{"list":"other","total":66,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1711.05769","title":"PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning","created":"2017-11-15","cited_by_count":898},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2102.07078","title":"Exploiting Shared Representations for Personalized Federated Learning","created":"2021-02-14","cited_by_count":541},{"id":"2006.04088","title":"An Efficient Framework for Clustered Federated Learning","created":"2020-06-07","cited_by_count":511},{"id":"2103.00710","title":"Towards Personalized Federated Learning","created":"2021-03-01","cited_by_count":464},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"2002.10619","title":"Three Approaches for Personalization with Applications to Federated Learning","created":"2020-02-25","cited_by_count":325},{"id":"1712.06541","title":"Size-Independent Sample Complexity of Neural Networks","created":"2017-12-18","cited_by_count":290},{"id":"2006.14769","title":"Supermasks in Superposition","created":"2020-06-26","cited_by_count":227},{"id":"2109.04617","title":"Efficiently Identifying Task Groupings for Multi-Task Learning","created":"2021-09-10","cited_by_count":222},{"id":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"id":"1910.06562","title":"Compacting, Picking and Growing for Unforgetting Continual Learning","created":"2019-10-15","cited_by_count":207},{"id":"1505.06279","title":"The Benefit of Multitask Representation Learning","created":"2015-05-23","cited_by_count":195},{"id":"2006.11650","title":"On the Theory of Transfer Learning: The Importance of Task Diversity","created":"2020-06-20","cited_by_count":186},{"id":"1906.02717","title":"Adaptive Gradient-Based Meta-Learning Methods","created":"2019-06-06","cited_by_count":183},{"id":"1810.02032","title":"Gradient descent aligns the layers of deep linear networks","created":"2018-10-04","cited_by_count":182},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"2002.11684","title":"Provable Meta-Learning of Linear Representations","created":"2020-02-26","cited_by_count":161},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"1805.12076","title":"Towards Understanding the Role of Over-Parametrization in Generalization of Neural Networks","created":"2018-05-30","cited_by_count":142},{"id":"1711.01239","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","created":"2017-11-03","cited_by_count":126},{"id":"2005.00944","title":"Understanding and Improving Information Transfer in Multi-Task Learning","created":"2020-05-02","cited_by_count":114},{"id":"1910.13616","title":"Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulation","created":"2019-10-30","cited_by_count":103},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82},{"id":"1905.05301","title":"Hierarchically Structured Meta-learning","created":"2019-05-13","cited_by_count":68},{"id":"1902.10644","title":"Provable Guarantees for Gradient-Based Meta-Learning","created":"2019-02-27","cited_by_count":67},{"id":"2006.09486","title":"Convergence of Meta-Learning with Task-Specific Adaptation over Partial Parameters","created":"2020-06-16","cited_by_count":65},{"id":"1902.05522","title":"Superposition of many models into one","created":"2019-02-14","cited_by_count":64},{"id":"2106.03027","title":"Model Zoo: A Growing \"Brain\" That Learns Continually","created":"2021-06-06","cited_by_count":54},{"id":"2010.06531","title":"Impact of Representation Learning in Linear Bandits","created":"2020-10-13","cited_by_count":52},{"id":"2204.07689","title":"Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners","created":"2022-04-16","cited_by_count":51},{"id":"1903.12117","title":"Many Task Learning with Task Routing","created":"2019-03-28","cited_by_count":50},{"id":"2002.08936","title":"Meta-learning for mixed linear regression","created":"2020-02-20","cited_by_count":44},{"id":"2006.09702","title":"Robust Meta-learning for Mixed Linear Regression with Small Batches","created":"2020-06-17","cited_by_count":41},{"id":"1904.03292","title":"The Information Complexity of Learning Tasks, their Structure and their Distance","created":"2019-04-05","cited_by_count":36},{"id":"2106.15434","title":"Zoo-Tuning: Adaptive Transfer from a Zoo of Models","created":"2021-06-29","cited_by_count":35},{"id":"1903.09109","title":"A Principled Approach for Learning Task Similarity in Multitask Learning","created":"2019-03-21","cited_by_count":32},{"id":"2106.08053","title":"On the Power of Multitask Representation Learning in Linear MDP","created":"2021-06-15","cited_by_count":30},{"id":"2202.03483","title":"MAML and ANIL Provably Learn Representations","created":"2022-02-07","cited_by_count":30},{"id":"2206.05900","title":"Provable Benefit of Multitask Representation Learning in Reinforcement Learning","created":"2022-06-13","cited_by_count":29},{"id":"2006.15785","title":"A No-Free-Lunch Theorem for MultiTask Learning","created":"2020-06-29","cited_by_count":28},{"id":"2105.14095","title":"Weighted Training for Cross-Task Learning","created":"2021-05-28","cited_by_count":22},{"id":"2105.14989","title":"Representation Learning Beyond Linear Prediction Functions","created":"2021-05-31","cited_by_count":21},{"id":"2201.06142","title":"Towards Sample-efficient Overparameterized Meta-learning","created":"2022-01-16","cited_by_count":21},{"id":"2008.02447","title":"Functional Regularization for Representation Learning: A Unified Theoretical Perspective","created":"2020-08-06","cited_by_count":18},{"id":"2205.12755","title":"An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems","created":"2022-05-25","cited_by_count":16},{"id":"2203.02026","title":"Provable and Efficient Continual Representation Learning","created":"2022-03-03","cited_by_count":14},{"id":"1411.2635","title":"A chain rule for the expected suprema of Gaussian processes","created":"2014-11-10","cited_by_count":13},{"id":"2201.04805","title":"Non-Stationary Representation Learning in Sequential Linear Bandits","created":"2022-01-13","cited_by_count":13},{"id":"2205.10937","title":"muNet: Evolving Pretrained Deep Neural Networks into Scalable Auto-tuning Multitask Systems","created":"2022-05-22","cited_by_count":12},{"id":"2111.07126","title":"On the Statistical Benefits of Curriculum Learning","created":"2021-11-13","cited_by_count":10},{"id":"1802.01223","title":"Learning Compact Neural Networks with Regularization","created":"2018-02-05","cited_by_count":8},{"id":"2101.11201","title":"Similarity of Classification Tasks","created":"2021-01-27","cited_by_count":7},{"id":"1603.02185","title":"Distributed Multi-Task Learning with Shared Representation","created":"2016-03-07","cited_by_count":5},{"id":"2009.00387","title":"Boosting Share Routing for Multi-task Learning","created":"2020-09-01","cited_by_count":4},{"id":"2212.05191","title":"SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing","created":"2022-12-10","cited_by_count":3}],"next_cursor":null}