{"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/privacy-without-noisy-gradients-slicing","title":"Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training","arxiv_id":"2410.19941","date":"2024-10-25","proceeding":null,"authors":["Kristjan Greenewald","Yuancheng Yu","Hao Wang","Kai Xu"],"abstract":"Training generative models with differential privacy (DP) typically involves injecting noise into gradient updates or adapting the discriminator's training procedure. As a result, such approaches often struggle with hyper-parameter tuning and convergence. We consider the slicing privacy mechanism that injects noise into random low-dimensional projections of the private data, and provide strong privacy guarantees for it. These noisy projections are used for training generative models. To enable optimizing generative models using this DP approach, we introduce the smoothed-sliced $f$-divergence and show it enjoys statistical consistency. Moreover, we present a kernel-based estimator for this divergence, circumventing the need for adversarial training. Extensive numerical experiments demonstrate that our approach can generate synthetic data of higher quality compared with baselines. Beyond performance improvement, our method, by sidestepping the need for noisy gradients, offers data scientists the flexibility to adjust generator architecture and hyper-parameters, run the optimization over any number of epochs, and even restart the optimization process -- all without incurring additional privacy costs.","url_abs":"https://arxiv.org/abs/2410.19941v1","url_pdf":"https://arxiv.org/pdf/2410.19941v1.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":[],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.19941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.19941"}},"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":"deterministic:regex_extraction","url":"https://github.com/ParkLabML/DP-MERF","reach":null}],"summary":{"ran_draft_wrong":6},"by_repo_kind":{"found_in_text":{"samples":6,"ran":6,"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":"6162d8bbe51fdd4a","entry":"data_label_embedding","repo":"ParkLabML/DP-MERF","repo_kind":"found_in_text","path":"code_balanced/rff_mmd_approx.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_balanced/rff_mmd_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6162d8bbe51fdd4a"}},{"code_sha256_prefix":"9c5facf6d71627c3","entry":"get_rff_mmd_loss","repo":"ParkLabML/DP-MERF","repo_kind":"found_in_text","path":"code_balanced/rff_mmd_approx.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_balanced/rff_mmd_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9c5facf6d71627c3"}},{"code_sha256_prefix":"95b98450b23bce47","entry":"rff_rahimi_recht","repo":"ParkLabML/DP-MERF","repo_kind":"found_in_text","path":"code_balanced/rff_mmd_approx.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_balanced/rff_mmd_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95b98450b23bce47"}},{"code_sha256_prefix":"e92ce76147ad7b7f","entry":"rff_sphere","repo":"ParkLabML/DP-MERF","repo_kind":"found_in_text","path":"code_balanced/rff_mmd_approx.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_balanced/rff_mmd_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e92ce76147ad7b7f"}},{"code_sha256_prefix":"d5bcd1501023ba31","entry":"weights_rahimi_recht","repo":"ParkLabML/DP-MERF","repo_kind":"found_in_text","path":"code_balanced/rff_mmd_approx.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_balanced/rff_mmd_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d5bcd1501023ba31"}},{"code_sha256_prefix":"b5f3bdb3acb38588","entry":"weights_sphere","repo":"ParkLabML/DP-MERF","repo_kind":"found_in_text","path":"code_balanced/rff_mmd_approx.py","file_url":"https://github.com/ParkLabML/DP-MERF/blob/HEAD/code_balanced/rff_mmd_approx.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b5f3bdb3acb38588"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}