GENERALIZATION BOUND OF GLOBALLY OPTIMAL NON-CONVEX NEURAL NETWORK TRAINING: TRANSPORTATION MAP ESTIMATION BY INFINITE DIMENSIONAL LANGEVIN DYNAMICS

von Suzuki, Taiji
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 23 of 27 (2021)

Improved Convergence Rate of Stochastic Gradient Langevin Dynamics with Variance Reduction and its Application to Optimization

von Kinoshita, Yuri
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 25 of 50 (2023)

BIAS-VARIANCE REDUCED LOCAL SGD FOR LESS HETEROGENEOUS FEDERATED LEARNING

von MURATA, TOMOYA
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 10 of 16 (2022)

OPTIMIZATION AND GENERALIZATION ANALYSIS OF TRANSDUCTION THROUGH GRADIENT BOOSTING AND APPLICATION TO MULTI-SCALE GRAPH NEURAL NETWORKS

von Oono, Kenta
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 23 of 27 (2021)

ON LEARNABILITY VIA GRADIENT METHOD FOR TWO-LAYER RELU NEURAL NETWORKS IN TEACHER-STUDENT SETTING

von AKIYAMA, SHUNTA
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 1 of 16 (2022)

Escaping Saddle Points with Bias-Variance Reduced Local Perturbed SGD for Communication Efficient Nonconvex Distributed Learning

von Murata, Tomoya
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 7 of 50 (2023)

Deep learning is adaptive to intrinsic dimensionality of model smoothness in anisotropic Besov space

von Suzuki, Taiji
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 5 of 36 (2022)

Game theoretic derivation of discrete distributions and discrete pricing formulas

von Takemura, Akimichi
Veröffentlicht 2005

Hara Takashi monogatari

von Suzuki, Teiji
Veröffentlicht 581983

Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis

von Nitanda, Atsushi
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 24 of 36 (2022)

QUANTITATIVE UNDERSTANDING OF VAE AS A NON-LINEARLY SCALED ISOMETRIC EMBEDDING

von NAKAGAWA, AKIRA
Veröffentlicht in International Conference on Machine Learning (38. : 2021 : Online) International Conference on Machine Learning (ICML 2021 ; Part 10 of 16 (2022)

Use of primal-dual technique in the network algorithm for two-way contingency tables

von Suzuki, Taiji
Veröffentlicht 2004

Density ratio estimation in machine learning

von Sugiyama, Masashi
Veröffentlicht 2012

Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime

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

High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation

von Ba, Jimmy
Veröffentlicht in NeurIPS (36. : 2022 : New Orleans, La.; Online) 36th Conference on Neural Information Processing Systems (NeurIPS 2022 ; Volume 49 of 50 (2023)

Differentiable Multiple Shooting Layers

von Massaroli, Stefano
Veröffentlicht in NeurIPS (35. : 2021 : Online) 35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 20 of 36 (2022)