{"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/discriminative-learning-of-sum-product","title":"Discriminative Learning of Sum-Product Networks","arxiv_id":null,"date":"2011-01-01","proceeding":null,"authors":["Robert Gens"],"abstract":"Sum-product networks are a new deep architecture that can perform fast, exact inference on high-treewidth models. Only generative methods for training SPNs\r\nhave been proposed to date. In this paper, we present the first discriminative\r\ntraining algorithms for SPNs, combining the high accuracy of the former with\r\nthe representational power and tractability of the latter. We show that the class\r\nof tractable discriminative SPNs is broader than the class of tractable generative\r\nones, and propose an efficient backpropagation-style algorithm for computing the\r\ngradient of the conditional log likelihood. Standard gradient descent suffers from\r\nthe diffusion problem, but networks with many layers can be learned reliably using “hard” gradient descent, where marginal inference is replaced by MPE inference (i.e., inferring the most probable state of the non-evidence variables). The\r\nresulting updates have a simple and intuitive form. We test discriminative SPNs\r\non standard image classification tasks. We obtain the best results to date on the\r\nCIFAR-10 dataset, using fewer features than prior methods with an SPN architecture that learns local image structure discriminatively. We also report the highest\r\npublished test accuracy on STL-10 even though we only use the labeled portion\r\nof the dataset.","url_abs":"https://www.sciencedirect.com/science/article/abs/pii/S0893608019303946","url_pdf":"http://papers.nips.cc/paper/4516-discriminative-learning-of-sum-product-networks.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":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-stl-10","task":"Image Classification","dataset":"STL-10","model":"Discriminative Learning of Sum-Product Networks","rank_in_archive_order":100,"of":117,"metrics":{"Percentage correct":"62.3"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}