1 citations · 1 across the 12 of their papers we have counts for
15 papers
Architecture-Aware Mixed Precision for Replica-Exchange Training of Geometry-Aware Neural Operators with Uncertainty Quantification
Ujin Jeon, Michael Penwarden, Wenqian Chen +1
Geometry-aware neural operators face substantial computational and memory demands when learning across complex physical domains. We introduce Architecture-Aware Mixed Precision (AA…
Finite-Sample Inference for Sparsely Permuted Linear Regression
Hirofumi Ota, Masaaki Imaizumi
We study a linear observation model with an unknown permutation called \textit{permuted/shuffled linear regression}, where responses and covariates are mismatched and the permutati…
Zero Generalization Error Theorem for Random Interpolators via Algebraic Geometry
Naoki Yoshida, Isao Ishikawa, Masaaki Imaizumi
We theoretically demonstrate that the generalization error of interpolators for machine learning models under teacher-student settings becomes 0 once the number of training samples…
Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning
Baiyuan Chen, Shinji Ito, Masaaki Imaizumi
Transformers have demonstrated exceptional performance across a wide range of domains. While their ability to perform reinforcement learning in-context has been established both th…
Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs
Mana Sakai, Ryo Karakida, Masaaki Imaizumi
In modern theoretical analyses of neural networks, the infinite-width limit is often invoked to justify Gaussian approximations of neuron preactivations (e.g., via neural network G…
High-dimensional Nonparametric Contextual Bandit Problem
Shogo Iwazaki, Junpei Komiyama, Masaaki Imaizumi
We consider the kernelized contextual bandit problem with a large feature space. This problem involves arms, and the goal of the forecaster is to maximize the cumulative reward…
Precise gradient descent training dynamics for finite-width multi-layer neural networks
Qiyang Han, Masaaki Imaizumi
In this paper, we provide the first precise distributional characterization of gradient descent iterates for general multi-layer neural networks under the canonical single-index re…
Minimax Rates of Estimation for Optimal Transport Map between Infinite-Dimensional Spaces
Donlapark Ponnoprat, Masaaki Imaizumi
We investigate the estimation of an optimal transport map between probability measures on an infinite-dimensional space and reveal its minimax optimal rate. Optimal transport theor…
Landscape computations for the edge of chaos in nonlinear dynamical systems
Motoki Nakata, Masaaki Imaizumi
We propose a stochastic sampling approach to identify stability boundaries in general dynamical systems. The global landscape of Lyapunov exponent in multi-dimensional parameter sp…
Approximation of Permutation Invariant Polynomials by Transformers: Efficient Construction in Column-Size
Naoki Takeshita, Masaaki Imaizumi
Transformers are a type of neural network that have demonstrated remarkable performance across various domains, particularly in natural language processing tasks. Motivated by this…
Universality of estimators for high-dimensional linear models with block dependency
Toshiki Tsuda, Masaaki Imaizumi
We study the universality property of estimators for high-dimensional linear models, which implies that the distribution of estimators is independent of whether the covariates foll…
Automatic Domain Adaptation by Transformers in In-Context Learning
Ryuichiro Hataya, Kota Matsui, Masaaki Imaizumi
Selecting or designing an appropriate domain adaptation algorithm for a given problem remains challenging. This paper presents a Transformer model that can provably approximate and…
High-Dimensional Single-Index Models: Link Estimation and Marginal Inference
Kazuma Sawaya, Yoshimasa Uematsu, Masaaki Imaizumi
This study proposes a novel method for estimation and hypothesis testing in high-dimensional single-index models. We address a common scenario where the sample size and the dimensi…
Effect of Weight Quantization on Learning Models by Typical Case Analysis
Shuhei Kashiwamura, Ayaka Sakata, Masaaki Imaizumi
This paper examines the quantization methods used in large-scale data analysis models and their hyperparameter choices. The recent surge in data analysis scale has significantly in…
Bayesian Analysis for Over-parameterized Linear Model via Effective Spectra
Tomoya Wakayama, Masaaki Imaizumi
In high-dimensional Bayesian statistics, various methods have been developed, including prior distributions that induce parameter sparsity to handle many parameters. Yet, these app…