AN IMPROVED ANALYSIS OF TRAINING OVER-PARAMETERIZED DEEP NEURAL NETWORKS

von Zou, Difan
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 3 of 20 (2020)

A FINITE-TIME ANALYSIS OF Q-LEARNING WITH NEURAL NETWORK FUNCTION APPROXIMATION

von Xu, Pan
Veröffentlicht in International Conference on Machine Learning (37. : 2020 : Online) 37th International Conference on Machine Learning (ICML 2020) ; Part 14 of 15 (2021)

Proxy Convexity: A Unified Framework for the Analysis of Neural Networks Trained by Gradient Descent

von Frei, Spencer
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 10 of 36 (2022)

TIGHT SAMPLE COMPLEXITY OF LEARNING ONE-HIDDEN-LAYER CONVOLUTIONAL NEURAL

von Cao, Yuan
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 14 of 20 (2020)

Dimension-Free Complexity Bounds for High-Order Nonconvex Finite-Sum Optimization

von Zhou, Dongruo
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 33 of 33 (2023)

GENERALIZATION BOUNDS OF STOCHASTIC GRADIENT DESCENT FOR WIDE AND DEEP NEURAL NETWORKS

von Cao, Yuan
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 14 of 20 (2020)

Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs

von Zhou, Dongruo
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 47 of 50 (2023)

ON THE CONVERGENCE OF HAMILTONIAN MONTE CARLO WITH STOCHASTIC GRADIENTS

von ZOU, DIFAN
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 16 of 16 (2022)

PROVABLY EFFICIENT REINFORCEMENT LEARNING FOR DISCOUNTED MDPS WITH FEATURE MAPPING

von ZHOU, DONGRUO
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 16 of 16 (2022)

PROVABLE ROBUSTNESS OF ADVERSARIAL TRAINING FOR LEARNING HALFSPACES WITH NOISE

von ZOU, DIFAN
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 16 of 16 (2022)

Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs

von He, Jiafan
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 27 of 36 (2022)

STOCHASTIC GRADIENT HAMILTONIAN MONTE CARLO METHODS WITH RECURSIVE VARIANCE REDUCTION

von Zou, Difan
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 5 of 20 (2020)

Provably Efficient Reinforcement Learning with Linear Function Approximation under Adaptivity Constraints

von Wang, Tianhao
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 17 of 36 (2022)

Risk Bounds for Over-parameterized Maximum Margin Classification on Sub-Gaussian Mixtures

von Cao, Yuan
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 11 of 36 (2022)

AGNOSTIC LEARNING OF A SINGLE NEURON WITH GRADIENT DESCENT

von Frei, Spencer
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 7 of 27 (2021)

On the Sample Complexity of Learning Infinite-Horizon Discounted Linear Kernel MDPs

von Chen, Yuanzhou
Veröffentlicht in International Conference on Machine Learning (39. : 2022 : Baltimore, Md.; Online) International Conference on Machine Learning (ICML 2022) ; Part 4 of 33 (2023)

PROVABLE GENERALIZATION OF SGD-TRAINED NEURAL NETWORKS OF ANY WIDTH IN THE PRESENCE OF ADVERSARIAL LABEL NOISE

von FREI, SPENCER
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 5 of 16 (2022)

LOGARITHMIC REGRET FOR REINFORCEMENT LEARNING WITH LINEAR FUNCTION APPROXIMATION

von HE, JIAFAN
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 6 of 16 (2022)

FASTER CONVERGENCE OF STOCHASTIC GRADIENT LANGEVIN DYNAMICS FOR NON-LOG-CONCAVE SAMPLING

von Zou, Difan
Veröffentlicht in Conference on Uncertainty in Artificial Intelligence (37. : 2021 : Online) 37th Conference on Uncertainty in Artificial Intelligence (UAI 2021) ; Part 2 of 3 (2022)

Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation

von ZHANG, Weitong
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 3 of 36 (2022)