13 citations · 23 across the 13 of their papers we have counts for
15 papers
Symmetry-quotient Flatness and Generalization
Taiki Miyagawa
This paper develops a theorem-level pipeline in symmetry-quotient settings: quotient linear stability implies quotient flatness, quotient flatness implies input smoothness, and inp…
Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
Taiki Miyagawa, Akinori F. Ebihara
We propose non-parametric estimators for the average run length (ARL) and average detection delay (ADD) in quickest changepoint detection (QCD) under finite and irregular sequence…
Differentially Private Synthetic Text Generation for Retrieval-Augmented Generation (RAG)
Junki Mori, Kazuya Kakizaki, Taiki Miyagawa +1
Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by grounding them in external knowledge. However, its application in sensitive domains is limited by priv…
Rethinking the Backbone in Class Imbalanced Federated Source Free Domain Adaptation: The Utility of Vision Foundation Models
Kosuke Kihara, Junki Mori, Taiki Miyagawa +1
Federated Learning (FL) offers a framework for training models collaboratively while preserving data privacy of each client. Recently, research has focused on Federated Source-Free…
Robust Deepfake Detection for Electronic Know Your Customer Systems Using Registered Images
Takuma Amada, Kazuya Kakizaki, Taiki Miyagawa +3
In this paper, we present a deepfake detection algorithm specifically designed for electronic Know Your Customer (eKYC) systems. To ensure the reliability of eKYC systems against d…
Learning the Optimal Stopping for Early Classification within Finite Horizons via Sequential Probability Ratio Test
Akinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai +1
Time-sensitive machine learning benefits from Sequential Probability Ratio Test (SPRT), which provides an optimal stopping time for early classification of time series. However, in…
Federated Source-free Domain Adaptation for Classification: Weighted Cluster Aggregation for Unlabeled Data
Junki Mori, Kosuke Kihara, Taiki Miyagawa +3
Federated learning (FL) commonly assumes that the server or some clients have labeled data, which is often impractical due to annotation costs and privacy concerns. Addressing this…
Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset
Hideyuki Oiso, Yuto Matsunaga, Kazuya Kakizaki +1
We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) hig…
Multi-Object Tracking as Attention Mechanism
Hiroshi Fukui, Taiki Miyagawa, Yusuke Morishita
We propose a conceptually simple and thus fast multi-object tracking (MOT) model that does not require any attached modules, such as the Kalman filter, Hungarian algorithm, transfo…
Toward Asymptotic Optimality: Sequential Unsupervised Regression of Density Ratio for Early Classification
Akinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai +1
Theoretically-inspired sequential density ratio estimation (SDRE) algorithms are proposed for the early classification of time series. Conventional SDRE algorithms can fail to esti…
Toward Equation of Motion for Deep Neural Networks: Continuous-time Gradient Descent and Discretization Error Analysis
Taiki Miyagawa
We derive and solve an ``Equation of Motion'' (EoM) for deep neural networks (DNNs), a differential equation that precisely describes the discrete learning dynamics of DNNs. Differ…
Convolutional Neural Networks for Time-dependent Classification of Variable-length Time Series
Azusa Sawada, Taiki Miyagawa, Akinori F. Ebihara +2
Time series data are often obtained only within a limited time range due to interruptions during observation process. To classify such partial time series, we need to account for 1…
The Power of Log-Sum-Exp: Sequential Density Ratio Matrix Estimation for Speed-Accuracy Optimization
Taiki Miyagawa, Akinori F. Ebihara
We propose a model for multiclass classification of time series to make a prediction as early and as accurate as possible. The matrix sequential probability ratio test (MSPRT) is k…
Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy
Akinori F. Ebihara, Taiki Miyagawa, Kazuyuki Sakurai +1
Classifying sequential data as early and as accurately as possible is a challenging yet critical problem, especially when a sampling cost is high. One algorithm that achieves this…
Double-Trace Deformations and Entanglement Entropy in AdS
Taiki Miyagawa, Noburo Shiba, Tadashi Takayanagi
We compute the bulk entanglement entropy of a massive scalar field in a Poincare AdS with the Dirichlet and Neumann boundary condition when we trace out a half space. Moreover, by…