{"total":21,"rows":[{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221,"area":null},{"id":"2106.06770","title":"What can linearized neural networks actually say about generalization?","created":"2021-06-12","cited_by_count":49,"area":null},{"id":"2102.00084","title":"A linearized framework and a new benchmark for model selection for fine-tuning","created":"2021-01-29","cited_by_count":41,"area":null},{"id":"2106.07880","title":"Scaling Neural Tangent Kernels via Sketching and Random Features","created":"2021-06-15","cited_by_count":32,"area":null},{"id":"2207.06343","title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2203.14577","title":"Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?","created":"2022-03-28","cited_by_count":18,"area":null},{"id":"2101.06640","title":"Estimating informativeness of samples with Smooth Unique Information","created":"2021-01-17","cited_by_count":15,"area":null},{"id":"2302.01428","title":"Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation","created":"2023-02-02","cited_by_count":14,"area":null},{"id":"2406.11129","title":"Neural Lineage","created":"2024-06-17","cited_by_count":9,"area":null},{"id":"2201.12423","title":"Benchmarking Resource Usage for Efficient Distributed Deep Learning","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2104.01351","title":"Random Features for the Neural Tangent Kernel","created":"2021-04-03","cited_by_count":6,"area":null},{"id":"2509.22832","title":"Efficient Fine-Grained GPU Performance Modeling for Distributed Deep Learning of LLM","created":"2025-09-26","cited_by_count":4,"area":null},{"id":"2206.11173","title":"Cold Posteriors through PAC-Bayes","created":"2022-06-22","cited_by_count":3,"area":null},{"id":"2309.05292","title":"The fine print on tempered posteriors","created":"2023-09-11","cited_by_count":3,"area":null},{"id":"2509.23592","title":"Toward a Holistic Approach to Continual Model Merging","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2410.21645","title":"Predicting the Encoding Error of SIRENs","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2212.09040","title":"The Underlying Correlated Dynamics in Neural Training","created":"2022-12-18","cited_by_count":1,"area":null},{"id":"2412.15519","title":"PreNeT: Leveraging Computational Features to Predict Deep Neural Network Training Time","created":"2024-12-20","cited_by_count":1,"area":null},{"id":"2405.10679","title":"Off-the-Shelf Neural Network Architectures for Forex Time Series Prediction come at a Cost","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2408.01331","title":"UnifiedNN: Efficient Neural Network Training on the Cloud","created":"2024-08-02","cited_by_count":0,"area":null},{"id":"2410.02980","title":"DecTrain: Deciding When to Train a Monocular Depth DNN Online","created":"2024-10-03","cited_by_count":0,"area":null}],"next_cursor":null}