{"total":197,"rows":[{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739,"area":null},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541,"area":null},{"id":"2306.04637","title":"Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection","created":"2023-06-07","cited_by_count":298,"area":null},{"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":"2106.04538","title":"What Makes Multi-modal Learning Better than Single (Provably)","created":"2021-06-08","cited_by_count":153,"area":null},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2112.15121","title":"On the Role of Neural Collapse in Transfer Learning","created":"2021-12-30","cited_by_count":100,"area":null},{"id":"2209.15240","title":"Universal Prompt Tuning for Graph Neural Networks","created":"2022-09-30","cited_by_count":100,"area":null},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84,"area":null},{"id":"2201.10787","title":"Variational Model Inversion Attacks","created":"2022-01-26","cited_by_count":75,"area":null},{"id":"2310.00035","title":"LoRA ensembles for large language model fine-tuning","created":"2023-09-29","cited_by_count":67,"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":"2106.03027","title":"Model Zoo: A Growing \"Brain\" That Learns Continually","created":"2021-06-06","cited_by_count":54,"area":null},{"id":"2110.02473","title":"The Power of Contrast for Feature Learning: A Theoretical Analysis","created":"2021-10-06","cited_by_count":53,"area":null},{"id":"2308.13985","title":"Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective","created":"2023-08-27","cited_by_count":51,"area":null},{"id":"2106.09017","title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","created":"2021-06-16","cited_by_count":50,"area":null},{"id":"2102.04132","title":"Near-optimal Representation Learning for Linear Bandits and Linear RL","created":"2021-02-08","cited_by_count":45,"area":null},{"id":"2106.02695","title":"Meta-Learning with Fewer Tasks through Task Interpolation","created":"2021-06-04","cited_by_count":45,"area":null},{"id":"2106.12108","title":"Near-Optimal Linear Regression under Distribution Shift","created":"2021-06-23","cited_by_count":42,"area":null},{"id":"2105.02221","title":"How Fine-Tuning Allows for Effective Meta-Learning","created":"2021-05-05","cited_by_count":41,"area":null},{"id":"2205.14571","title":"Provable Benefits of Representational Transfer in Reinforcement Learning","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2207.01603","title":"Invariant and Transportable Representations for Anti-Causal Domain Shifts","created":"2022-07-04","cited_by_count":37,"area":null},{"id":"2303.10720","title":"Trainable Projected Gradient Method for Robust Fine-tuning","created":"2023-03-19","cited_by_count":37,"area":null},{"id":"2408.12186","title":"Transformers are Minimax Optimal Nonparametric In-Context Learners","created":"2024-08-22","cited_by_count":37,"area":null},{"id":"2106.10189","title":"Adversarial Training Helps Transfer Learning via Better Representations","created":"2021-06-18","cited_by_count":36,"area":null},{"id":"2305.00316","title":"The Ideal Continual Learner: An Agent That Never Forgets","created":"2023-04-29","cited_by_count":35,"area":null},{"id":"2202.05250","title":"Adaptive and Robust Multi-Task Learning","created":"2022-02-10","cited_by_count":34,"area":null},{"id":"2202.12891","title":"Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effects","created":"2022-02-25","cited_by_count":32,"area":null},{"id":"2106.08053","title":"On the Power of Multitask Representation Learning in Linear MDP","created":"2021-06-15","cited_by_count":30,"area":null},{"id":"2206.05900","title":"Provable Benefit of Multitask Representation Learning in Reinforcement Learning","created":"2022-06-13","cited_by_count":29,"area":null},{"id":"2202.12230","title":"Sample Efficiency of Data Augmentation Consistency Regularization","created":"2022-02-24","cited_by_count":28,"area":null},{"id":"2205.09797","title":"Improving Multi-Task Generalization via Regularizing Spurious Correlation","created":"2022-05-19","cited_by_count":28,"area":null},{"id":"2303.17765","title":"Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness","created":"2023-03-31","cited_by_count":28,"area":null},{"id":"2212.00926","title":"Fair Generative Models via Transfer Learning","created":"2022-12-02","cited_by_count":27,"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":"2106.05418","title":"Probing transfer learning with a model of synthetic correlated datasets","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2309.12458","title":"A Theory of Multimodal Learning","created":"2023-09-21","cited_by_count":25,"area":null},{"id":"2106.06098","title":"Meta-Adaptive Nonlinear Control: Theory and Algorithms","created":"2021-06-11","cited_by_count":23,"area":null},{"id":"2105.14095","title":"Weighted Training for Cross-Task Learning","created":"2021-05-28","cited_by_count":22,"area":null},{"id":"2210.11075","title":"Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noise","created":"2022-10-20","cited_by_count":22,"area":null},{"id":"2303.01566","title":"On the Provable Advantage of Unsupervised Pretraining","created":"2023-03-02","cited_by_count":22,"area":null},{"id":"2105.14989","title":"Representation Learning Beyond Linear Prediction Functions","created":"2021-05-31","cited_by_count":21,"area":null},{"id":"2201.06142","title":"Towards Sample-efficient Overparameterized Meta-learning","created":"2022-01-16","cited_by_count":21,"area":null},{"id":"2303.14582","title":"Identification of Negative Transfers in Multitask Learning Using Surrogate Models","created":"2023-03-25","cited_by_count":20,"area":null},{"id":"2107.01641","title":"A Theoretical Analysis of Fine-tuning with Linear Teachers","created":"2021-07-04","cited_by_count":17,"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":"2502.01755","title":"Robust Federated Finetuning of LLMs via Alternating Optimization of LoRA","created":"2025-02-03","cited_by_count":17,"area":null},{"id":"2112.10955","title":"Joint Learning of Linear Time-Invariant Dynamical Systems","created":"2021-12-21","cited_by_count":16,"area":null},{"id":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16,"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":"2107.04518","title":"Optimal Gradient-based Algorithms for Non-concave Bandit Optimization","created":"2021-07-09","cited_by_count":15,"area":null},{"id":"2108.08770","title":"Learning-to-learn non-convex piecewise-Lipschitz functions","created":"2021-08-19","cited_by_count":15,"area":null},{"id":"2108.11018","title":"A Scaling Law for Synthetic-to-Real Transfer: How Much Is Your Pre-training Effective?","created":"2021-08-25","cited_by_count":15,"area":null},{"id":"2110.05076","title":"A Closer Look at Prototype Classifier for Few-shot Image Classification","created":"2021-10-11","cited_by_count":15,"area":null},{"id":"2110.14098","title":"Provable Lifelong Learning of Representations","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2201.11211","title":"Learning Mixtures of Linear Dynamical Systems","created":"2022-01-26","cited_by_count":15,"area":null},{"id":"2504.05426","title":"Survey on Algorithms for multi-index models","created":"2025-04-07","cited_by_count":15,"area":null},{"id":"2202.00911","title":"Active Multi-Task Representation Learning","created":"2022-02-02","cited_by_count":14,"area":null},{"id":"2203.02026","title":"Provable and Efficient Continual Representation Learning","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2210.13497","title":"Subspace Recovery from Heterogeneous Data with Non-isotropic Noise","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2303.10859","title":"Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs","created":"2023-03-20","cited_by_count":14,"area":null},{"id":"2305.12224","title":"On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training","created":"2023-05-20","cited_by_count":14,"area":null},{"id":"2310.02275","title":"MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data","created":"2023-09-29","cited_by_count":14,"area":null},{"id":"2201.04805","title":"Non-Stationary Representation Learning in Sequential Linear Bandits","created":"2022-01-13","cited_by_count":13,"area":null},{"id":"2308.04428","title":"Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data","created":"2023-08-08","cited_by_count":13,"area":null},{"id":"2309.05505","title":"Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning","created":"2023-09-11","cited_by_count":13,"area":null},{"id":"2406.11828","title":"Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations","created":"2024-06-17","cited_by_count":13,"area":null},{"id":"2106.15615","title":"A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning","created":"2021-06-29","cited_by_count":12,"area":null},{"id":"2205.15701","title":"Provable General Function Class Representation Learning in Multitask Bandits and MDPs","created":"2022-05-31","cited_by_count":12,"area":null},{"id":"2102.00940","title":"Meta-learning with negative learning rates","created":"2021-02-01","cited_by_count":11,"area":null},{"id":"2203.09308","title":"Few-Shot Learning on Graphs","created":"2022-03-17","cited_by_count":11,"area":null},{"id":"2203.14383","title":"Continual learning: a feature extraction formalization, an efficient algorithm, and fundamental obstructions","created":"2022-03-27","cited_by_count":11,"area":null},{"id":"2206.13482","title":"Understanding Benign Overfitting in Gradient-Based Meta Learning","created":"2022-06-27","cited_by_count":11,"area":null},{"id":"2302.01928","title":"Aligning Robot and Human Representations","created":"2023-02-03","cited_by_count":11,"area":null},{"id":"2312.13978","title":"Metalearning with Very Few Samples Per Task","created":"2023-12-21","cited_by_count":11,"area":null},{"id":"2404.01153","title":"TransFusion: Covariate-Shift Robust Transfer Learning for High-Dimensional Regression","created":"2024-04-01","cited_by_count":11,"area":null},{"id":"2111.07126","title":"On the Statistical Benefits of Curriculum Learning","created":"2021-11-13","cited_by_count":10,"area":null},{"id":"2102.11503","title":"Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution","created":"2021-02-23","cited_by_count":9,"area":null},{"id":"2106.15367","title":"MAML is a Noisy Contrastive Learner in Classification","created":"2021-06-29","cited_by_count":9,"area":null},{"id":"2107.02378","title":"Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks","created":"2021-07-06","cited_by_count":9,"area":null},{"id":"2107.06466","title":"Going Beyond Linear RL: Sample Efficient Neural Function Approximation","created":"2021-07-14","cited_by_count":9,"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":"2305.00152","title":"Limits of Model Selection under Transfer Learning","created":"2023-04-29","cited_by_count":9,"area":null},{"id":"2306.02556","title":"Improved Active Multi-Task Representation Learning via Lasso","created":"2023-06-05","cited_by_count":9,"area":null},{"id":"2306.10234","title":"Federated Few-shot Learning","created":"2023-06-17","cited_by_count":9,"area":null},{"id":"2111.03135","title":"Scaffolding Sets","created":"2021-11-04","cited_by_count":8,"area":null},{"id":"2206.01206","title":"Positive Unlabeled Contrastive Learning","created":"2022-06-01","cited_by_count":8,"area":null},{"id":"2302.11709","title":"Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes","created":"2023-02-23","cited_by_count":8,"area":null},{"id":"2303.09663","title":"Efficient Computation Sharing for Multi-Task Visual Scene Understanding","created":"2023-03-16","cited_by_count":8,"area":null},{"id":"2307.02295","title":"Meta-Learning Adversarial Bandit Algorithms","created":"2023-07-05","cited_by_count":8,"area":null},{"id":"2307.10870","title":"Nonlinear Meta-Learning Can Guarantee Faster Rates","created":"2023-07-20","cited_by_count":8,"area":null},{"id":"2401.09716","title":"HCVP: Leveraging Hierarchical Contrastive Visual Prompt for Domain Generalization","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2402.14966","title":"Smoothness Adaptive Hypothesis Transfer Learning","created":"2024-02-22","cited_by_count":8,"area":null},{"id":"2403.06871","title":"On the Generalization Ability of Unsupervised Pretraining","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2103.00137","title":"Meta-Learning with Graph Neural Networks: Methods and Applications","created":"2021-02-27","cited_by_count":7,"area":null},{"id":"2103.08463","title":"How to distribute data across tasks for meta-learning?","created":"2021-03-15","cited_by_count":7,"area":null},{"id":"2207.05205","title":"Scaling Novel Object Detection with Weakly Supervised Detection Transformers","created":"2022-07-11","cited_by_count":7,"area":null},{"id":"2212.12532","title":"Generalization Bounds for Few-Shot Transfer Learning with Pretrained Classifiers","created":"2022-12-23","cited_by_count":7,"area":null},{"id":"2307.02388","title":"Multi-Task Learning with Summary Statistics","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2406.04596","title":"Federated Representation Learning in the Under-Parameterized Regime","created":"2024-06-07","cited_by_count":7,"area":null}],"next_cursor":"100"}