{"total":23,"rows":[{"id":"2202.12172","title":"Overcoming a Theoretical Limitation of Self-Attention","created":"2022-02-24","cited_by_count":113,"area":null},{"id":"2211.10873","title":"Interpretable Scientific Discovery with Symbolic Regression: A Review","created":"2022-11-20","cited_by_count":105,"area":null},{"id":"2105.08306","title":"Sample Efficient Linear Meta-Learning by Alternating Minimization","created":"2021-05-18","cited_by_count":25,"area":null},{"id":"2305.13571","title":"Latent Positional Information is in the Self-Attention Variance of Transformer Language Models Without Positional Embeddings","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2103.06386","title":"Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning","created":"2021-03-10","cited_by_count":9,"area":null},{"id":"2103.08713","title":"Multi-task learning for virtual flow metering","created":"2021-03-15","cited_by_count":6,"area":null},{"id":"2206.12441","title":"Joint Representation Training in Sequential Tasks with Shared Structure","created":"2022-06-24","cited_by_count":5,"area":null},{"id":"2501.19067","title":"From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2404.18161","title":"IMEX-Reg: Implicit-Explicit Regularization in the Function Space for Continual Learning","created":"2024-04-28","cited_by_count":4,"area":null},{"id":"2502.13257","title":"Random Forest Autoencoders for Guided Representation Learning","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2508.09888","title":"Modern Neural Networks for Small Tabular Datasets: The New Default for Field-Scale Digital Soil Mapping?","created":"2025-08-13","cited_by_count":4,"area":null},{"id":"2507.11683","title":"PGT-I: Scaling Spatiotemporal GNNs with Memory-Efficient Distributed Training","created":"2025-07-15","cited_by_count":3,"area":null},{"id":"2405.10890","title":"A Versatile Framework for Analyzing Galaxy Image Data by Implanting Human-in-the-loop on a Large Vision Model","created":"2024-05-17","cited_by_count":2,"area":null},{"id":"2102.11807","title":"Data-driven analysis of central bank digital currency (CBDC) projects drivers","created":"2021-02-23","cited_by_count":0,"area":null},{"id":"2107.10763","title":"Learning to Transfer: A Foliated Theory","created":"2021-07-22","cited_by_count":0,"area":null},{"id":"2112.01401","title":"Newton methods based convolution neural networks using parallel processing","created":"2021-12-02","cited_by_count":0,"area":null},{"id":"2201.06344","title":"ExpertNet: A Symbiosis of Classification and Clustering","created":"2022-01-17","cited_by_count":0,"area":null},{"id":"2304.08883","title":"Parameterized Neural Networks for Finance","created":"2023-04-18","cited_by_count":0,"area":null},{"id":"2307.07575","title":"A Quantitative Approach to Predicting Representational Learning and Performance in Neural Networks","created":"2023-07-14","cited_by_count":0,"area":null},{"id":"2501.04067","title":"Explainable Time Series Prediction of Tyre Energy in Formula One Race Strategy","created":"2025-01-07","cited_by_count":0,"area":null},{"id":"2502.18167","title":"Sharper Risk Bound for Multi-Task Learning with Multi-Graph Dependent Data","created":"2025-02-25","cited_by_count":0,"area":null},{"id":"2505.15579","title":"Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2512.04912","title":"A result relating convex n-widths to covering numbers with some applications to neural networks","created":"2025-12-04","cited_by_count":0,"area":null}],"next_cursor":null}