Learning Theory

On the Linear Convergence of Policy Gradient Methods for Finite MDPs AISTATS 2021 On the Minimal Error of Empirical Risk Minimization COLT 2021 On the Minimax Optimality of the EM Algorithm for Learning Two-Component Mixed Linear Regression AISTATS 2021 On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization IJCAI 2021 On the number of linear functions composing deep neural network: Towards a refined definition of neural networks complexity AISTATS 2021 On the Optimality of Batch Policy Optimization Algorithms ICML 2021 On the Parameterized Complexity of Polytree Learning IJCAI 2021 On the Power of Differentiable Learning versus PAC and SQ Learning NeurIPS 2021 On the Predictability of Pruning Across Scales ICML 2021 On the proliferation of support vectors in high dimensions AISTATS 2021 On the Provable Generalization of Recurrent Neural Networks NeurIPS 2021 On the Random Conjugate Kernel and Neural Tangent Kernel ICML 2021 On the Representation of Solutions to Elliptic PDEs in Barron Spaces NeurIPS 2021 On the Representation Power of Set Pooling Networks NeurIPS 2021 On the Role of Optimization in Double Descent: A Least Squares Study NeurIPS 2021 On the Sample Complexity of Learning under Geometric Stability NeurIPS 2021 On the Sample Complexity of Privately Learning Axis-Aligned Rectangles NeurIPS 2021 On the Stability of Random Matrix Product with Markovian Noise: Application to Linear Stochastic Approximation and TD Learning COLT 2021 On the Suboptimality of Thompson Sampling in High Dimensions NeurIPS 2021 On the Theory of Implicit Deep Learning: Global Convergence with Implicit Layers ICLR 2021 On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift JMLR 2021 On the Theory of Reinforcement Learning with Once-per-Episode Feedback NeurIPS 2021 On the Transferability of Minimal Prediction Preserving Inputs in Question Answering NAACL 2021 On the Universality of the Double Descent Peak in Ridgeless Regression ICLR 2021 On the Validity of Modeling SGD with Stochastic Differential Equations (SDEs) NeurIPS 2021