{"url":"/method/pgm","slug":"pgm","name":"PGM","full_name":"Probability Guided Maxout","full_name_withheld":false,"description_markdown":"A regularization criterion that, differently from [dropout](https://paperswithcode.com/method/dropout) and its variants, is deterministic rather than random. It grounds on the empirical evidence that feature descriptors with larger L2-norm and highly-active nodes are strongly correlated to confident class predictions. Thus, the criterion guides towards dropping a percentage of the most active nodes of the descriptors, proportionally to the estimated class probability","description_state":"present","introduced_year":null,"introduced_by":{"title":null,"paper":null,"first_author":null,"n_authors":0,"url_abs":null,"archive_paper_url":null},"source":{"url":null,"title":null,"url_on_a_paper_host":false},"code_snippet_url":"https://github.com/clferrari/probability-guided-maxout","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Regularization","url":"/methods/category/regularization","pwc_aliases":[]}],"n_papers_tagged":63,"archive_num_papers":63,"papers_newest_first":[{"paper":"/paper/partition-generative-modeling-masked-modeling","title":"Partition Generative Modeling: Masked Modeling Without Masks","date":"2025-05-24","arxiv_id":"2505.18883","n_code_links":1,"syntology":{"ran":8,"of":14,"unverified":6,"pointer_only":0}},{"paper":null,"title":"Smooth optimization algorithms for global and locally low-rank regularizers","date":"2025-05-09","arxiv_id":"2505.06073","n_code_links":0,"syntology":null},{"paper":null,"title":"Knowledge-Aided Semantic Communication Leveraging Probabilistic Graphical Modeling","date":"2024-08-08","arxiv_id":"2408.04499","n_code_links":0,"syntology":null},{"paper":null,"title":"Model Predictive Simulation Using Structured Graphical Models and Transformers","date":"2024-06-28","arxiv_id":"2406.19635","n_code_links":0,"syntology":null},{"paper":null,"title":"Digital Twinning of a Pressurized Water Reactor Startup Operation and Partial Computational Offloading in In-network Computing-Assisted Multiaccess Edge Computing","date":"2024-06-24","arxiv_id":"2407.12011","n_code_links":0,"syntology":null},{"paper":null,"title":"A-I-RAVEN and I-RAVEN-Mesh: Two New Benchmarks for Abstract Visual Reasoning","date":"2024-06-16","arxiv_id":"2406.11061","n_code_links":0,"syntology":null},{"paper":null,"title":"Differentiable Proximal Graph Matching","date":"2024-05-26","arxiv_id":"2405.16479","n_code_links":0,"syntology":null},{"paper":"/paper/fast-pgm-fast-probabilistic-graphical-model","title":"Fast-PGM: Fast Probabilistic Graphical Model Learning and Inference","date":"2024-05-24","arxiv_id":"2405.15605","n_code_links":1,"syntology":null},{"paper":"/paper/prompt-customization-for-continual-learning","title":"Prompt Customization for Continual Learning","date":"2024-04-28","arxiv_id":"2404.18060","n_code_links":1,"syntology":null},{"paper":null,"title":"Solving the Clustering Reasoning Problems by Modeling a Deep-Learning-Based Probabilistic Model","date":"2024-03-05","arxiv_id":"2403.03173","n_code_links":0,"syntology":null},{"paper":"/paper/magic-benchmarking-large-language-model","title":"MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration","date":"2023-11-14","arxiv_id":"2311.08562","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":0}},{"paper":null,"title":"Assessment of Differentially Private Synthetic Data for Utility and Fairness in End-to-End Machine Learning Pipelines for Tabular Data","date":"2023-10-30","arxiv_id":"2310.19250","n_code_links":0,"syntology":null},{"paper":null,"title":"Approximate Implication for Probabilistic Graphical Models","date":"2023-10-21","arxiv_id":"2310.13942","n_code_links":0,"syntology":null},{"paper":null,"title":"Probabilistic Modeling of Human Teams to Infer False Beliefs","date":"2023-10-19","arxiv_id":"2310.12929","n_code_links":0,"syntology":null},{"paper":"/paper/delta-ai-local-objectives-for-amortized","title":"Delta-AI: Local objectives for amortized inference in sparse graphical models","date":"2023-10-03","arxiv_id":"2310.02423","n_code_links":1,"syntology":{"ran":3,"of":4,"unverified":1,"pointer_only":0}},{"paper":null,"title":"Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning","date":"2023-07-11","arxiv_id":"2307.05004","n_code_links":0,"syntology":null},{"paper":null,"title":"Approximate inference of marginals using the IBIA framework","date":"2023-06-01","arxiv_id":"2306.00335","n_code_links":0,"syntology":null},{"paper":"/paper/on-neural-networks-as-infinite-tree","title":"On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models","date":"2023-05-27","arxiv_id":"2305.17583","n_code_links":1,"syntology":{"ran":0,"of":7,"unverified":7,"pointer_only":0}},{"paper":null,"title":"Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models","date":"2023-03-23","arxiv_id":"2303.13472","n_code_links":0,"syntology":null},{"paper":"/paper/neural-graph-revealers","title":"Neural Graph Revealers","date":"2023-02-27","arxiv_id":"2302.13582","n_code_links":1,"syntology":null},{"paper":null,"title":"Structure Learning and Parameter Estimation for Graphical Models via Penalized Maximum Likelihood Methods","date":"2023-01-30","arxiv_id":"2301.13269","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-visible-infrared-person-re","title":"Unsupervised Visible-Infrared Person Re-Identification via Progressive Graph Matching and Alternate Learning","date":"2023-01-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training","date":"2022-10-30","arxiv_id":"2210.16892","n_code_links":0,"syntology":null},{"paper":null,"title":"Policy Gradient Methods for Designing Dynamic Output Feedback Controllers","date":"2022-10-18","arxiv_id":"2210.09735","n_code_links":0,"syntology":null},{"paper":null,"title":"Brain-inspired probabilistic generative model for double articulation analysis of spoken language","date":"2022-07-06","arxiv_id":"2207.02457","n_code_links":0,"syntology":null},{"paper":"/paper/savir-t-spatially-attentive-visual-reasoning","title":"SAViR-T: Spatially Attentive Visual Reasoning with Transformers","date":"2022-06-18","arxiv_id":"2206.09265","n_code_links":1,"syntology":null},{"paper":"/paper/effective-abstract-reasoning-with-dual-1","title":"Effective Abstract Reasoning with Dual-Contrast Network","date":"2022-05-27","arxiv_id":"2205.13720","n_code_links":1,"syntology":{"ran":5,"of":7,"unverified":2,"pointer_only":7}},{"paper":"/paper/emergent-communication-through-metropolis","title":"Emergent Communication through Metropolis-Hastings Naming Game with Deep Generative Models","date":"2022-05-24","arxiv_id":"2205.12392","n_code_links":1,"syntology":null},{"paper":"/paper/approximating-permutations-with-neural","title":"Approximating Permutations with Neural Network Components for Travelling Photographer Problem","date":"2022-04-30","arxiv_id":"2205.00242","n_code_links":0,"syntology":null},{"paper":null,"title":"Incremental Inference on Higher-Order Probabilistic Graphical Models Applied to Constraint Satisfaction Problems","date":"2022-02-25","arxiv_id":"2202.12916","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/decision-making","name":"Decision Making","papers":4},{"task":"/task/visual-reasoning","name":"Visual Reasoning","papers":4},{"task":"/task/reinforcement-learning","name":"Reinforcement Learning","papers":3},{"task":"/task/semantic-segmentation","name":"Semantic Segmentation","papers":3},{"task":"/task/bayesian-inference","name":"Bayesian Inference","papers":2},{"task":"/task/graph-matching","name":"Graph Matching","papers":2},{"task":"/task/language-modeling","name":"Language Modeling","papers":2},{"task":"/task/language-modelling","name":"Language Modelling","papers":2},{"task":"/task/minecraft","name":"Minecraft","papers":2},{"task":"/task/time-series","name":"Time Series Analysis","papers":2},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":2},{"task":"/task/ai-agent","name":"AI Agent","papers":1},{"task":"/task/activity-recognition","name":"Activity Recognition","papers":1},{"task":"/task/anatomy","name":"Anatomy","papers":1},{"task":"/task/attribute","name":"Attribute","papers":1},{"task":"/task/autonomous-vehicles","name":"Autonomous Vehicles","papers":1},{"task":"/task/machine-learning","name":"BIG-bench Machine Learning","papers":1},{"task":"/task/bayesian-optimisation","name":"Bayesian Optimisation","papers":1},{"task":"/task/benchmarking","name":"Benchmarking","papers":1},{"task":"/task/blocking","name":"Blocking","papers":1}],"tasks_shown":20,"n_tasks":72,"usage_by_year":[{"year":"2013","papers":3},{"year":"2014","papers":1},{"year":"2016","papers":3},{"year":"2017","papers":1},{"year":"2018","papers":3},{"year":"2019","papers":4},{"year":"2020","papers":9},{"year":"2021","papers":9},{"year":"2022","papers":8},{"year":"2023","papers":12},{"year":"2024","papers":8},{"year":"2025","papers":2}],"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/pgm"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}