Taiji Suzuki

On Learnability via Gradient Method for Two-Layer ReLU Neural Networks\n in Teacher-Student Setting

2021 · arXiv (Cornell University)

Deep learning empirically achieves high performance in many applications, but\nits training dynamics has not been fully understood theoretically. In this\npaper, we explore theoretical analysis on training two-layer ReLU neural\nnetworks in a teacher-student regression model, in …

Convergence of mean-field Langevin dynamics: Time and space discretization, stochastic gradient, and variance reduction

2023 · arXiv (Cornell University)

The mean-field Langevin dynamics (MFLD) is a nonlinear generalization of the Langevin dynamics that incorporates a distribution-dependent drift, and it naturally arises from the optimization of two-layer neural networks via (noisy) gradient descent. Recent works …

On the Role of Label Noise in the Feature Learning Process

2025 · arXiv (Cornell University)

Deep learning with noisy labels presents significant challenges. In this work, we theoretically characterize the role of label noise from a feature learning perspective. Specifically, we consider a signal-noise data distribution, where each sample comprises …