{"url":"/method/amp","slug":"amp","name":"AMP","full_name":"Adversarial Model Perturbation","full_name_withheld":false,"description_markdown":"Based on the understanding that the flat local minima of the empirical risk cause the model to generalize better. Adversarial Model Perturbation (AMP) improves generalization via minimizing the **AMP loss**, which is obtained from the empirical risk by applying the **worst** norm-bounded perturbation on each point in the parameter space.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Regularizing Neural Networks via Adversarial Model Perturbation","paper":"/paper/regularizing-neural-networks-via-adversarial","first_author":"Yaowei Zheng","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/regularizing-neural-networks-via-adversarial"},"source":{"url":"https://arxiv.org/abs/2010.04925v4","title":"Regularizing Neural Networks via Adversarial Model Perturbation","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/hiyouga/AMP-Regularizer","code_snippet_url_on_a_code_host":true,"categories":[{"area":"General","area_id":"general","collection":"Optimization","url":"/methods/category/optimization","pwc_aliases":[]}],"n_papers_tagged":92,"archive_num_papers":92,"papers_newest_first":[{"paper":null,"title":"AmpLyze: A Deep Learning Model for Predicting the Hemolytic Concentration","date":"2025-07-10","arxiv_id":"2507.08162","n_code_links":0,"syntology":null},{"paper":null,"title":"GLAMP: An Approximate Message Passing Framework for Transfer Learning with Applications to Lasso-based Estimators","date":"2025-05-28","arxiv_id":"2505.22594","n_code_links":0,"syntology":null},{"paper":null,"title":"Graph Neural Network Aided Detection for the Multi-User Multi-Dimensional Index Modulated Uplink","date":"2025-05-27","arxiv_id":"2505.21343","n_code_links":0,"syntology":null},{"paper":null,"title":"Detailed Evaluation of Modern Machine Learning Approaches for Optic Plastics Sorting","date":"2025-05-22","arxiv_id":"2505.16513","n_code_links":0,"syntology":null},{"paper":null,"title":"Aliasing Reduction in Neural Amp Modeling by Smoothing Activations","date":"2025-05-07","arxiv_id":"2505.04082","n_code_links":0,"syntology":null},{"paper":"/paper/efficient-llms-with-amp-attention-heads-and","title":"Efficient LLMs with AMP: Attention Heads and MLP Pruning","date":"2025-04-29","arxiv_id":"2504.21174","n_code_links":2,"syntology":null},{"paper":null,"title":"Targeted AMP generation through controlled diffusion with efficient embeddings","date":"2025-04-24","arxiv_id":"2504.17247","n_code_links":0,"syntology":null},{"paper":null,"title":"Tensor Generalized Approximate Message Passing","date":"2025-03-25","arxiv_id":"2504.00008","n_code_links":0,"syntology":null},{"paper":"/paper/zo2-scalable-zeroth-order-fine-tuning-for","title":"ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory","date":"2025-03-16","arxiv_id":"2503.12668","n_code_links":1,"syntology":null},{"paper":null,"title":"Asymptotics of Non-Convex Generalized Linear Models in High-Dimensions: A proof of the replica formula","date":"2025-02-27","arxiv_id":"2502.20003","n_code_links":0,"syntology":null},{"paper":null,"title":"Noise-conditioned Energy-based Annealed Rewards (NEAR): A Generative Framework for Imitation Learning from Observation","date":"2025-01-24","arxiv_id":"2501.14856","n_code_links":0,"syntology":null},{"paper":"/paper/comprehensive-assessment-of-bert-based","title":"Comprehensive Assessment of BERT-Based Methods for Predicting Antimicrobial Peptides","date":"2024-12-24","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"SGAC: A Graph Neural Network Framework for Imbalanced and Structure-Aware AMP Classification","date":"2024-12-20","arxiv_id":"2412.16276","n_code_links":0,"syntology":null},{"paper":null,"title":"Unifying AMP Algorithms for Rotationally-Invariant Models","date":"2024-12-02","arxiv_id":"2412.01574","n_code_links":0,"syntology":null},{"paper":null,"title":"Fast, robust approximate message passing","date":"2024-11-05","arxiv_id":"2411.02764","n_code_links":0,"syntology":null},{"paper":"/paper/building-conformal-prediction-intervals-with","title":"Building Conformal Prediction Intervals with Approximate Message Passing","date":"2024-10-21","arxiv_id":"2410.16493","n_code_links":1,"syntology":null},{"paper":null,"title":"Deep Unfolded Approximate Message Passing for Quantitative Acoustic Microscopy Image Reconstruction","date":"2024-09-20","arxiv_id":"2409.13634","n_code_links":0,"syntology":null},{"paper":null,"title":"Unrolled denoising networks provably learn optimal Bayesian inference","date":"2024-09-19","arxiv_id":"2409.12947","n_code_links":0,"syntology":null},{"paper":"/paper/digital-semantic-communications-an","title":"Digital Semantic Communications: An Alternating Multi-Phase Training Strategy with Mask Attack","date":"2024-08-09","arxiv_id":"2408.04972","n_code_links":1,"syntology":null},{"paper":null,"title":"Distributed Memory Approximate Message Passing","date":"2024-07-25","arxiv_id":"2407.17727","n_code_links":0,"syntology":null},{"paper":"/paper/dataset-distillation-by-automatic-training","title":"Dataset Distillation by Automatic Training Trajectories","date":"2024-07-19","arxiv_id":"2407.14245","n_code_links":1,"syntology":{"ran":3,"of":5,"unverified":2,"pointer_only":5}},{"paper":null,"title":"Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions","date":"2024-07-03","arxiv_id":"2407.03522","n_code_links":0,"syntology":null},{"paper":"/paper/iampcn-a-deep-learning-approach-for","title":"iAMPCN: a deep-learning approach for identifying antimicrobial peptides and their functional activities","date":"2024-06-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"title":"MoFormer: Multi-objective Antimicrobial Peptide Generation Based on Conditional Transformer Joint Multi-modal Fusion Descriptor","date":"2024-06-03","arxiv_id":"2406.02610","n_code_links":0,"syntology":null},{"paper":null,"title":"Sparse Regression Codes for Non-coherent SIMO channels","date":"2024-05-16","arxiv_id":"2405.09915","n_code_links":0,"syntology":null},{"paper":null,"title":"HMAMP: Hypervolume-Driven Multi-Objective Antimicrobial Peptides Design","date":"2024-05-01","arxiv_id":"2405.00753","n_code_links":0,"syntology":null},{"paper":"/paper/ampcliff-quantitative-definition-and","title":"AMPCliff: quantitative definition and benchmarking of activity cliffs in antimicrobial peptides","date":"2024-04-15","arxiv_id":"2404.09738","n_code_links":1,"syntology":null},{"paper":null,"title":"Inferring Change Points in High-Dimensional Regression via Approximate Message Passing","date":"2024-04-11","arxiv_id":"2404.07864","n_code_links":0,"syntology":null},{"paper":null,"title":"AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving","date":"2024-03-20","arxiv_id":"2403.13331","n_code_links":0,"syntology":null},{"paper":null,"title":"Joint Activity-Delay Detection and Channel Estimation for Asynchronous Massive Random Access: A Free Probability Theory Approach","date":"2024-02-28","arxiv_id":"2402.17996","n_code_links":0,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/denoising","name":"Denoising","papers":7},{"task":"/task/compressed-sensing","name":"compressed sensing","papers":6},{"task":"/task/regression-1","name":"regression","papers":6},{"task":"/task/action-detection","name":"Action Detection","papers":4},{"task":"/task/activity-detection","name":"Activity Detection","papers":4},{"task":"/task/bayesian-inference","name":"Bayesian Inference","papers":4},{"task":"/task/parameter-estimation","name":"parameter estimation","papers":4},{"task":"/task/benchmarking","name":"Benchmarking","papers":3},{"task":"/task/graph-neural-network","name":"Graph Neural Network","papers":3},{"task":"/task/prediction","name":"Prediction","papers":3},{"task":"/task/protein-language-model","name":"Protein Language Model","papers":3},{"task":"/task/variational-inference","name":"Variational Inference","papers":3},{"task":"/task/model","name":"model","papers":3},{"task":"/task/clustering","name":"Clustering","papers":2},{"task":"/task/decoder","name":"Decoder","papers":2},{"task":"/task/distributed-computing","name":"Distributed Computing","papers":2},{"task":"/task/diversity","name":"Diversity","papers":2},{"task":"/task/drug-discovery","name":"Drug Discovery","papers":2},{"task":"/task/quantization","name":"Quantization","papers":2},{"task":"/task/uncertainty-quantification","name":"Uncertainty Quantification","papers":2}],"tasks_shown":20,"n_tasks":72,"usage_by_year":[{"year":"2020","papers":3},{"year":"2021","papers":14},{"year":"2022","papers":20},{"year":"2023","papers":22},{"year":"2024","papers":22},{"year":"2025","papers":11}],"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/amp"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}