{"total":17,"rows":[{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"id":"2103.03014","title":"Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy","created":"2021-03-04","cited_by_count":62,"area":null},{"id":"2106.02266","title":"SAND-mask: An Enhanced Gradient Masking Strategy for the Discovery of Invariances in Domain Generalization","created":"2021-06-04","cited_by_count":50,"area":null},{"id":"2107.11442","title":"Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition","created":"2021-07-23","cited_by_count":33,"area":null},{"id":"2107.03860","title":"SSSE: Efficiently Erasing Samples from Trained Machine Learning Models","created":"2021-07-08","cited_by_count":28,"area":null},{"id":"2203.04248","title":"Dual Lottery Ticket Hypothesis","created":"2022-03-08","cited_by_count":27,"area":null},{"id":"2209.08554","title":"Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions","created":"2022-09-18","cited_by_count":20,"area":null},{"id":"2207.12534","title":"Trainability Preserving Neural Pruning","created":"2022-07-25","cited_by_count":16,"area":null},{"id":"2301.05219","title":"Why is the State of Neural Network Pruning so Confusing? On the Fairness, Comparison Setup, and Trainability in Network Pruning","created":"2023-01-12","cited_by_count":16,"area":null},{"id":"2102.07725","title":"Neural Network Compression for Noisy Storage Devices","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2412.00143","title":"Is Oracle Pruning the True Oracle?","created":"2024-11-28","cited_by_count":7,"area":null},{"id":"2202.01290","title":"Cyclical Pruning for Sparse Neural Networks","created":"2022-02-02","cited_by_count":6,"area":null},{"id":"2105.05916","title":"Dynamical Isometry: The Missing Ingredient for Neural Network Pruning","created":"2021-05-12","cited_by_count":2,"area":null},{"id":"2412.03035","title":"A Granger-Causal Perspective on Gradient Descent with Application to Pruning","created":"2024-12-04","cited_by_count":1,"area":null},{"id":"2201.06376","title":"UWC: Unit-wise Calibration Towards Rapid Network Compression","created":"2022-01-17","cited_by_count":0,"area":null},{"id":"2602.23219","title":"Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2605.06402","title":"SparseForge: Efficient Semi-Structured LLM Sparsification via Annealing of Hessian-Guided Soft-Mask","created":"2026-05-07","cited_by_count":0,"area":null}],"next_cursor":null}