{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/effectiveness-of-mpc-friendly-softmax","title":"Effectiveness of MPC-friendly Softmax Replacement","arxiv_id":"2011.11202","date":"2020-11-23","proceeding":null,"authors":["Marcel Keller","Ke Sun"],"abstract":"Softmax is widely used in deep learning to map some representation to a probability distribution. As it is based on exp/log functions that are relatively expensive in multi-party computation, Mohassel and Zhang (2017) proposed a simpler replacement based on ReLU to be used in secure computation. However, we could not reproduce the accuracy they reported for training on MNIST with three fully connected layers. Later works (e.g., Wagh et al., 2019 and 2021) used the softmax replacement not for computing the output probability distribution but for approximating the gradient in back-propagation. In this work, we analyze the two uses of the replacement and compare them to softmax, both in terms of accuracy and cost in multi-party computation. We found that the replacement only provides a significant speed-up for a one-layer network while it always reduces accuracy, sometimes significantly. Thus we conclude that its usefulness is limited and one should use the original softmax function instead.","url_abs":"https://arxiv.org/abs/2011.11202v2","url_pdf":"https://arxiv.org/pdf/2011.11202v2.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":"effectiveness-of-mpc-friendly-softmax","repo_url":"https://github.com/mkskeller/mnist-mpc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"effectiveness-of-mpc-friendly-softmax","repo_url":"https://github.com/csiro-mlai/deep-mpc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"effectiveness-of-mpc-friendly-softmax","repo_url":"https://github.com/csiro-mlai/mnist-mpc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2011.11202","atlas_url":"https://app.syntology.ai/?focus=2011.11202","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2011.11202"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2011.11202\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2011.11202"},"call":"get_concepts_for_paper(arxiv_id=\"2011.11202\")"}],"by_repo":[{"repo":"mkskeller/mnist-mpc","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"csiro-mlai/deep-mpc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"csiro-mlai/mnist-mpc","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"51789e31417e5aad5c88f26af5f2061e279f6de7f4283962515460a04eec17a1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}