arXiv subjects

Ayano Nakai-Kasai

Publications and source records attributed to Ayano Nakai-Kasai.

11 recordsLinked to original sources

arXiv2026

Federated Learning with Hypergradient-based Online Update of Aggregation Weights

Federated learning using mobile and Internet of Things devices requires not only the ability to handle heterogeneity of clients' data distributions but also high adaptability to varying communication environments. We propose FedHAW (Federated Learning with Hypergradient-based update of Aggregation Weights) that implements online updates of aggregation weights. FedHAW updates the aggregation weights by using hypergradient, the gradient of the objective function with respect to the weights, which can be calculated with low computational overhead. Simulation results show that the proposed method possesses high generalization performance in heterogeneous environments and high robustness to communication errors.

cs.LG↗

arXiv2026

Computationally Efficient Sparse Signal Recovery via Linear Sketching and Deep Unfolding

This paper provides a sparse signal recovery algorithm, DU-PSISTA (Deep Unfolded-Periodic Sketched Iterative Shrinkage-Thresholding Algorithm), which aims to balance computational efficiency and accuracy for recovering high-dimensional sparse signals, and a convergence analysis under sufficient conditions. DU-PSISTA introduces a random matrix projection known as sketching to reduce the dimensionality of gradient computations and periodically alternates between the standard ISTA and the sketched variant. This hybrid structure enables flexible control over the trade-off between accuracy and computational complexity through a pre-configurable period parameter. The algorithm includes many parameters to be tuned such as step sizes and thresholding factors so that we incorporate deep unfolding that optimizes the parameters through data-driven training, enabling the algorithm to adaptively improve convergence speed and performance. We show that the proposed method achieves a linear-type contraction to a neighborhood of the true sparse signal with properly selected parameters. The analysis provides an interpretation for the effectiveness of the hybrid structure to improve recovery accuracy. Numerical experiments confirm that our method achieves comparable recovery performance to conventional deep unfolded ISTA while reducing computational complexity, especially when the period parameter and sketch size are properly selected. The results are also consistent with the theoretical insights.

eess.SP↗

arXiv2026

Online Architecture Search for Compressed Sensing based on Hypergradient Descent

AS-ISTA (Architecture Searched-Iterative Shrinkage Thresholding Algorithm) and AS-FISTA (AS-Fast ISTA) are compressed sensing algorithms introducing structural parameters to ISTA and FISTA to enable architecture search within the iterative process. The structural parameters are determined using deep unfolding, but this approach requires training data and the large overhead of training time. In this paper, we propose HGD-AS-ISTA (Hypergradient Descent-AS-ISTA) and HGD-AS-FISTA that use hypergradient descent, which is an online hyperparameter optimization method, to determine the structural parameters. Experimental results show that the proposed method improves performance of the conventional ISTA/FISTA while avoiding the need for re-training when the environment changes.

eess.SP↗

arXiv2025

Multi-Output Gaussian Processes for Graph-Structured Data

Graph-structured data is a type of data to be obtained associated with a graph structure where vertices and edges describe some kind of data correlation. This paper proposes a regression method on graph-structured data, which is based on multi-output Gaussian processes (MOGP), to capture both the correlation between vertices and the correlation between associated data. The proposed formulation is built on the definition of MOGP. This allows it to be applied to a wide range of data configurations and scenarios. Moreover, it has high expressive capability due to its flexibility in kernel design. It includes existing methods of Gaussian processes for graph-structured data as special cases and is possible to remove restrictions on data configurations, model selection, and inference scenarios in the existing methods. The performance of extensions achievable by the proposed formulation is evaluated through computer experiments with synthetic and real data.

cs.LG↗

arXiv2024

Ordinary Differential Equation-based MIMO Signal Detection

The required signal processing rate in future wireless communication systems exceeds the performance of the latest electronics-based processors. Introduction of analog optical computation is one promising direction for energy-efficient processing. This paper considers a continuous-time minimum mean squared error detection for multiple-input multiple-output systems to realize signal detection using analog optical devices. The proposed method is formulated by an ordinary differential equation (ODE) and its performance at any continuous time can be theoretically analyzed. Deriving and analyzing the continuous-time system is a meaningful step to verifying the feasibility of analog-domain signal processing in the future systems. In addition, considering such an ODE brings byproducts to discrete-time detection algorithms, which can be a novel methodology of algorithm construction and analysis.

eess.SP↗

arXiv2023

Deep Unfolding-based Weighted Averaging for Federated Learning in Heterogeneous Environments

Federated learning is a collaborative model training method that iterates model updates by multiple clients and aggregation of the updates by a central server. Device and statistical heterogeneity of participating clients cause significant performance degradation so that an appropriate aggregation weight should be assigned to each client in the aggregation phase of the server. To adjust the aggregation weights, this paper employs deep unfolding, which is known as the parameter tuning method that leverages both learning capability using training data like deep learning and domain knowledge. This enables us to directly incorporate the heterogeneity of the environment of interest into the tuning of the aggregation weights. The proposed approach can be combined with various federated learning algorithms. The results of numerical experiments indicate that a higher test accuracy for unknown class-balanced data can be obtained with the proposed method than that with conventional heuristic weighting methods. The proposed method can handle large-scale learning models with the aid of pretrained models such that it can perform practical real-world tasks. Convergence rate of federated learning algorithms with the proposed method is also provided in this paper.

cs.LG↗

arXiv2023

Stochastic Dynamics of Noisy Average Consensus: Analysis and Optimization

A continuous-time average consensus system is a linear dynamical system defined over a graph, where each node has its own state value that evolves according to a simultaneous linear differential equation. A node is allowed to interact with neighboring nodes. Average consensus is a phenomenon that the all the state values converge to the average of the initial state values. In this paper, we assume that a node can communicate with neighboring nodes through an additive white Gaussian noise channel. We first formulate the noisy average consensus system by using a stochastic differential equation (SDE), which allows us to use the Euler-Maruyama method, a numerical technique for solving SDEs. By studying the stochastic behavior of the residual error of the Euler-Maruyama method, we arrive at the covariance evolution equation. The analysis of the residual error leads to a compact formula for mean squared error (MSE), which shows that the sum of the inverse eigenvalues of the Laplacian matrix is the most dominant factor influencing the MSE. Furthermore, we propose optimization problems aimed at minimizing the MSE at a given target time, and introduce a deep unfolding-based optimization method to solve these problems. The quality of the solution is validated by numerical experiments.

math.OC↗

arXiv2023

Gradient Flow Decoding for LDPC Codes

The power consumption of the integrated circuit is becoming a significant burden, particularly for large-scale signal processing tasks requiring high throughput. The decoding process of LDPC codes is such a heavy signal processing task that demands power efficiency and higher decoding throughput. A promising approach to reducing both power and latency of a decoding process is to use an analog circuit instead of a digital circuit. This paper investigates a continuous-time gradient flow-based approach for decoding LDPC codes, which employs a potential energy function similar to the objective function used in the gradient descent bit flipping (GDBF) algorithm. We experimentally demonstrate that the decoding performance of the gradient flow decoding is comparable to that of the multi-bit mode GDBF algorithm. Since an analog circuit of the gradient flow decoding requires only analog arithmetic operations and an integrator, future advancements in programmable analog integrated circuits may make practical implementation feasible.

cs.IT↗

arXiv2023

Ordinary Differential Equation-based Sparse Signal Recovery

This study investigates the use of continuous-time dynamical systems for sparse signal recovery. The proposed dynamical system is in the form of a nonlinear ordinary differential equation (ODE) derived from the gradient flow of the Lasso objective function. The sparse signal recovery process of this ODE-based approach is demonstrated by numerical simulations using the Euler method. The state of the continuous-time dynamical system eventually converges to the equilibrium point corresponding to the minimum of the objective function. To gain insight into the local convergence properties of the system, a linear approximation around the equilibrium point is applied, yielding a closed-form error evolution ODE. This analysis shows the behavior of convergence to the equilibrium point. In addition, a variational optimization problem is proposed to optimize a time-dependent regularization parameter in order to improve both convergence speed and solution quality. The deep unfolded-variational optimization method is introduced as a means of solving this optimization problem, and its effectiveness is validated through numerical experiments.

cs.IT↗

arXiv2022

MMSE Signal Detection for MIMO Systems based on Ordinary Differential Equation

Motivated by emerging technologies for energy efficient analog computing and continuous-time processing, this paper proposes continuous-time minimum mean squared error estimation for multiple-input multiple-output (MIMO) systems based on an ordinary differential equation. Mean squared error (MSE) is a principal detection performance measure of estimation methods for MIMO systems. We derive an analytical MSE formula that indicates the MSE at any time. The MSE of the proposed method depends on a regularization parameter which affects the convergence property of the MSE. Furthermore, we extend the proposed method by using a time-dependent regularization parameter to achieve better convergence performance. Numerical experiments indicated excellent agreement with the theoretical values and improvement in the convergence performance owing to the use of the time-dependent parameter.

cs.IT↗

arXiv2022

Precoder Design for Correlated Data Aggregation via Over-the-Air Computation in Sensor Networks

Over-the-air computation (AirComp) enables efficient wireless data aggregation in sensor networks by simultaneous processing of calculation and communication. This paper proposes a novel precoder design for AirComp that incorporates statistical properties of sensing data, spatial correlation and heterogeneous data correlation. The proposed design of the precoder requires no iterative processes so that it can be realized with low computational costs. Moreover, this method provides dimensionality reduction of sensing data to reduce communication costs per sensor. We evaluate performance of the proposed method in terms of various system parameters. The results show the superiority of the proposed method to conventional non-iterative methods in cases where there are a large number of sensors and where the number of receive antennas at the aggregator is less than that of the total transmit antennas at the sensors.

eess.SP↗