arXiv subjects

Shenglong Zhou

Publications and source records attributed to Shenglong Zhou.

At least 37 records · Page 2Linked to original sources

arXiv2023

New Environment Adaptation with Few Shots for OFDM Receiver and mmWave Beamforming

Few-shot learning (FSL) enables adaptation to new tasks with only limited training data. In wireless communications, channel environments can vary drastically; therefore, FSL techniques can quickly adjust transceiver accordingly. In this paper, we develop two FSL frameworks that fit in wireless transceiver design. Both frameworks are base on optimization programs that can be solved by well-known algorithms like the inexact alternating direction method of multipliers (iADMM) and the inexact alternating direction method (iADM). As examples, we demonstrate how the proposed two FSL frameworks are used for the OFDM receiver and beamforming (BF) for the millimeter wave (mmWave) system. The numerical experiments confirm their desirable performance in both applications compared to other popular approaches, such as transfer learning (TL) and model-agnostic meta-learning.

cs.DC↗

arXiv2023

Federated Reinforcement Learning for Resource Allocation in V2X Networks

Resource allocation significantly impacts the performance of vehicle-to-everything (V2X) networks. Most existing algorithms for resource allocation are based on optimization or machine learning (e.g., reinforcement learning). In this paper, we explore resource allocation in a V2X network under the framework of federated reinforcement learning (FRL). On one hand, the usage of RL overcomes many challenges from the model-based optimization schemes. On the other hand, federated learning (FL) enables agents to deal with a number of practical issues, such as privacy, communication overhead, and exploration efficiency. The framework of FRL is then implemented by the inexact alternative direction method of multipliers (ADMM), where subproblems are solved approximately using policy gradients and accelerated by an adaptive step size calculated from their second moments. The developed algorithm, PASM, is proven to be convergent under mild conditions and has a nice numerical performance compared with some baseline methods for solving the resource allocation problem in a V2X network.

cs.LG↗

arXiv2023

Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning

The performance of existing supervised neuron segmentation methods is highly dependent on the number of accurate annotations, especially when applied to large scale electron microscopy (EM) data. By extracting semantic information from unlabeled data, self-supervised methods can improve the performance of downstream tasks, among which the mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images. However, due to the high degree of structural locality in EM images, as well as the existence of considerable noise, many voxels contain little discriminative information, making MIM pretraining inefficient on the neuron segmentation task. To overcome this challenge, we propose a decision-based MIM that utilizes reinforcement learning (RL) to automatically search for optimal image masking ratio and masking strategy. Due to the vast exploration space, using single-agent RL for voxel prediction is impractical. Therefore, we treat each input patch as an agent with a shared behavior policy, allowing for multi-agent collaboration. Furthermore, this multi-agent model can capture dependencies between voxels, which is beneficial for the downstream segmentation task. Experiments conducted on representative EM datasets demonstrate that our approach has a significant advantage over alternative self-supervised methods on the task of neuron segmentation. Code is available at \url{https://github.com/ydchen0806/dbMiM}.

cs.CV↗

arXiv2023

Federated Learning via Inexact ADMM

One of the crucial issues in federated learning is how to develop efficient optimization algorithms. Most of the current ones require full device participation and/or impose strong assumptions for convergence. Different from the widely-used gradient descent-based algorithms, in this paper, we develop an inexact alternating direction method of multipliers (ADMM), which is both computation- and communication-efficient, capable of combating the stragglers' effect, and convergent under mild conditions. Furthermore, it has a high numerical performance compared with several state-of-the-art algorithms for federated learning.

math.OC↗

arXiv2023

0/1 Deep Neural Networks via Block Coordinate Descent

The step function is one of the simplest and most natural activation functions for deep neural networks (DNNs). As it counts 1 for positive variables and 0 for others, its intrinsic characteristics (e.g., discontinuity and no viable information of subgradients) impede its development for several decades. Even if there is an impressive body of work on designing DNNs with continuous activation functions that can be deemed as surrogates of the step function, it is still in the possession of some advantageous properties, such as complete robustness to outliers and being capable of attaining the best learning-theoretic guarantee of predictive accuracy. Hence, in this paper, we aim to train DNNs with the step function used as an activation function (dubbed as 0/1 DNNs). We first reformulate 0/1 DNNs as an unconstrained optimization problem and then solve it by a block coordinate descend (BCD) method. Moreover, we acquire closed-form solutions for sub-problems of BCD as well as its convergence properties. Furthermore, we also integrate $\ell_{2,0}$-regularization into 0/1 DNN to accelerate the training process and compress the network scale. As a result, the proposed algorithm has a high performance on classifying MNIST and Fashion-MNIST datasets. As a result, the proposed algorithm has a desirable performance on classifying MNIST, FashionMNIST, Cifar10, and Cifar100 datasets.

cs.LG↗

arXiv2023

Generalized Lightness Adaptation with Channel Selective Normalization

Lightness adaptation is vital to the success of image processing to avoid unexpected visual deterioration, which covers multiple aspects, e.g., low-light image enhancement, image retouching, and inverse tone mapping. Existing methods typically work well on their trained lightness conditions but perform poorly in unknown ones due to their limited generalization ability. To address this limitation, we propose a novel generalized lightness adaptation algorithm that extends conventional normalization techniques through a channel filtering design, dubbed Channel Selective Normalization (CSNorm). The proposed CSNorm purposely normalizes the statistics of lightness-relevant channels and keeps other channels unchanged, so as to improve feature generalization and discrimination. To optimize CSNorm, we propose an alternating training strategy that effectively identifies lightness-relevant channels. The model equipped with our CSNorm only needs to be trained on one lightness condition and can be well generalized to unknown lightness conditions. Experimental results on multiple benchmark datasets demonstrate the effectiveness of CSNorm in enhancing the generalization ability for the existing lightness adaptation methods. Code is available at https://github.com/mdyao/CSNorm.

cs.CV↗

arXiv2023

Learning Fine-Grained Features for Pixel-wise Video Correspondences

Video analysis tasks rely heavily on identifying the pixels from different frames that correspond to the same visual target. To tackle this problem, recent studies have advocated feature learning methods that aim to learn distinctive representations to match the pixels, especially in a self-supervised fashion. Unfortunately, these methods have difficulties for tiny or even single-pixel visual targets. Pixel-wise video correspondences were traditionally related to optical flows, which however lead to deterministic correspondences and lack robustness on real-world videos. We address the problem of learning features for establishing pixel-wise correspondences. Motivated by optical flows as well as the self-supervised feature learning, we propose to use not only labeled synthetic videos but also unlabeled real-world videos for learning fine-grained representations in a holistic framework. We adopt an adversarial learning scheme to enhance the generalization ability of the learned features. Moreover, we design a coarse-to-fine framework to pursue high computational efficiency. Our experimental results on a series of correspondence-based tasks demonstrate that the proposed method outperforms state-of-the-art rivals in both accuracy and efficiency.

cs.CV↗

arXiv2022

Exact Penalty Method for Federated Learning

Federated learning has burgeoned recently in machine learning, giving rise to a variety of research topics. Popular optimization algorithms are based on the frameworks of the (stochastic) gradient descent methods or the alternating direction method of multipliers. In this paper, we deploy an exact penalty method to deal with federated learning and propose an algorithm, FedEPM, that enables to tackle four critical issues in federated learning: communication efficiency, computational complexity, stragglers' effect, and data privacy. Moreover, it is proven to be convergent and testified to have high numerical performance.

cs.LG↗

arXiv2022

Gradient Projection Newton Algorithm for Sparse Collaborative Learning Using Synthetic and Real Datasets of Applications

Exploring the relationship among multiple sets of data from one same group enables practitioners to make better decisions in medical science and engineering. In this paper, we propose a sparse collaborative learning (SCL) model, an optimization with double-sparsity constraints, to process the problem with two sets of data and a shared response variable. It is capable of dealing with the classification problems or the regression problems dependent on the discreteness of the response variable as well as exploring the relationship between two datasets simultaneously. To solve SCL, we first present some necessary and sufficient optimality conditions and then design a gradient projection Newton algorithm which has proven to converge to a unique locally optimal solution globally with at least a quadratic convergence rate. Finally, the reported numerical experiments illustrate the efficiency of the proposed method.

math.OC↗

arXiv2022

Gradient Projection Newton Pursuit for Sparsity Constrained Optimization

Hard-thresholding-based algorithms have seen various advantages for sparse optimization in controlling the sparsity and allowing for fast computation. Recent research shows that when techniques of the Newton-type methods are integrated, their numerical performance can be improved surprisingly. This paper develops a gradient projection Newton pursuit algorithm that mainly adopts the hard-thresholding operator and employs the Newton pursuit only when certain conditions are satisfied. The proposed algorithm is capable of converging globally and quadratically under the standard assumptions. When it comes to compressive sensing problems, the imposed assumptions are much weaker than those for many state-of-the-art algorithms. Moreover, extensive numerical experiments have demonstrated its high performance in comparison with the other leading solvers.

math.OC↗

arXiv2022

Test-time Batch Normalization

Deep neural networks often suffer the data distribution shift between training and testing, and the batch statistics are observed to reflect the shift. In this paper, targeting of alleviating distribution shift in test time, we revisit the batch normalization (BN) in the training process and reveals two key insights benefiting test-time optimization: $(i)$ preserving the same gradient backpropagation form as training, and $(ii)$ using dataset-level statistics for robust optimization and inference. Based on the two insights, we propose a novel test-time BN layer design, GpreBN, which is optimized during testing by minimizing Entropy loss. We verify the effectiveness of our method on two typical settings with distribution shift, i.e., domain generalization and robustness tasks. Our GpreBN significantly improves the test-time performance and achieves the state of the art results.

cs.LG↗

arXiv2022

Retinal Vessel Segmentation with Pixel-wise Adaptive Filters

Accurate retinal vessel segmentation is challenging because of the complex texture of retinal vessels and low imaging contrast. Previous methods generally refine segmentation results by cascading multiple deep networks, which are time-consuming and inefficient. In this paper, we propose two novel methods to address these challenges. First, we devise a light-weight module, named multi-scale residual similarity gathering (MRSG), to generate pixel-wise adaptive filters (PA-Filters). Different from cascading multiple deep networks, only one PA-Filter layer can improve the segmentation results. Second, we introduce a response cue erasing (RCE) strategy to enhance the segmentation accuracy. Experimental results on the DRIVE, CHASE_DB1, and STARE datasets demonstrate that our proposed method outperforms state-of-the-art methods while maintaining a compact structure. Code is available at https://github.com/Limingxing00/Retinal-Vessel-Segmentation-ISBI20222.

eess.IV↗

arXiv2022

Communication-Efficient ADMM-based Federated Learning

Federated learning has shown its advances over the last few years but is facing many challenges, such as how algorithms save communication resources, how they reduce computational costs, and whether they converge. To address these issues, this paper proposes exact and inexact ADMM-based federated learning. They are not only communication-efficient but also converge linearly under very mild conditions, such as convexity-free and irrelevance to data distributions. Moreover, the inexact version has low computational complexity, thereby alleviating the computational burdens significantly.

cs.LG↗

arXiv2021

Heaviside Set Constrained Optimization: Optimality and Newton Method

Data in the real world frequently involve binary status: truth or falsehood, positiveness or negativeness, similarity or dissimilarity, spam or non-spam, and to name a few, with applications into the regression, classification problems and so on. To characterize the binary status, one of the ideal functions is the Heaviside step function that returns one for one status and zero for the other. Hence, it is of dis-continuity. Because of this, the conventional approaches to deal with the binary status tremendously benefit from its continuous surrogates. In this paper, we target the Heaviside step function directly and study the Heaviside set constrained optimization: calculating the tangent and normal cones of the feasible set, establishing several first-order sufficient and necessary optimality conditions, as well as developing a Newton type method that enjoys locally quadratic convergence and excellent numerical performance.

math.OC↗

arXiv2021

Quadratic Convergence of Smoothing Newton's Method for 0/1 Loss Optimization

It has been widely recognized that the 0/1 loss function is one of the most natural choices for modelling classification errors, and it has a wide range of applications including support vector machines and 1-bit compressed sensing. Due to the combinatorial nature of the 0/1 loss function, methods based on convex relaxations or smoothing approximations have dominated the existing research and are often able to provide approximate solutions of good quality. However, those methods are not optimizing the 0/1 loss function directly and hence no optimality has been established for the original problem. This paper aims to study the optimality conditions of the 0/1 function minimization, and for the first time to develop Newton's method that directly optimizes the 0/1 function with a local quadratic convergence under reasonable conditions. Extensive numerical experiments demonstrate its superior performance as one would expect from Newton-type methods.ions. Extensive numerical experiments demonstrate its superior performance as one would expect from Newton-type methods.

math.OC↗

arXiv2021

Computing One-bit Compressive Sensing via Double-Sparsity Constrained Optimization

One-bit compressive sensing gains its popularity in signal processing and communications due to its low storage costs and low hardware complexity. However, it has been a challenging task to recover the signal only by exploiting the one-bit (the sign) information. In this paper, we appropriately formulate the one-bit compressive sensing into a double-sparsity constrained optimization problem. The first-order optimality conditions for this nonconvex and discontinuous problem are established via the newly introduced $τ$-stationarity, based on which, a gradient projection subspace pursuit (\texttt{GPSP}) algorithm is developed. It is proven that \texttt{GPSP} can converge globally and terminate within finite steps. Numerical experiments have demonstrated its excellent performance in terms of a high order of accuracy with a fast computational speed.

math.OC↗

arXiv2021

Accretionary Learning with Deep Neural Networks

One of the fundamental limitations of Deep Neural Networks (DNN) is its inability to acquire and accumulate new cognitive capabilities. When some new data appears, such as new object classes that are not in the prescribed set of objects being recognized, a conventional DNN would not be able to recognize them due to the fundamental formulation that it takes. The current solution is typically to re-design and re-learn the entire network, perhaps with a new configuration, from a newly expanded dataset to accommodate new knowledge. This process is quite different from that of a human learner. In this paper, we propose a new learning method named Accretionary Learning (AL) to emulate human learning, in that the set of objects to be recognized may not be pre-specified. The corresponding learning structure is modularized, which can dynamically expand to register and use new knowledge. During accretionary learning, the learning process does not require the system to be totally re-designed and re-trained as the set of objects grows in size. The proposed DNN structure does not forget previous knowledge when learning to recognize new data classes. We show that the new structure and the design methodology lead to a system that can grow to cope with increased cognitive complexity while providing stable and superior overall performance.

cs.LG↗

arXiv2021

An Extended Newton-type Algorithm for $\ell_2$-Regularized Sparse Logistic Regression and Its Efficiency for Classifying Large-scale Datasets

Sparse logistic regression, as an effective tool of classification, has been developed tremendously in recent two decades, from its origination the $\ell_1$-regularized version to the sparsity constrained models. This paper is carried out on the sparsity constrained logistic regression by the Newton method. We begin with establishing its first-order optimality condition associated with a $τ$-stationary point. This point can be equivalently interpreted as a system of equations which is then efficiently solved by the Newton method. The method has a considerably low computational complexity and enjoys global and quadratic convergence properties. Numerical experiments on random and real data demonstrate its superior performance when against seven state-of-the-art solvers.

math.OC↗