{"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/stochastic-gradient-methods-with-layer-wise","title":"Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks","arxiv_id":"1905.11286","date":"2019-05-27","proceeding":null,"authors":["Boris Ginsburg","Patrice Castonguay","Oleksii Hrinchuk","Oleksii Kuchaiev","Vitaly Lavrukhin","Ryan Leary","Jason Li","Huyen Nguyen","Yang Zhang","Jonathan M. Cohen"],"abstract":"We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay. In our experiments on neural networks for image classification, speech recognition, machine translation, and language modeling, it performs on par or better than well tuned SGD with momentum and Adam or AdamW. Additionally, NovoGrad (1) is robust to the choice of learning rate and weight initialization, (2) works well in a large batch setting, and (3) has two times smaller memory footprint than Adam.","url_abs":"https://arxiv.org/abs/1905.11286v3","url_pdf":"https://arxiv.org/pdf/1905.11286v3.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":"stochastic-gradient-methods-with-layer-wise","repo_url":"https://github.com/NVIDIA/OpenSeq2Seq","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"stochastic-gradient-methods-with-layer-wise","repo_url":"https://github.com/Edresson/VoiceSplit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"stochastic-gradient-methods-with-layer-wise","repo_url":"https://github.com/convergence-lab/novograd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"stochastic-optimization","task_name":"Stochastic Optimization"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adamw","method_name":"AdamW"},{"method_slug":"sgd","method_name":"SGD"},{"method_slug":"sgd-with-momentum","method_name":"SGD with Momentum"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.11286","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1905.11286"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/NVIDIA/OpenSeq2Seq","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Edresson/VoiceSplit","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/convergence-lab/novograd","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":15},"by_repo_kind":{"named_in_paper":{"samples":5,"ran":0,"repositories":1},"listed":{"samples":11,"ran":1,"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":"9563ca1187f4def1","entry":"formatter","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"generator_paper.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/generator_paper.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9563ca1187f4def1"}},{"code_sha256_prefix":"e2be51dbbe1b0417","entry":"dynamic_range_compression","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/audio.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e2be51dbbe1b0417"}},{"code_sha256_prefix":"f2c495798df6e4e4","entry":"dynamic_range_decompression","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/audio.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f2c495798df6e4e4"}},{"code_sha256_prefix":"37bbc4307e40fc3d","entry":"eval_dataloader","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/dataset.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"37bbc4307e40fc3d"}},{"code_sha256_prefix":"63cdde3c993f3ca1","entry":"fig2np","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/tensorboard.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/tensorboard.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63cdde3c993f3ca1"}},{"code_sha256_prefix":"2f44eccb0ea1dddd","entry":"get_audios_with_random_amp","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/generic_utils.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/generic_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f44eccb0ea1dddd"}},{"code_sha256_prefix":"b490372d6caf2e08","entry":"get_mask","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/generic_utils.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/generic_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b490372d6caf2e08"}},{"code_sha256_prefix":"8b74825f106b92de","entry":"glob_re_to_filename","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/generic_utils.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/generic_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8b74825f106b92de"}},{"code_sha256_prefix":"3ca5033f79170e1d","entry":"levenshtein","repo":"NVIDIA/OpenSeq2Seq","repo_kind":"named_in_paper","path":"external_lm_rescore/process_beam_dump.py","file_url":"https://github.com/NVIDIA/OpenSeq2Seq/blob/HEAD/external_lm_rescore/process_beam_dump.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3ca5033f79170e1d"}},{"code_sha256_prefix":"208ca2fc2f2bfbce","entry":"load_test_sample","repo":"NVIDIA/OpenSeq2Seq","repo_kind":"named_in_paper","path":"ctc_decoder_with_lm/ctc-test.py","file_url":"https://github.com/NVIDIA/OpenSeq2Seq/blob/HEAD/ctc_decoder_with_lm/ctc-test.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"208ca2fc2f2bfbce"}},{"code_sha256_prefix":"00c6b131afd785b5","entry":"load_vocab","repo":"NVIDIA/OpenSeq2Seq","repo_kind":"named_in_paper","path":"ctc_decoder_with_lm/ctc-test.py","file_url":"https://github.com/NVIDIA/OpenSeq2Seq/blob/HEAD/ctc_decoder_with_lm/ctc-test.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"00c6b131afd785b5"}},{"code_sha256_prefix":"c34124e879d7f774","entry":"plot_spectrogram_to_numpy","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/tensorboard.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/tensorboard.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c34124e879d7f774"}},{"code_sha256_prefix":"fe91957d004bddae","entry":"score_fun_linear","repo":"NVIDIA/OpenSeq2Seq","repo_kind":"named_in_paper","path":"external_lm_rescore/process_beam_dump.py","file_url":"https://github.com/NVIDIA/OpenSeq2Seq/blob/HEAD/external_lm_rescore/process_beam_dump.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fe91957d004bddae"}},{"code_sha256_prefix":"758f37e8c4f07d0f","entry":"softmax","repo":"NVIDIA/OpenSeq2Seq","repo_kind":"named_in_paper","path":"frame_asr.py","file_url":"https://github.com/NVIDIA/OpenSeq2Seq/blob/HEAD/frame_asr.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"758f37e8c4f07d0f"}},{"code_sha256_prefix":"433047dab631b9ad","entry":"test_dataloader","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/dataset.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"433047dab631b9ad"}},{"code_sha256_prefix":"b4d4be1b39e495ba","entry":"train_dataloader","repo":"Edresson/VoiceSplit","repo_kind":"listed","path":"utils/dataset.py","file_url":"https://github.com/Edresson/VoiceSplit/blob/HEAD/utils/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b4d4be1b39e495ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}