Representation learning is all about discovering the hidden modular attributes that generate the data faithfully. We explore the potential of Denoising Diffusion Probabilistic Model (DM) in unsupervised learning of the modular attributes. We build a theoretical framework that connects the diffusion time-steps and the hidden attributes, which serves as an effective inductive bias for unsupervised learning. Specifically, the forward diffusion process incrementally adds Gaussian noise to samples at each time-step, which essentially collapses different samples into similar ones by losing attributes, e.g., fine-grained attributes such as texture are lost with less noise added (i.e., early time-steps), while coarse-grained ones such as shape are lost by adding more noise (i.e., late time-steps). To disentangle the modular attributes, at each time-step t, we learn a t-specific feature to compensate for the newly lost attribute, and the set of all 1,...,t-specific features, corresponding to the cumulative set of lost attributes, are trained to make up for the reconstruction error of a pre-trained DM at time-step t. On CelebA, FFHQ, and Bedroom datasets, the learned feature significantly improves attribute classification and enables faithful counterfactual generation, e.g., interpolating only one specified attribute between two images, validating the disentanglement quality. Codes are in https://github.com/yue-zhongqi/diti.
Federated reinforcement learning (FRL) has emerged as a promising paradigm for reducing the sample complexity of reinforcement learning tasks by exploiting information from different agents. However, when each agent interacts with a potentially different environment, little to nothing is known theoretically about the non-asymptotic performance of FRL algorithms. The lack of such results can be attributed to various technical challenges and their intricate interplay: Markovian sampling, linear function approximation, multiple local updates to save communication, heterogeneity in the reward functions and transition kernels of the agents' MDPs, and continuous state-action spaces. Moreover, in the on-policy setting, the behavior policies vary with time, further complicating the analysis. In response, we introduce FedSARSA, a novel federated on-policy reinforcement learning scheme, equipped with linear function approximation, to address these challenges and provide a comprehensive finite-time error analysis. Notably, we establish that FedSARSA converges to a policy that is near-optimal for all agents, with the extent of near-optimality proportional to the level of heterogeneity. Furthermore, we prove that FedSARSA leverages agent collaboration to enable linear speedups as the number of agents increases, which holds for both fixed and adaptive step-size configurations.
Tennis is so popular that coaches and players are curious about factors other than skill, such as momentum. This article will try to define and quantify momentum, providing a basis for real-time analysis of tennis matches. Based on the tennis Grand Slam men's singles match data in recent years, we built two models, one is to build a model based on data-driven, and the other is to build a model based on empirical formulas. For the data-driven model, we first found a large amount of public data including public data on tennis matches in the past five years and personal information data of players. Then the data is preprocessed, and feature engineered, and a fusion model of SVM, Random Forrest algorithm and XGBoost was established. For the mechanism analysis model, important features were selected based on the suggestions of many tennis players and enthusiasts, the sliding window algorithm was used to calculate the weight, and different methods were used to visualize the momentum. For further analysis of the momentum fluctuation, it is based on the popular CUMSUM algorithm in the industry as well as the RUN Test, and the result shows the momentum is not random and the trend might be random. At last, the robustness of the fusion model is analyzed by Monte Carlo simulation.
The principle of orthogonal time-frequency-space (OTFS) signaling is firstly analyzed, followed by explaining that OTFS embeds another signaling scheme referred to as orthogonal short-time Fourier (OSTF). Then, the relationship among OTFS, OSTF, orthogonal frequency-division multiplexing (OFDM) and single-carrier frequency-division multiple-access (SC-FDMA) is explored, demonstrating that OSTF/OTFS are fundamentally the extensions of OFDM/SC-FDMA from one-dimensional (1D) signaling to two-dimensional (2D) signaling. Hence, the characteristics and performance of OSTF/OTFS schemes can be perceived from the well-understood OFDM/SC-FDMA schemes. Accordingly, the advantages and disadvantages of OSTF/OTFS are discussed. Furthermore, from the principles of OFDM/SC-FDMA, the multiuser multiplexing in OSTF/OTFS systems is analyzed with respect to uplink and downlink, respectively. Added on this, a range of generalized multiplexing schemes are presented, whose characteristics are briefly analyzed.
Previous deep learning-based event denoising methods mostly suffer from poor interpretability and difficulty in real-time processing due to their complex architecture designs. In this paper, we propose window-based event denoising, which simultaneously deals with a stack of events while existing element-based denoising focuses on one event each time. Besides, we give the theoretical analysis based on probability distributions in both temporal and spatial domains to improve interpretability. In temporal domain, we use timestamp deviations between processing events and central event to judge the temporal correlation and filter out temporal-irrelevant events. In spatial domain, we choose maximum a posteriori (MAP) to discriminate real-world event and noise, and use the learned convolutional sparse coding to optimize the objective function. Based on the theoretical analysis, we build Temporal Window (TW) module and Soft Spatial Feature Embedding (SSFE) module to process temporal and spatial information separately, and construct a novel multi-scale window-based event denoising network, named MSDNet. The high denoising accuracy and fast running speed of our MSDNet enables us to achieve real-time denoising in complex scenes. Extensive experimental results verify the effectiveness and robustness of our MSDNet. Our algorithm can remove event noise effectively and efficiently and improve the performance of downstream tasks.
Existing blind image quality assessment (BIQA) methods focus on designing complicated networks based on convolutional neural networks (CNNs) or transformer. In addition, some BIQA methods enhance the performance of the model in a two-stage training manner. Despite the significant advancements, these methods remarkably raise the parameter count of the model, thus requiring more training time and computational resources. To tackle the above issues, we propose a lightweight parallel framework (LPF) for BIQA. First, we extract the visual features using a pre-trained feature extraction network. Furthermore, we construct a simple yet effective feature embedding network (FEN) to transform the visual features, aiming to generate the latent representations that contain salient distortion information. To improve the robustness of the latent representations, we present two novel self-supervised subtasks, including a sample-level category prediction task and a batch-level quality comparison task. The sample-level category prediction task is presented to help the model with coarse-grained distortion perception. The batch-level quality comparison task is formulated to enhance the training data and thus improve the robustness of the latent representations. Finally, the latent representations are fed into a distortion-aware quality regression network (DaQRN), which simulates the human vision system (HVS) and thus generates accurate quality scores. Experimental results on multiple benchmark datasets demonstrate that the proposed method achieves superior performance over state-of-the-art approaches. Moreover, extensive analyses prove that the proposed method has lower computational complexity and faster convergence speed.
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation models using reinforcement learning (RL), and the multi-dimensionality, heterogeneity, and conflicting nature of human preferences further complicate the alignment process. In this paper, we introduce Rewards-in-Context (RiC), which conditions the response of a foundation model on multiple rewards in its prompt context and applies supervised fine-tuning for alignment. The salient features of RiC are simplicity and adaptivity, as it only requires supervised fine-tuning of a single foundation model and supports dynamic adjustment for user preferences during inference time. Inspired by the analytical solution of an abstracted convex optimization problem, our dynamic inference-time adjustment method approaches the Pareto-optimal solution for multiple objectives. Empirical evidence demonstrates the efficacy of our method in aligning both Large Language Models (LLMs) and diffusion models to accommodate diverse rewards with only around $10\%$ GPU hours compared with multi-objective RL baseline.
In this paper, we study the problem of online tracking in linear control systems, where the objective is to follow a moving target. Unlike classical tracking control, the target is unknown, non-stationary, and its state is revealed sequentially, thus, fitting the framework of online non-stochastic control. We consider the case of quadratic costs and propose a new algorithm, called predictive linear online tracking (PLOT). The algorithm uses recursive least squares with exponential forgetting to learn a time-varying dynamic model of the target. The learned model is used in the optimal policy under the framework of receding horizon control. We show the dynamic regret of PLOT scales with $\mathcal{O}(\sqrt{TV_T})$, where $V_T$ is the total variation of the target dynamics and $T$ is the time horizon. Unlike prior work, our theoretical results hold for non-stationary targets. We implement PLOT on a real quadrotor and provide open-source software, thus, showcasing one of the first successful applications of online control methods on real hardware.
This paper presents a convolutional neural network model for precipitation nowcasting that combines data-driven learning with physics-informed domain knowledge. We propose LUPIN, a Lagrangian Double U-Net for Physics-Informed Nowcasting, that draws from existing extrapolation-based nowcasting methods and implements the Lagrangian coordinate system transformation of the data in a fully differentiable and GPU-accelerated manner to allow for real-time end-to-end training and inference. Based on our evaluation, LUPIN matches and exceeds the performance of the chosen benchmark, opening the door for other Lagrangian machine learning models.
Controlling the shape of deformable linear objects using robots and constraints provided by environmental fixtures has diverse industrial applications. In order to establish robust contacts with these fixtures, accurate estimation of the contact state is essential for preventing and rectifying potential anomalies. However, this task is challenging due to the small sizes of fixtures, the requirement for real-time performances, and the infinite degrees of freedom of the deformable linear objects. In this paper, we propose a real-time approach for estimating both contact establishment and subsequent changes by leveraging the dependency between the applied and detected contact force on the deformable linear objects. We seamlessly integrate this method into the robot control loop and achieve an adaptive shape control framework which avoids, detects and corrects anomalies automatically. Real-world experiments validate the robustness and effectiveness of our contact estimation approach across various scenarios, significantly increasing the success rate of shape control processes.