Learning-to-Learn Stochastic Gradient Descent with Biased Regularization

25 March 2019

Papers citing "Learning-to-Learn Stochastic Gradient Descent with Biased Regularization"

50 / 76 papers shown

Title
Meta-learning of shared linear representations beyond well-specified linear regression Mathieu Even Laurent Massoulié 254 0 0 31 Jan 2025
Imperative Learning: A Self-supervised Neuro-Symbolic Learning Framework for Robot AutonomyThe international journal of robotics research (IJRR), 2024 Chen Wang Kaiyi Ji Shaoshu Su Zhongqiang Ren Taimeng Fu ... Yi Du Qihang Li Yue Yang Xiao Lin Zhipeng Zhao SSL 372 18 0 28 Jan 2025
Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta LearningNeural Information Processing Systems (NeurIPS), 2024 Yiqin Lv Qi Wang Dong Liang Zheng Xie 191 5 0 30 Oct 2024
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum ComparatorNeural Information Processing Systems (NeurIPS), 2024 Siyuan Xu Minghui Zhu OffRL 148 2 0 13 Oct 2024
A Statistical Theory of Regularization-Based Continual Learning Xuyang Zhao Huiyuan Wang Weiran Huang Wei Lin 181 24 0 10 Jun 2024
A CMDP-within-online framework for Meta-Safe Reinforcement Learning Vanshaj Khattar Yuhao Ding Bilgehan Sel Javad Lavaei Ming Jin OffRL 145 18 0 26 May 2024
Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured trainingNeural Information Processing Systems (NeurIPS), 2024 Yanlai Yang Matt Jones Michael C. Mozer Mengye Ren 171 3 0 14 Mar 2024
More Flexible PAC-Bayesian Meta-Learning by Learning Learning Algorithms Hossein Zakerinia Amin Behjati Christoph H. Lampert FedML 162 9 0 06 Feb 2024
Leveraging Gradients for Unsupervised Accuracy Estimation under Distribution Shift Renchunzi Xie Ambroise Odonnat Vasilii Feofanov I. Redko Jianfeng Zhang Bo An UQCV 297 1 0 17 Jan 2024
Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System InstancesInternational Conference on Learning Representations (ICLR), 2023 M. Khodak Edmond Chow Maria-Florina Balcan Ameet Talwalkar 140 0 0 03 Oct 2023
A Simple Yet Effective Strategy to Robustify the Meta Learning ParadigmNeural Information Processing Systems (NeurIPS), 2023 Qi Wang Yiqin Lv Yanghe Feng Zheng Xie Jincai Huang 163 14 0 01 Oct 2023
Nonlinear Meta-Learning Can Guarantee Faster RatesSIAM Journal on Mathematics of Data Science (SIMODS), 2023 Dimitri Meunier Zhu Li Arthur Gretton Samory Kpotufe 304 7 0 20 Jul 2023
Hypothesis Transfer Learning with Surrogate Classification Losses: Generalization Bounds through Algorithmic StabilityInternational Conference on Machine Learning (ICML), 2023 Anass Aghbalou Guillaume Staerman 163 6 0 31 May 2023
Towards Constituting Mathematical Structures for Learning to OptimizeInternational Conference on Machine Learning (ICML), 2023 Jialin Liu Xiaohan Chen Zhangyang Wang W. Yin HanQin Cai 177 16 0 29 May 2023
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning Jun Shu Xiang Yuan Deyu Meng Zongben Xu 157 5 0 13 May 2023
Bayes meets Bernstein at the Meta Level: an Analysis of Fast Rates in Meta-Learning with PAC-Bayes Charles Riou Pierre Alquier Badr-Eddine Chérief-Abdellatif 173 10 0 23 Feb 2023
Improving Meta-Learning Generalization with Activation-Based Early-Stopping Simon Guiroy C. Pal Gonçalo Mordido Sarath Chandar 151 3 0 03 Aug 2022
EEML: Ensemble Embedded Meta-learningWISE (WISE), 2022 Geng Li Boyuan Ren Hongzhi Wang FedML 100 2 0 18 Jun 2022
Provable Generalization of Overparameterized Meta-learning Trained with SGDNeural Information Processing Systems (NeurIPS), 2022 Yu Huang Yingbin Liang Longbo Huang MLT 168 11 0 18 Jun 2022
A General framework for PAC-Bayes Bounds for Meta-Learning A. Rezazadeh AI4CE 155 4 0 11 Jun 2022
On Hypothesis Transfer Learning of Functional Linear ModelsInternational Conference on Machine Learning (ICML), 2022 Haotian Lin M. Reimherr 229 5 0 09 Jun 2022
Meta Representation Learning with Contextual Linear Bandits Leonardo Cella Karim Lounici Massimiliano Pontil 174 6 0 30 May 2022
Meta-Learning Adversarial Bandits Maria-Florina Balcan Keegan Harris M. Khodak Zhiwei Steven Wu FedML AAML 101 7 0 27 May 2022
Multi-Environment Meta-Learning in Stochastic Linear BanditsInternational Symposium on Information Theory (ISIT), 2022 Ahmadreza Moradipari Mohammad Ghavamzadeh Taha Rajabzadeh Christos Thrampoulidis M. Alizadeh 113 5 0 12 May 2022
Nearly Minimax Algorithms for Linear Bandits with Shared Representation Jiaqi Yang Qi Lei Jason D. Lee S. Du 155 16 0 29 Mar 2022
Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms Javad Azizi T. Duong Yasin Abbasi-Yadkori András Gyorgy Claire Vernade Mohammad Ghavamzadeh 278 8 0 25 Feb 2022
Trace norm regularization for multi-task learning with scarce dataAnnual Conference Computational Learning Theory (COLT), 2022 Etienne Boursier Mikhail Konobeev Nicolas Flammarion 124 11 0 14 Feb 2022
Adaptive and Robust Multi-Task LearningAnnals of Statistics (Ann. Stat.), 2022 Yaqi Duan Kaizheng Wang 299 35 0 10 Feb 2022
Meta Learning MDPs with Linear Transition ModelsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Robert Muller Aldo Pacchiano 165 4 0 21 Jan 2022
Learning Tensor Representations for Meta-LearningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2022 Samuel Deng Yilin Guo Daniel J. Hsu Debmalya Mandal FedML OOD SSL 140 2 0 18 Jan 2022
Generalization Bounds For Meta-Learning: An Information-Theoretic Analysis Qi Chen Changjian Shui M. Marchand 163 56 0 29 Sep 2021
Dynamic Regret Analysis for Online Meta-Learning Parvin Nazari E. Khorram CLL 114 5 0 29 Sep 2021
Learning-to-learn non-convex piecewise-Lipschitz functions Maria-Florina Balcan M. Khodak Dravyansh Sharma Ameet Talwalkar 110 18 0 19 Aug 2021
Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks Jun Shu Deyu Meng Zongben Xu 161 11 0 06 Jul 2021
On the Power of Multitask Representation Learning in Linear MDP Rui Lu Gao Huang S. Du 121 30 0 15 Jun 2021
Adaptive Clustering and Personalization in Multi-Agent Stochastic Linear Bandits A. Ghosh Abishek Sankararaman Kannan Ramchandran 148 4 0 15 Jun 2021
Meta-Adaptive Nonlinear Control: Theory and AlgorithmsNeural Information Processing Systems (NeurIPS), 2021 Guanya Shi Kamyar Azizzadenesheli Michael O'Connell Soon-Jo Chung Yisong Yue 242 45 0 11 Jun 2021
Conditional Meta-Learning of Linear RepresentationsNeural Information Processing Systems (NeurIPS), 2021 Giulia Denevi Massimiliano Pontil C. Ciliberto 159 13 0 30 Mar 2021
Meta-Learning with Graph Neural Networks: Methods and ApplicationsSIGKDD Explorations (SIGKDD Explor.), 2021 Debmalya Mandal Sourav Medya Brian Uzzi Charu C. Aggarwal AI4CE 221 24 0 27 Feb 2021
Meta-Learning with Neural Tangent KernelsInternational Conference on Learning Representations (ICLR), 2021 Jiuxiang Gu Zhenyi Wang Jiayi Xian Changyou Chen Jinhui Xu 97 21 0 07 Feb 2021
Meta-strategy for Learning Tuning Parameters with GuaranteesEntropy (Entropy), 2021 Dimitri Meunier Pierre Alquier 128 9 0 04 Feb 2021
On Data Efficiency of Meta-learningInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2021 Maruan Al-Shedivat Liam Li Eric Xing Ameet Talwalkar FedML 106 25 0 30 Jan 2021
Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and BeyondIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2021 Risheng Liu Jiaxin Gao Jin Zhang Deyu Meng Zhouchen Lin AI4CE 336 252 0 27 Jan 2021
An Information-Theoretic Analysis of the Impact of Task Similarity on Meta-LearningInternational Symposium on Information Theory (ISIT), 2021 Sharu Theresa Jose Osvaldo Simeone 181 13 0 21 Jan 2021
Provably Training Overparameterized Neural Network Classifiers with Non-convex ConstraintsElectronic Journal of Statistics (EJS), 2020 You-Lin Chen Zhaoran Wang Mladen Kolar 113 0 0 30 Dec 2020
Accelerating Distributed Online Meta-Learning via Multi-Agent Collaboration under Limited CommunicationACM Interational Symposium on Mobile Ad Hoc Networking and Computing (MobiHoc), 2020 Sen Lin M. Dedeoglu Junshan Zhang FedML 117 6 0 15 Dec 2020
Convergence Properties of Stochastic HypergradientsInternational Conference on Artificial Intelligence and Statistics (AISTATS), 2020 Riccardo Grazzi Massimiliano Pontil Saverio Salzo 235 28 0 13 Nov 2020
A Distribution-Dependent Analysis of Meta-LearningInternational Conference on Machine Learning (ICML), 2020 Mikhail Konobeev Ilja Kuzborskij Csaba Szepesvári OOD 176 6 0 31 Oct 2020
Meta-Learning with Adaptive HyperparametersNeural Information Processing Systems (NeurIPS), 2020 Sungyong Baik Myungsub Choi Janghoon Choi Heewon Kim Kyoung Mu Lee 239 145 0 31 Oct 2020
Theoretical bounds on estimation error for meta-learning James Lucas Mengye Ren Irene Kameni T. Pitassi R. Zemel 103 12 0 14 Oct 2020