{"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/kernel-exponential-family-estimation-via","title":"Kernel Exponential Family Estimation via Doubly Dual Embedding","arxiv_id":"1811.02228","date":"2018-11-06","proceeding":null,"authors":["Bo Dai","Hanjun Dai","Arthur Gretton","Le Song","Dale Schuurmans","Niao He"],"abstract":"We investigate penalized maximum log-likelihood estimation for exponential\nfamily distributions whose natural parameter resides in a reproducing kernel\nHilbert space. Key to our approach is a novel technique, doubly dual embedding,\nthat avoids computation of the partition function. This technique also allows\nthe development of a flexible sampling strategy that amortizes the cost of\nMonte-Carlo sampling in the inference stage. The resulting estimator can be\neasily generalized to kernel conditional exponential families. We establish a\nconnection between kernel exponential family estimation and MMD-GANs, revealing\na new perspective for understanding GANs. Compared to the score matching based\nestimators, the proposed method improves both memory and time efficiency while\nenjoying stronger statistical properties, such as fully capturing smoothness in\nits statistical convergence rate while the score matching estimator appears to\nsaturate. Finally, we show that the proposed estimator empirically outperforms\nstate-of-the-art","url_abs":"http://arxiv.org/abs/1811.02228v3","url_pdf":"http://arxiv.org/pdf/1811.02228v3.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":"kernel-exponential-family-estimation-via","repo_url":"https://github.com/Hanjun-Dai/dde","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1811.02228","atlas_url":"https://app.syntology.ai/?focus=1811.02228","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}