{"list":"other","total":54,"rows":[{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1801.05039","title":"Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator","created":"2018-01-15","cited_by_count":250},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"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":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"1710.01688","title":"On the Sample Complexity of the Linear Quadratic Regulator","created":"2017-10-04","cited_by_count":159},{"id":"1802.08334","title":"Learning Without Mixing: Towards A Sharp Analysis of Linear System Identification","created":"2018-02-22","cited_by_count":158},{"id":"1906.04280","title":"Mean estimation and regression under heavy-tailed distributions--a survey","created":"2019-06-10","cited_by_count":136},{"id":"2001.09576","title":"Naive Exploration is Optimal for Online LQR","created":"2020-01-27","cited_by_count":116},{"id":"2012.08496","title":"Spectral Methods for Data Science: A Statistical Perspective","created":"2020-12-15","cited_by_count":112},{"id":"2006.12466","title":"Information Theoretic Regret Bounds for Online Nonlinear Control","created":"2020-06-22","cited_by_count":90},{"id":"1812.01251","title":"Near optimal finite time identification of arbitrary linear dynamical systems","created":"2018-12-04","cited_by_count":89},{"id":"2006.10277","title":"Active Learning for Nonlinear System Identification with Guarantees","created":"2020-06-18","cited_by_count":80},{"id":"1806.05722","title":"Non-asymptotic Identification of LTI Systems from a Single Trajectory","created":"2018-06-14","cited_by_count":78},{"id":"1810.11546","title":"Mobile Sensor Data Anonymization","created":"2018-10-26","cited_by_count":70},{"id":"2102.04939","title":"RL for Latent MDPs: Regret Guarantees and a Lower Bound","created":"2021-02-09","cited_by_count":70},{"id":"1812.08305","title":"Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems","created":"2018-12-20","cited_by_count":67},{"id":"1710.01852","title":"Finite Time Identification in Unstable Linear Systems","created":"2017-10-05","cited_by_count":66},{"id":"1309.6821","title":"Sample Complexity of Multi-task Reinforcement Learning","created":"2013-09-26","cited_by_count":58},{"id":"1902.00768","title":"Learning Linear Dynamical Systems with Semi-Parametric Least Squares","created":"2019-02-02","cited_by_count":58},{"id":"1806.07104","title":"Online Linear Quadratic Control","created":"2018-06-19","cited_by_count":56},{"id":"1912.08866","title":"Continuous Meta-Learning without Tasks","created":"2019-12-18","cited_by_count":50},{"id":"2107.02729","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","created":"2021-07-06","cited_by_count":48},{"id":"1706.03161","title":"Toeplitz Inverse Covariance-Based Clustering of Multivariate Time Series Data","created":"2017-06-10","cited_by_count":47},{"id":"2003.11227","title":"Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems","created":"2020-03-25","cited_by_count":46},{"id":"2004.14681","title":"Learning nonlinear dynamical systems from a single trajectory","created":"2020-04-30","cited_by_count":46},{"id":"2002.08936","title":"Meta-learning for mixed linear regression","created":"2020-02-20","cited_by_count":44},{"id":"2006.08714","title":"Latent Bandits Revisited","created":"2020-06-15","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":"1802.07895","title":"Learning Mixtures of Linear Regressions with Nearly Optimal Complexity","created":"2018-02-22","cited_by_count":37},{"id":"2012.07774","title":"Small Covers for Near-Zero Sets of Polynomials and Learning Latent Variable Models","created":"2020-12-14","cited_by_count":28},{"id":"1912.07629","title":"Learning Mixtures of Linear Regressions in Subexponential Time via Fourier Moments","created":"2019-12-16","cited_by_count":26},{"id":"2006.02601","title":"On the Minimax Optimality of the EM Algorithm for Learning Two-Component Mixed Linear Regression","created":"2020-06-04","cited_by_count":24},{"id":"1806.10749","title":"On Adaptive Linear-Quadratic Regulators","created":"2018-06-28","cited_by_count":21},{"id":"2010.03799","title":"Learning the Linear Quadratic Regulator from Nonlinear Observations","created":"2020-10-08","cited_by_count":21},{"id":"1903.10343","title":"Sample Complexity Lower Bounds for Linear System Identification","created":"2019-03-25","cited_by_count":20},{"id":"2110.13878","title":"Deep Explicit Duration Switching Models for Time Series","created":"2021-10-26","cited_by_count":17},{"id":"2011.09929","title":"Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback Systems","created":"2020-11-19","cited_by_count":16},{"id":"2112.10955","title":"Joint Learning of Linear Time-Invariant Dynamical Systems","created":"2021-12-21","cited_by_count":16},{"id":"1912.12309","title":"Sample Complexity of Kalman Filtering for Unknown Systems","created":"2019-12-27","cited_by_count":12},{"id":"2009.11282","title":"Learning Mixtures of Low-Rank Models","created":"2020-09-23","cited_by_count":11},{"id":"2007.00722","title":"Sequential Transfer in Reinforcement Learning with a Generative Model","created":"2020-07-01","cited_by_count":10},{"id":"2110.15263","title":"Coresets for Time Series Clustering","created":"2021-10-28","cited_by_count":8},{"id":"2106.07537","title":"A Wasserstein Minimax Framework for Mixed Linear Regression","created":"2021-06-14","cited_by_count":7},{"id":"2006.16406","title":"Recovery of Sparse Signals from a Mixture of Linear Samples","created":"2020-06-29","cited_by_count":6},{"id":"2111.06395","title":"Kalman Filtering with Adversarial Corruptions","created":"2021-11-11","cited_by_count":6},{"id":"1910.07732","title":"Event-triggered Learning for Linear Quadratic Control","created":"2019-10-17","cited_by_count":4},{"id":"2009.12783","title":"Machine Learning in Event-Triggered Control: Recent Advances and Open Issues","created":"2020-09-27","cited_by_count":4},{"id":"2011.04970","title":"A Q-learning algorithm for discrete-time linear-quadratic control with random parameters of unknown distribution: convergence and stabilization","created":"2020-11-10","cited_by_count":3},{"id":"2104.14134","title":"Stable Online Control of Linear Time-Varying Systems","created":"2021-04-29","cited_by_count":3},{"id":"2110.14011","title":"Cluster-and-Conquer: A Framework For Time-Series Forecasting","created":"2021-10-26","cited_by_count":1}],"next_cursor":null}