{"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/probabilistic-discriminative-learning-with","title":"Probabilistic Discriminative Learning with Layered Graphical Models","arxiv_id":"1902.00057","date":"2019-01-31","proceeding":null,"authors":["Yuesong Shen","Tao Wu","Csaba Domokos","Daniel Cremers"],"abstract":"Probabilistic graphical models are traditionally known for their successes in\ngenerative modeling. In this work, we advocate layered graphical models (LGMs)\nfor probabilistic discriminative learning. To this end, we design LGMs in close\nanalogy to neural networks (NNs), that is, they have deep hierarchical\nstructures and convolutional or local connections between layers. Equipped with\ntensorized truncated variational inference, our LGMs can be efficiently trained\nvia backpropagation on mainstream deep learning frameworks such as PyTorch. To\ndeal with continuous valued inputs, we use a simple yet effective soft-clamping\nstrategy for efficient inference. Through extensive experiments on image\nclassification over MNIST and FashionMNIST datasets, we demonstrate that LGMs\nare capable of achieving competitive results comparable to NNs of similar\narchitectures, while preserving transparent probabilistic modeling.","url_abs":"http://arxiv.org/abs/1902.00057v1","url_pdf":"http://arxiv.org/pdf/1902.00057v1.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":"probabilistic-discriminative-learning-with","repo_url":"https://github.com/tum-vision/lgm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"variational-inference","task_name":"Variational Inference"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}