Infrared imaging has emerged as a robust solution for urban object detection under low-light and adverse weather conditions, offering significant advantages over traditional visible-light cameras. However, challenges such as class imbalance, thermal noise, and computational constraints can significantly hinder model performance in practical settings. To address these issues, we evaluate multiple YOLO variants on the FLIR ADAS V2 dataset, ultimately selecting YOLOv8 as our baseline due to its balanced accuracy and efficiency. Building on this foundation, we present MS-YOLO (MobileNetv4 and SlideLoss based on YOLO), which replaces YOLOv8’s CSPDarknet backbone with the more efficient MobileNetV4, reducing computational overhead by 1.5% while sustaining high accuracy. In addition, we introduce SlideLoss, a novel loss function that dynamically emphasizes under-represented and occluded samples, boosting precision without sacrificing recall. Experiments on the FLIR ADAS V2 benchmark show that MS-YOLO attains competitive mAP and superior precision while operating at only 6.7 GFLOPs. These results demonstrate that MS-YOLO effectively addresses the dual challenge of maintaining high detection quality while minimizing computational costs, making it well-suited for real-time edge deployment in urban environments.

Most multi-agent reinforcement learning approaches adopt two types of policy optimization methods that either update policy simultaneously or sequentially. Simultaneously updating policies of all agents introduces non-stationarity problem. Although sequentially updating policies agent-by-agent in an appropriate order improves policy performance, it is prone to low efficiency due to sequential execution, resulting in longer model training and execution time. Intuitively, partitioning policies of all agents according to their interdependence and updating joint policy batch-by-batch can effectively balance performance and efficiency. However, how to determine the optimal batch partition of policies and batch updating order are challenging problems. Firstly, a sequential batched policy updating scheme, B2MAPO (Batch by Batch Multi-Agent Policy Optimization), is proposed with a theoretical guarantee of the monotonic incrementally tightened bound. Secondly, a universal modulized plug-and-play B2MAPO hierarchical framework, which satisfies CTDE principle, is designed to conveniently integrate any MARL models to fully exploit and merge their merits, including policy optimality and inference efficiency. Next, a DAG-based B2MAPO algorithm is devised, which is a carefully designed implementation of B2MAPO framework. The upper layer employs PPO algorithm with attention mechanism to reveal interdependence between policies, and generates DAGs of agents which are used to produce optimal batch sequence through topological sorting. The lower layer trains two joint policies in parallel and minimizes KL divergence between them periodically. One joint policy is sequentially updated according to B2MAPO scheme with batch sequence, another derived joint policy is simultaneously updated by MAPPO. While decentralized execution, only the derived joint policy is adopted for decision-making. Comprehensive experimental results conducted on StarCraftII Multi-agent Challenge and Google Football Research demonstrate the performance of DAG-based B2MAPO algorithm outperforms baseline methods. Meanwhile, compared with A2PO, our algorithm reduces the model training and execution time by 60.4% and 78.7%, respectively.

Subspace Indexing with Interpolation (SIM-I) on Stiefel and Grassmann manifolds is proposed in this work. Given a partition of some original high-dimensional data set, SIM-I is constructed via two steps: in the first step we build linear affinity-aware subspace models based on each partition; in the second step we interpolate between several adjacent linear subspace models constructed in the first step using the “center of mass” calculation on Stiefel and Grassmann manifolds. Through these two steps, SIM-I builds a globally nonlinear and smoothly regularized low-dimensional embedding model of the original data set. Furthermore, given sufficiently many training samples on the data manifold either labelled by some pre-trained learning model such as Deep Neural Networks (DNNs) or provided with original natural labels, we first apply SIM-I on this data set and then perform nearest-neighbor classification on the resulting low-dimensional embedding. This helps us to build a Lightweight Inference Engine (LIE) carrying similar level of feature extraction by the pre-trained learning model. For DNNs, such LIE can be interpreted as some (nonstandard) shallow neural network with a wide first hidden layer. From this perspective, SIM-I provides a way to exchange deep network for wide but shallow ones and may provide some new insights to interpret DNNs.

The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning. While past studies confirm that the magnitude and the covariance structure of gradient noise are critical for regularization, it remains unclear whether or not the class of noise distributions is important. In this work we provide negative results by showing that noises in classes different from the SGD noise can also effectively regularize gradient descent. Our finding is based on a novel observation on the structure of the SGD noise: it is the multiplication of the gradient matrix and a sampling noise that arises from the mini-batch sampling procedure. Moreover, the sampling noises unify two kinds of gradient regularizing noises that belong to the Gaussian class: the one using (scaled) Fisher as covariance and the one using the gradient covariance of SGD as covariance. Finally, thanks to the flexibility of choosing noise class, an algorithm is proposed to perform noisy gradient descent that generalizes well, the variant of which even benefits large batch SGD training without hurting generalization.

We study the convergence behavior of a stochastic heavy-ball method with a small stepsize. Under a change of time scale, we approximate the discrete scheme by a stochastic differential equation that models small random perturbations of a coupled system of nonlinear oscillators. We rigorously show that the perturbed system converges to a local minimum in a logarithmic time. This indicates that for the diffusion process that approximates the stochastic heavy-ball method, it takes (up to a logarithmic factor) only a linear time of the square root of the inverse stepsize to escape from all saddle points. This results may suggest a fast convergence of its discrete-time counterpart. Our theoretical results are validated by numerical experiments.

Stochastic compositional optimization arises in many important machine learning tasks such as reinforcement learning and portfolio management. The objective function is the composition of two expectations of stochastic functions, and is more challenging to optimize than vanilla stochastic optimization problems. In this paper, we investigate the stochastic compositional optimization in the general smooth non-convex setting. We employ a recently developed idea of \textit{Stochastic Recursive Gradient Descent} to design a novel algorithm named SARAH-Compositional, and prove a sharp Incremental First-order Oracle (IFO) complexity upper bound for stochastic compositional optimization: $\mathcal{O}((n+m)^{1/2} \varepsilon^{-2})$ in the finite-sum case and $\mathcal{O}(\varepsilon^{-3})$ in the online case. Such a complexity is known to be the best one among IFO complexity results for non-convex stochastic compositional optimization. Numerical experiments validate the superior performance of our algorithm and theory.

Linear discriminant analysis (LDA) is a well-known technique for linear classification, feature extraction, and dimension reduction. To improve the accuracy of LDA under the high dimension low sample size (HDLSS) settings, shrunken estimators, such as Graphical Lasso, can be used to strike a balance between biases and variances. Although the estimator with induced sparsity obtains a faster convergence rate, however, the introduced bias may also degrade the performance. In this paper, we theoretically analyze how the sparsity and the convergence rate of the precision matrix (also known as inverse covariance matrix) estimator would affect the classification accuracy by proposing an analytic model on the upper bound of an LDA misclassification rate. Guided by the model, we propose a novel classifier, DBSDA , which improves classification accuracy through debiasing. Theoretical analysis shows that DBSDA possesses a reduced upper bound of misclassification rate and better asymptotic properties than sparse LDA (SDA). We conduct experiments on both synthetic datasets and real application datasets to confirm the correctness of our theoretical analysis and demonstrate the superiority of DBSDA over LDA, SDA, and other downstream competitors under HDLSS settings.

Fisher's Linear Discriminant Analysis (FLD) is a well-known technique for linear classification, feature extraction and dimension reduction. The empirical FLD relies on two key estimations from the data -- the mean vector for each class and the (inverse) covariance matrix. To improve the accuracy of FLD under the High Dimension Low Sample Size (HDLSS) settings, Covariance-Regularized FLD (CRLD) has been proposed to use shrunken covariance estimators, such as Graphical Lasso, to strike a balance between biases and variances. Though CRLD could obtain better classification accuracy, it usually incurs bias and converges to the optimal result with a slower asymptotic rate. Inspired by the recent progress in de-biased Lasso, we propose a novel FLD classifier, DBLD, which improves classification accuracy of CRLD through de-biasing. Theoretical analysis shows that DBLD possesses better asymptotic properties than CRLD. We conduct experiments on both synthetic datasets and real application datasets to confirm the correctness of our theoretical analysis and demonstrate the superiority of DBLD over classical FLD, CRLD and other downstream competitors under HDLSS settings.

Sparse Discriminant Analysis (SDA) has been widely used to improve the performance of classical Fisher's Linear Discriminant Analysis in supervised metric learning, feature selection and classification. With the increasing needs of distributed data collection, storage and processing, enabling the Sparse Discriminant Learning to embrace the Multi-Party distributed computing environments becomes an emerging research topic. This paper proposes a novel Multi-Party SDA algorithm, which can learn SDA models effectively without sharing any raw dataand basic statistics among machines. The proposed algorithm 1) leverages the direct estimation of SDA [1] to derive a distributed loss function for the discriminant learning, 2) parameterizes the distributed loss function with local/global estimates through bootstrapping, and 3) approximates a global estimation of linear discriminant projection vector by optimizing the "distributed bootstrapping loss function" with gossip-based stochastic gradient descent. Experimental results on both synthetic and real-world benchmark datasets show that our algorithm can compete with the centralized SDA with similar performance, and significantly outperforms the most recent distributed SDA [2] in terms of accuracy and F1-score.

Linear Discriminant Analysis (LDA) is widely-used for supervised dimension reduction and linear classification. Classical LDA, however, suffers from the ill-posed estimation problem on data with high dimension and low sample size (HDLSS). To cope with this problem, in this paper, we propose an Adaptive Wishart Discriminant Analysis (AWDA) for classification, that makes predictions in an ensemble way. Comparing to existing approaches, AWDA has two advantages: 1) leveraging theWishart distribution, AWDA ensembles multiple LDA classifiers parameterized by the sampled covariance matrices via a Bayesian Voting Scheme, which theoretically improves the robustness of classification, compared to LDA classifiers using a single (probably ill-posed) covariance matrix estimator; 2) AWDA updates the weights for voting optimally to adapt the local information of each new input data, so as to enable the nonlinear classification. Theoretical analysis indicates that AWDA guarantees a close approximation to the optimal Bayesian inference and thus achieves robust performance on high dimensional data. Extensive experiments on real-world datasets show that our approach outperforms state-of-the-art algorithms by a large margin.

While exploring human mobility can benefit many applications such as smart transportation, city planning, and urban economics, there are two key questions that need to be answered: (i) What is the nature of the spatial diffusion of human mobility across regions with different urban functions? (ii) How to spot and trace the trip purposes of human mobility trajectories? To answer these questions, we study large-scale and city-wide taxi trajectories; and furtherly organize them as arrival sequences according to the chronological arrival time. We figure out an important property across different regions from the arrival sequences, namely human mobility synchronization effect, which can be exploited to explain the phenomenon that two regions have similar arrival patterns in particular time periods if they share similar urban functions. In addition, the arrival sequences are mixed by arrival events with distinct trip purposes, which can be revealed by the regional environment of both the origins and destinations. To that end, in this paper, we develop a joint model that integrates Mixture of Hawkes Process (MHP) with a hierarchical topic model to capture the arrival sequences with mixed trip purposes. Essentially, the human mobility synchronization effect is encoded as a synchronization rate in the MHP; while the regional environment is modeled by introducing latent Trip Purpose and POI Topic to generate the Point of Interests (POIs) in the regions. Moreover, we provide an effective inference algorithm for parameter learning. Finally, we conduct intensive experiments on synthetic data and real-world data, and the experimental results have demonstrated the effectiveness of the proposed model.