{"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":"/method/logan","slug":"logan","name":"LOGAN","full_name":"LOGAN","full_name_withheld":false,"description_markdown":"**LOGAN** is a generative adversarial network that uses a latent optimization approach using [natural gradient descent](https://paperswithcode.com/method/natural-gradient-descent) (NGD). For the Fisher matrix in NGD, the authors use the empirical Fisher $F'$ with Tikhonov damping:\r\n\r\n$$ F' = g \\cdot g^{T} + \\beta{I} $$\r\n\r\nThey also use Euclidian Norm regularization for the optimization step.\r\n\r\nFor LOGAN's base architecture, [BigGAN-deep](https://paperswithcode.com/method/biggan-deep) is used with a few modifications: increasing the size of the latent source from $186$ to $256$, to compensate the randomness of the source lost\r\nwhen optimising $z$. 2, using the uniform distribution $U\\left(−1, 1\\right)$ instead of the standard normal distribution $N\\left(0, 1\\right)$ for $p\\left(z\\right)$ to be consistent with the clipping operation, using  leaky [ReLU](https://paperswithcode.com/method/relu) (with the slope of 0.2 for the negative part) instead of ReLU as the non-linearity for smoother gradient flow for $\\frac{\\delta{f}\\left(z\\right)}{\\delta{z}}$ .","description_state":"present","introduced_year":null,"introduced_by":{"title":"LOGAN: Latent Optimisation for Generative Adversarial Networks","paper":"/paper/logan-latent-optimisation-for-generative-1","first_author":"Yan Wu","n_authors":5,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/logan-latent-optimisation-for-generative-1"},"source":{"url":"https://arxiv.org/abs/1912.00953v2","title":"LOGAN: Latent Optimisation for Generative Adversarial Networks","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/Hosein47/LOGAN","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Adversarial Networks","url":"/methods/category/generative-adversarial-networks","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":6,"archive_num_papers":6,"papers_newest_first":[{"paper":null,"slug":"auditing-algorithmic-fairness-in-machine","title":"Auditing Algorithmic Fairness in Machine Learning for Health with Severity-Based LOGAN","date":"2022-11-16","arxiv_id":"2211.08742","n_code_links":0,"syntology":null},{"paper":null,"slug":"sinogram-denoise-based-on-generative","title":"Sinogram Denoise Based on Generative Adversarial Networks","date":"2021-08-09","arxiv_id":"2108.03903","n_code_links":0,"syntology":null},{"paper":null,"slug":"direct-reconstruction-of-linear-parametric","title":"Direct Reconstruction of Linear Parametric Images from Dynamic PET Using Nonlocal Deep Image Prior","date":"2021-06-18","arxiv_id":"2106.10359","n_code_links":0,"syntology":null},{"paper":"/paper/logan-local-group-bias-detection-by","slug":"logan-local-group-bias-detection-by","title":"LOGAN: Local Group Bias Detection by Clustering","date":"2020-10-06","arxiv_id":"2010.02867","n_code_links":1,"syntology":null},{"paper":null,"slug":"allpass-feedback-delay-networks","title":"Allpass Feedback Delay Networks","date":"2020-07-14","arxiv_id":"2007.07337","n_code_links":0,"syntology":null},{"paper":"/paper/logan-latent-optimisation-for-generative-1","slug":"logan-latent-optimisation-for-generative-1","title":"LOGAN: Latent Optimisation for Generative Adversarial Networks","date":"2019-12-02","arxiv_id":"1912.00953","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":2,"n_instrument":3,"unverified":3,"pointer_only":2,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":null}}],"papers_shown":6,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":6,"with_a_code_link":2,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":6,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":1,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":1,"papers_where_code_ran_first_page":"/method/logan/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/logan/papers/ran/1","json":"/method/logan/papers/ran/1.json","rows":1}],"tasks":[{"task":"/task/bias-detection","name":"Bias Detection","papers":2},{"task":"/task/clustering","name":"Clustering","papers":2},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":1},{"task":"/task/denoising","name":"Denoising","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":"/task/image-generation","name":"Image Generation","papers":1}],"tasks_shown":8,"n_tasks":8,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":2},{"year":"2021","papers":2},{"year":"2022","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/logan"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=LOGAN","read_at":"2026-10-05T00:58:43+00:00","query":"LOGAN","kind":"paper","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"1912.00953","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"unresolved_bearers","may_be_wrong_sense":true,"bearers_found":7,"served":null,"leading_other_bearer":{"arxiv_id":"1705.07663","title":"LOGAN: Membership Inference Attacks Against Generative Models","citations":107,"named_by":["title_prefix"],"bearer_name":"LOGAN: Membership Inference Attacks Against Generative Models","ask_with":"have('1705.07663')"},"n_other_bearers_listed":5,"note":"Nothing resolved to 'LOGAN' by name, but 7 thing(s) here DECLARE that name -- most cited: the paper 'LOGAN: Membership Inference Attacks Against Generative Models' (arXiv:1705.07663, 107 citations). That is a RESOLUTION miss, not a coverage gap: the corpus holds the name under a spelling the lookup did not reach. Ask again with an entry of `also_named`."},"name_competition_text":"Nothing resolved to this name, but 7 entries in Syntology's graph carry it; the most cited is the paper “LOGAN: Membership Inference Attacks Against Generative Models” (arXiv:1705.07663, 107 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach.","near_matches":[],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"7ea8415682a6fa262d87830364e89321ac6e47116e2e593f87e01bfabd27bb17","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}