{"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/differentially-private-sgd-without-clipping","title":"Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach","arxiv_id":"2311.14632","date":"2023-11-24","proceeding":null,"authors":["Xinwei Zhang","Zhiqi Bu","Zhiwei Steven Wu","Mingyi Hong"],"abstract":"Differentially Private Stochastic Gradient Descent with Gradient Clipping (DPSGD-GC) is a powerful tool for training deep learning models using sensitive data, providing both a solid theoretical privacy guarantee and high efficiency. However, using DPSGD-GC to ensure Differential Privacy (DP) comes at the cost of model performance degradation due to DP noise injection and gradient clipping. Existing research has extensively analyzed the theoretical convergence of DPSGD-GC, and has shown that it only converges when using large clipping thresholds that are dependent on problem-specific parameters. Unfortunately, these parameters are often unknown in practice, making it hard to choose the optimal clipping threshold. Therefore, in practice, DPSGD-GC suffers from degraded performance due to the {\\it constant} bias introduced by the clipping. In our work, we propose a new error-feedback (EF) DP algorithm as an alternative to DPSGD-GC, which not only offers a diminishing utility bound without inducing a constant clipping bias, but more importantly, it allows for an arbitrary choice of clipping threshold that is independent of the problem. We establish an algorithm-specific DP analysis for our proposed algorithm, providing privacy guarantees based on R{\\'e}nyi DP. Additionally, we demonstrate that under mild conditions, our algorithm can achieve nearly the same utility bound as DPSGD without gradient clipping. Our empirical results on Cifar-10/100 and E2E datasets, show that the proposed algorithm achieves higher accuracies than DPSGD while maintaining the same level of DP guarantee.","url_abs":"https://arxiv.org/abs/2311.14632v2","url_pdf":"https://arxiv.org/pdf/2311.14632v2.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":"differentially-private-sgd-without-clipping","repo_url":"https://github.com/564612540/DiceSGD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[{"method_slug":"gradient-clipping","method_name":"Gradient Clipping"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2311.14632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2311.14632"}},"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/564612540/DiceSGD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":2,"unverified":3},"by_repo_kind":{"official":{"samples":5,"ran":2,"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":"8abbe1def35e44da","entry":"create_cnn","repo":"564612540/DiceSGD","repo_kind":"official","path":"DiceSGD/model_utils.py","file_url":"https://github.com/564612540/DiceSGD/blob/HEAD/DiceSGD/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8abbe1def35e44da"}},{"code_sha256_prefix":"ec138312ab22cff7","entry":"create_resnet","repo":"564612540/DiceSGD","repo_kind":"official","path":"DiceSGD/model_utils.py","file_url":"https://github.com/564612540/DiceSGD/blob/HEAD/DiceSGD/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec138312ab22cff7"}},{"code_sha256_prefix":"0dfa7799743daf45","entry":"generate","repo":"564612540/DiceSGD","repo_kind":"official","path":"DiceSGD/decoding_utils.py","file_url":"https://github.com/564612540/DiceSGD/blob/HEAD/DiceSGD/decoding_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0dfa7799743daf45"}},{"code_sha256_prefix":"39879b7b6ed688dd","entry":"generate_synthetic","repo":"564612540/DiceSGD","repo_kind":"official","path":"DiceSGD/dataset.py","file_url":"https://github.com/564612540/DiceSGD/blob/HEAD/DiceSGD/dataset.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"39879b7b6ed688dd"}},{"code_sha256_prefix":"b755a07ff2fa0d35","entry":"get_prompt_dataset","repo":"564612540/DiceSGD","repo_kind":"official","path":"DiceSGD/misc.py","file_url":"https://github.com/564612540/DiceSGD/blob/HEAD/DiceSGD/misc.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b755a07ff2fa0d35"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}