Search Results for author:
Found 26 papers, 4 papers with code
Efficient Continual Learning through Frequency Decomposition and Integration
Inspired by this, we propose the Frequency Decomposition and Integration Network (FDINet), a novel framework that decomposes and integrates information across frequencies.
Hierarchical Multi-Graphs Learning for Robust Group Re-Identification
Group Re-identification (G-ReID) faces greater complexity than individual Re-identification (ReID) due to challenges like mutual occlusion, dynamic member interactions, and evolving group structures.
Asymptotic Analysis of Sample-averaged Q-learning
Incorporating statistical inference in RL algorithms is essential for understanding and managing uncertainty in model performance.
Continual Learning in the Frequency Domain
To our knowledge, this is the first study to utilize frequency domain features to enhance the performance and efficiency of CL training on edge devices.
Illumination Design for Joint Imaging and Wireless Power Transfer Systems
Our goal is to characterize the fundamental trade-off between imaging and wireless power transfer by optimizing the illumination signal.
Fast On-device LLM Inference with NPUs
On-device inference for Large Language Models (LLMs), driven by increasing privacy concerns and advancements of mobile-sized models, has gained significant interest.
Multi-Functional Beamforming Design for Integrated Sensing, Communication, and Computation
This system consists of a multi-antenna multi-functional base station (BS), an edge server, a target, and multiple singleantenna communication users.
Joint Power Allocation and Beamforming Design for Active IRS-Aided Directional Modulation Secure Systems
To meet the requirements of the network performance, a power allocation (PA) strategy is proposed and adopted in the system.
Sustainable Wireless Networks via Reconfigurable Intelligent Surfaces (RISs): Overview of the ETSI ISG RIS
Reconfigurable Intelligent Surfaces (RISs) are a novel form of ultra-low power devices that are capable to increase the communication data rates as well as the cell coverage in a cost- and energy-efficient way.
IOR: Inversed Objects Replay for Incremental Object Detection
Existing Incremental Object Detection (IOD) methods partially alleviate catastrophic forgetting when incrementally detecting new objects in real-world scenarios.
Large-Scale RIS Enabled Air-Ground Channels: Near-Field Modeling and Analysis
Then, we develop a beam domain channel model based on the proposed sub-array partition framework for large-scale RIS-enabled UAV-to-vehicle communication systems, which can be used to efficiently capture the sparse features in RIS-enabled UAV-to-vehicle channels in both near-field and far-field ranges.
3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis
Conversely, some GAN-based 2D portrait synthesis methods can achieve clear disentanglement of facial regions, but they cannot preserve view consistency due to a lack of 3D modeling abilities.
Cross-Domain Dual-Functional OFDM Waveform Design for Accurate Sensing/Positioning
For the communication-centric design, to maximize the achievable data rate, a fraction of REs are optimally allocated for communications according to prior knowledge of the communication channel.
Two Enhanced-rate Power Allocation Strategies for Active IRS-assisted Wireless Network
Subsequently, two high-performance PA strategies, enhanced multiple random initialization Newton's (EMRIN) and Taylor polynomial approximation (TPA), are proposed.
E2Net: Resource-Efficient Continual Learning with Elastic Expansion Network
In E2Net, we propose Representative Network Distillation to identify the representative core subnet by assessing parameter quantity and output similarity with the working network, distilling analogous subnets within the working network to mitigate reliance on rehearsal buffers and facilitating knowledge transfer across previous tasks.
Intelligent Reflecting Surface Aided Multi-Tier Hybrid Computing
Moreover, the results indicate that the DT assisted MEC system can precisely achieve the balance between local computing and task offloading since real-time system status can be obtained with the help of DT.
Statistical Inference with Stochastic Gradient Methods under $φ$-mixing Data
In this paper, we propose a mini-batch SGD estimator for statistical inference when the data is $\phi$-mixing.
Deep Feature Screening: Feature Selection for Ultra High-Dimensional Data via Deep Neural Networks
The applications of traditional statistical feature selection methods to high-dimension, low sample-size data often struggle and encounter challenging problems, such as overfitting, curse of dimensionality, computational infeasibility, and strong model assumption.
Calibrating multi-dimensional complex ODE from noisy data via deep neural networks
Our method is able to recover the ODE system without being subject to the curse of dimensionality and complicated ODE structure.
Online Statistical Inference for Parameters Estimation with Linear-Equality Constraints
Stochastic gradient descent (SGD) and projected stochastic gradient descent (PSGD) are scalable algorithms to compute model parameters in unconstrained and constrained optimization problems.
Distributed Adaptive Nearest Neighbor Classifier: Algorithm and Theory
When data is of an extraordinarily large size or physically stored in different locations, the distributed nearest neighbor (NN) classifier is an attractive tool for classification.
The Support and Resistance Line Method: An Analysis via Optimal Stopping
We study a mathematical model motivated by the support/resistance line method in technical analysis where the underlying stock price transitions between three states of nature in a path-dependent manner.
Domain-Invariant Speaker Vector Projection by Model-Agnostic Meta-Learning
Domain generalization remains a critical problem for speaker recognition, even with the state-of-the-art architectures based on deep neural nets.
Audio and Speech Processing
On Deep Instrumental Variables Estimate
The endogeneity issue is fundamentally important as many empirical applications may suffer from the omission of explanatory variables, measurement error, or simultaneous causality.
Optimal Nonparametric Inference via Deep Neural Network
Sufficient conditions on network architectures are provided such that the upper bounds become optimal (without log-sacrifice).
Nonparametric Inference under B-bits Quantization
Statistical inference based on lossy or incomplete samples is often needed in research areas such as signal/image processing, medical image storage, remote sensing, signal transmission.
