8 citations · 12 across the 7 of their papers we have counts for
7 papers
Block Coordinate Descent for Neural Networks Provably Finds Global Minima
Shunta Akiyama
In this paper, we consider a block coordinate descent (BCD) algorithm for training deep neural networks and provide a new global convergence guarantee under strictly monotonically…
Diffusion Models are Minimax Optimal Distribution Estimators
Kazusato Oko, Shunta Akiyama, Taiji Suzuki
While efficient distribution learning is no doubt behind the groundbreaking success of diffusion modeling, its theoretical guarantees are quite limited. In this paper, we provide t…
Versatile Single-Loop Method for Gradient Estimator: First and Second Order Optimality, and its Application to Federated Learning
Kazusato Oko, Shunta Akiyama, Tomoya Murata +1
While variance reduction methods have shown great success in solving large scale optimization problems, many of them suffer from accumulated errors and, therefore, should periodica…
Optimal design of lottery with cumulative prospect theory
Shunta Akiyama, Mitsuaki Obara, Yasushi Kawase
Lotteries are a prevalent form of gambling between a seller and buyers. Designing a lottery requires a model of how buyers make decisions when confronted with uncertain outcomes. C…
Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods
Shunta Akiyama, Taiji Suzuki
While deep learning has outperformed other methods for various tasks, theoretical frameworks that explain its reason have not been fully established. To address this issue, we inve…
On Learnability via Gradient Method for Two-Layer ReLU Neural Networks in Teacher-Student Setting
Shunta Akiyama, Taiji Suzuki
Deep learning empirically achieves high performance in many applications, but its training dynamics has not been fully understood theoretically. In this paper, we explore theoretic…
Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods
Taiji Suzuki, Shunta Akiyama
Establishing a theoretical analysis that explains why deep learning can outperform shallow learning such as kernel methods is one of the biggest issues in the deep learning literat…