Label Noise SGD Provably Prefers Flat Global Minimizers

von Damian, Alex
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 33 of 36 (2022)

On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias

von Safran, Itay
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 42 of 50 (2023)

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

von Nichani, Eshaan
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 19 of 50 (2023)

How Fine-Tuning Allows for Effective Meta-Learning

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

NEAR-OPTIMAL LINEAR REGRESSION UNDER DISTRIBUTION SHIFT

von LEI, QI
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 8 of 16 (2022)

Predicting What You Already Know Helps: Provable Self-Supervised Learning

von Lee, Jason D
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 1 of 36 (2022)

Implicit Bias of Gradient Descent on Reparametrized Models: On Equivalence to Mirror Descent

von Li, Zhiyuan
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 45 of 50 (2023)

NEURAL TEMPORAL-DIFFERENCE LEARNING CONVERGES TO GLOBAL OPTIMA

von Cai, Qi
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 15 of 20 (2020)

REGULARIZATION MATTERS: GENERALIZATION AND OPTIMIZATION OF NEURAL NETS V.S. THEIR INDUCED KERNEL

von Wei, Colin
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 13 of 20 (2020)

A THEORY OF LABEL PROPAGATION FOR SUBPOPULATION SHIFT

von CAI, TIANLE
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 2 of 16 (2022)

OPTIMAL TRANSPORT MAPPING VIA INPUT CONVEX NEURAL NETWORKS

von Makkuva, Ashok Vardhan
Veröffentlicht in International Conference on Machine Learning (37. : 2020 : Online) 37th International Conference on Machine Learning (ICML 2020) ; Part 9 of 15 (2021)

AGNOSTIC Q-LEARNING WITH FUNCTION APPROXIMATION IN DETERMINISTIC SYSTEMS: NEAR-OPTIMAL BOUNDS ON APPROXIMATION ERROR AND SAMPLE COMPLEXITY

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

CONVERGENCE OF META-LEARNING WITH TASK-SPECIFIC ADAPTATION OVER PARTIAL PARAMETERS

von Ji, Kaiyi
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 14 of 27 (2021)

Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems

von Uehara, Masatoshi
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 2 of 50 (2023)

BEYOND LAZY TRAINING FOR OVER-PARAMETERIZED TENSOR DECOMPOSITION

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

HOW TO CHARACTERIZE THE LANDSCAPE OF OVERPARAMETERIZED CONVOLUTIONAL NEURAL NETWORKS

von Gu, Yihong
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 5 of 27 (2021)

GENERALIZED LEVERAGE SCORE SAMPLING FOR NEURAL NETWORKS

von Lee, Jason D.
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 13 of 27 (2021)

From Gradient Flow on Population Loss to Learning with Stochastic Gradient Descent

von De Sa, Christopher M
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 40 of 50 (2023)

IMPLICIT BIAS IN DEEP LINEAR CLASSIFICATION: INITIALIZATION SCALE VS TRAINING ACCURACY

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

CONVERGENCE OF ADVERSARIAL TRAINING IN OVERPARAMETRIZED NEURAL NETWORKS

von Gao, Ruiqi
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 17 of 20 (2020)