":"google/bi-tempered-loss","repo_kind":"official","path":"jax/loss.py","file_url":"https://github.com/google/bi-tempered-loss/blob/HEAD/jax/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7e4e198c7c72dbea"}},{"code_sha256_prefix":"04e5103922882b09","entry":"for_loop","repo":"google/bi-tempered-loss","repo_kind":"official","path":"tensorflow/loss.py","file_url":"https://github.com/google/bi-tempered-loss/blob/HEAD/tensorflow/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"04e5103922882b09"}},{"code_sha256_prefix":"16f56f2ad3d1d6c1","entry":"log_t","repo":"google/bi-tempered-loss","repo_kind":"official","path":"jax/loss.py","file_url":"https://github.com/google/bi-tempered-loss/blob/HEAD/jax/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"16f56f2ad3d1d6c1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}