{"total":26,"rows":[{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222,"area":null},{"id":"2205.13692","title":"FedAvg with Fine Tuning: Local Updates Lead to Representation Learning","created":"2022-05-27","cited_by_count":56,"area":null},{"id":"2211.10844","title":"Learning to Generate Image Embeddings with User-level Differential Privacy","created":"2022-11-20","cited_by_count":23,"area":null},{"id":"2206.08868","title":"A Conditional Gradient-based Method for Simple Bilevel Optimization with Convex Lower-level Problem","created":"2022-06-17","cited_by_count":17,"area":null},{"id":"2307.06887","title":"Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks","created":"2023-07-13","cited_by_count":16,"area":null},{"id":"2312.13978","title":"Metalearning with Very Few Samples Per Task","created":"2023-12-21","cited_by_count":11,"area":null},{"id":"2301.12095","title":"MetaNO: How to Transfer Your Knowledge on Learning Hidden Physics","created":"2023-01-28","cited_by_count":10,"area":null},{"id":"2206.09136","title":"Provable Generalization of Overparameterized Meta-learning Trained with SGD","created":"2022-06-18","cited_by_count":9,"area":null},{"id":"2311.01420","title":"Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data","created":"2023-11-02","cited_by_count":7,"area":null},{"id":"2209.03112","title":"Multitask Learning via Shared Features: Algorithms and Hardness","created":"2022-09-07","cited_by_count":5,"area":null},{"id":"2309.06588","title":"Convergence of Gradient-based MAML in LQR","created":"2023-09-12","cited_by_count":5,"area":null},{"id":"2306.01589","title":"Transfer learning for atomistic simulations using GNNs and kernel mean embeddings","created":"2023-06-02","cited_by_count":4,"area":null},{"id":"2501.09429","title":"ADAGE: A generic two-layer framework for adaptive agent based modelling","created":"2025-01-16","cited_by_count":4,"area":null},{"id":"2303.04338","title":"Provable Pathways: Learning Multiple Tasks over Multiple Paths","created":"2023-03-08","cited_by_count":3,"area":null},{"id":"2410.05690","title":"Long-Context Linear System Identification","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2501.11002","title":"pMixFed: Efficient Personalized Federated Learning through Adaptive Layer-Wise Mixup","created":"2025-01-19","cited_by_count":3,"area":null},{"id":"2306.08942","title":"Active Representation Learning for General Task Space with Applications in Robotics","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2409.02708","title":"Few-shot Multi-Task Learning of Linear Invariant Features with Meta Subspace Pursuit","created":"2024-09-04","cited_by_count":2,"area":null},{"id":"2410.22264","title":"Provable Meta-Learning with Low-Rank Adaptations","created":"2024-10-29","cited_by_count":2,"area":null},{"id":"2406.04639","title":"Cooperative Meta-Learning with Gradient Augmentation","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2510.19797","title":"Transformers are almost optimal metalearners for linear classification","created":"2025-10-22","cited_by_count":1,"area":null},{"id":"2601.20774","title":"When More Data Doesn't Help: Limits of Adaptation in Multitask Learning","created":"2026-01-28","cited_by_count":1,"area":null},{"id":"2303.01335","title":"First-order ANIL provably learns representations despite overparametrization","created":"2023-03-02","cited_by_count":0,"area":null},{"id":"2310.09471","title":"Plug-and-Play Feature Generation for Few-Shot Medical Image Classification","created":"2023-10-14","cited_by_count":0,"area":null},{"id":"2501.18975","title":"Meta-learning of shared linear representations beyond well-specified linear regression","created":"2025-01-31","cited_by_count":0,"area":null},{"id":"2606.02008","title":"Provable Data Scaling Law for Meta Learning via Complexity Minimization","created":"2026-06-01","cited_by_count":0,"area":null}],"next_cursor":null}