arXiv subjects

Jun Wang

Publications and source records attributed to Jun Wang.

At least 739 records · Page 41Linked to original sources

arXiv2023

Multiple Access Design for Symbiotic Radios: Facilitating Massive IoT Connections with Cellular Networks

Symbiotic radio (SR) has emerged as a spectrum- and energy-efficient paradigm to support massive Internet of Things (IoT) connections. Two multiple access schemes are proposed in this paper to facilitate the massive IoT connections using the cellular network based on the SR technique, namely, the simultaneous access (SA) scheme and the selection diversity access (SDA) scheme. In the SA scheme, the base station (BS) transmits information to the receiver while multiple IoT devices transmit their information simultaneously by passively backscattering the BS signal to the receiver, while in the SDA scheme, only the IoT device with the strongest backscatter link transmits information to the receiver. In both of the schemes, the receiver jointly decodes the information from the BS and the IoT devices. To evaluate the above two schemes, in this paper, we have derived the closed-form expressions of the ergodic rates and the outage probabilities for the cellular and IoT transmissions. Finally, numerical results are provided to verify the theoretical analysis and compare the two proposed multiple access schemes. When the number of IoT devices is small, the SDA scheme is more appealing since it can significantly reduce the computational complexity while achieving equivalent performance to the SA scheme. When the number of IoT devices is large, the SA scheme is preferable since it guarantees a significantly better rate performance and a lower outage probability.

cs.IT↗

arXiv2023

Sim-to-Real Transfer for Quadrupedal Locomotion via Terrain Transformer

Deep reinforcement learning has recently emerged as an appealing alternative for legged locomotion over multiple terrains by training a policy in physical simulation and then transferring it to the real world (i.e., sim-to-real transfer). Despite considerable progress, the capacity and scalability of traditional neural networks are still limited, which may hinder their applications in more complex environments. In contrast, the Transformer architecture has shown its superiority in a wide range of large-scale sequence modeling tasks, including natural language processing and decision-making problems. In this paper, we propose Terrain Transformer (TERT), a high-capacity Transformer model for quadrupedal locomotion control on various terrains. Furthermore, to better leverage Transformer in sim-to-real scenarios, we present a novel two-stage training framework consisting of an offline pretraining stage and an online correction stage, which can naturally integrate Transformer with privileged training. Extensive experiments in simulation demonstrate that TERT outperforms state-of-the-art baselines on different terrains in terms of return, energy consumption and control smoothness. In further real-world validation, TERT successfully traverses nine challenging terrains, including sand pit and stair down, which can not be accomplished by strong baselines.

cs.RO↗

arXiv2023

General bound states in the continuum in momentum space

Polarization singularities including bound states in the continuum (BICs) and circularly polarized states have provided promising opportunities in the manipulation of light waves. Previous studies show that BICs in photonic crystal slabs are protected by $C_{2}T$ symmetry and hence normally exist on the high-symmetry lines of momentum space. Here, we propose an approach based on graph theory to study these polarization singularities in momentum space, especially in the region off the high-symmetry lines. With a polarization graph, it is demonstrated for the first time that BICs can stably exist off the high-symmetry lines of momentum space for both one-dimensional and two-dimensional photonic crystal slabs. Furthermore, two kinds of interesting processes, including the merging involved with this newly found BICs both on and off the high-symmetry lines, are observed by merely changing the thickness of photonic crystal slab. Our findings provide a new perspective to explore polarization singularities in momentum space and render their further applications in light-matter interaction and light manipulation.

physics.optics↗

arXiv2023

Photon Energy-Resolved Velocity Map Imaging from Spectral Domain Ghost Imaging

We present an approach that combines photon spectrum correlation analysis with the reconstruction of three-dimensional momentum distribution from velocity map images in an efficient, single-step procedure. We demonstrate its efficacy with the results from the photoionization of the $2p$-shell of argon using the FLASH free-electron laser~(FEL). Distinct spectral features due to the spin-orbit splitting of Ar$^+(2p^{-1})$ are resolved, despite the large average bandwidth of the ionizing pulses from the FEL. This demonstrates a clear advantage over the conventional analysis method, and it will be broadly beneficial for velocity map imaging experiments with FEL sources. The retrieved linewidth of the binding energy spectrum approaches the resolution limitation prescribed by the spectrometers used to collect the data. Our approach presents a path to extend spectral-domain ghost imaging to the case where the photoproduct observable is high-dimensional.

physics.atom-ph↗

arXiv2023

DistilPose: Tokenized Pose Regression with Heatmap Distillation

In the field of human pose estimation, regression-based methods have been dominated in terms of speed, while heatmap-based methods are far ahead in terms of performance. How to take advantage of both schemes remains a challenging problem. In this paper, we propose a novel human pose estimation framework termed DistilPose, which bridges the gaps between heatmap-based and regression-based methods. Specifically, DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling Encoder (TDE) and Simulated Heatmaps. TDE aligns the feature spaces of heatmap-based and regression-based models by introducing tokenization, while Simulated Heatmaps transfer explicit guidance (distribution and confidence) from teacher heatmaps into student models. Extensive experiments show that the proposed DistilPose can significantly improve the performance of the regression-based models while maintaining efficiency. Specifically, on the MSCOCO validation dataset, DistilPose-S obtains 71.6% mAP with 5.36M parameter, 2.38 GFLOPs and 40.2 FPS, which saves 12.95x, 7.16x computational cost and is 4.9x faster than its teacher model with only 0.9 points performance drop. Furthermore, DistilPose-L obtains 74.4% mAP on MSCOCO validation dataset, achieving a new state-of-the-art among predominant regression-based models.

cs.CV↗

arXiv2023

Is Nash Equilibrium Approximator Learnable?

In this paper, we investigate the learnability of the function approximator that approximates Nash equilibrium (NE) for games generated from a distribution. First, we offer a generalization bound using the Probably Approximately Correct (PAC) learning model. The bound describes the gap between the expected loss and empirical loss of the NE approximator. Afterward, we prove the agnostic PAC learnability of the Nash approximator. In addition to theoretical analysis, we demonstrate an application of NE approximator in experiments. The trained NE approximator can be used to warm-start and accelerate classical NE solvers. Together, our results show the practicability of approximating NE through function approximation.

cs.GT↗

arXiv2023

TriNet: stabilizing self-supervised learning from complete or slow collapse on ASR

Self-supervised learning (SSL) models confront challenges of abrupt informational collapse or slow dimensional collapse. We propose TriNet, which introduces a novel triple-branch architecture for preventing collapse and stabilizing the pre-training. TriNet learns the SSL latent embedding space and incorporates it to a higher level space for predicting pseudo target vectors generated by a frozen teacher. Our experimental results show that the proposed method notably stabilizes and accelerates pre-training and achieves a relative word error rate reduction (WERR) of 6.06% compared to the state-of-the-art (SOTA) Data2vec for a downstream benchmark ASR task. We will release our code at https://github.com/tencent-ailab/.

eess.AS↗

arXiv2023

DOMINO: Visual Causal Reasoning with Time-Dependent Phenomena

Current work on using visual analytics to determine causal relations among variables has mostly been based on the concept of counterfactuals. As such the derived static causal networks do not take into account the effect of time as an indicator. However, knowing the time delay of a causal relation can be crucial as it instructs how and when actions should be taken. Yet, similar to static causality, deriving causal relations from observational time-series data, as opposed to designed experiments, is not a straightforward process. It can greatly benefit from human insight to break ties and resolve errors. We hence propose a set of visual analytics methods that allow humans to participate in the discovery of causal relations associated with windows of time delay. Specifically, we leverage a well-established method, logic-based causality, to enable analysts to test the significance of potential causes and measure their influences toward a certain effect. Furthermore, since an effect can be a cause of other effects, we allow users to aggregate different temporal cause-effect relations found with our method into a visual flow diagram to enable the discovery of temporal causal networks. To demonstrate the effectiveness of our methods we constructed a prototype system named DOMINO and showcase it via a number of case studies using real-world datasets. Finally, we also used DOMINO to conduct several evaluations with human analysts from different science domains in order to gain feedback on the utility of our system in practical scenarios.

cs.HC↗

arXiv2023

Estimation of the Directions for Unknown Parameters in Semiparametric Models

Semiparametric models are useful in econometrics, social sciences and medicine application. In this paper, a new estimator based on least square methods is proposed to estimate the direction of unknown parameters in semi-parametric models. The proposed estimator is consistent and has asymptotic distribution under mild conditions without the knowledge of the form of link function. Simulations show that the proposed estimator is significantly superior to maximum score estimator given by Manski (1975) for binary response variables. When the error term is long-tailed distributions or distribution with infinity moments, the proposed estimator perform well. Its application is illustrated with data of exporting participation of manufactures in Guangdong.

stat.ME↗

arXiv2023

A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems

In order for agents in multi-agent systems (MAS) to be safe, they need to take into account the risks posed by the actions of other agents. However, the dominant paradigm in game theory (GT) assumes that agents are not affected by risk from other agents and only strive to maximise their expected utility. For example, in hybrid human-AI driving systems, it is necessary to limit large deviations in reward resulting from car crashes. Although there are equilibrium concepts in game theory that take into account risk aversion, they either assume that agents are risk-neutral with respect to the uncertainty caused by the actions of other agents, or they are not guaranteed to exist. We introduce a new GT-based Risk-Averse Equilibrium (RAE) that always produces a solution that minimises the potential variance in reward accounting for the strategy of other agents. Theoretically and empirically, we show RAE shares many properties with a Nash Equilibrium (NE), establishing convergence properties and generalising to risk-dominant NE in certain cases. To tackle large-scale problems, we extend RAE to the PSRO multi-agent reinforcement learning (MARL) framework. We empirically demonstrate the minimum reward variance benefits of RAE in matrix games with high-risk outcomes. Results on MARL experiments show RAE generalises to risk-dominant NE in a trust dilemma game and that it reduces instances of crashing by 7x in an autonomous driving setting versus the best performing baseline.

cs.LG↗

arXiv2023

DESTA: A Framework for Safe Reinforcement Learning with Markov Games of Intervention

Reinforcement learning (RL) involves performing exploratory actions in an unknown system. This can place a learning agent in dangerous and potentially catastrophic system states. Current approaches for tackling safe learning in RL simultaneously trade-off safe exploration and task fulfillment. In this paper, we introduce a new generation of RL solvers that learn to minimise safety violations while maximising the task reward to the extent that can be tolerated by the safe policy. Our approach introduces a novel two-player framework for safe RL called Distributive Exploration Safety Training Algorithm (DESTA). The core of DESTA is a game between two adaptive agents: Safety Agent that is delegated the task of minimising safety violations and Task Agent whose goal is to maximise the environment reward. Specifically, Safety Agent can selectively take control of the system at any given point to prevent safety violations while Task Agent is free to execute its policy at any other states. This framework enables Safety Agent to learn to take actions at certain states that minimise future safety violations, both during training and testing time, while Task Agent performs actions that maximise the task performance everywhere else. Theoretically, we prove that DESTA converges to stable points enabling safety violations of pretrained policies to be minimised. Empirically, we show DESTA's ability to augment the safety of existing policies and secondly, construct safe RL policies when the Task Agent and Safety Agent are trained concurrently. We demonstrate DESTA's superior performance against leading RL methods in Lunar Lander and Frozen Lake from OpenAI gym.

cs.LG↗

arXiv2023

Order Matters: Agent-by-agent Policy Optimization

While multi-agent trust region algorithms have achieved great success empirically in solving coordination tasks, most of them, however, suffer from a non-stationarity problem since agents update their policies simultaneously. In contrast, a sequential scheme that updates policies agent-by-agent provides another perspective and shows strong performance. However, sample inefficiency and lack of monotonic improvement guarantees for each agent are still the two significant challenges for the sequential scheme. In this paper, we propose the \textbf{A}gent-by-\textbf{a}gent \textbf{P}olicy \textbf{O}ptimization (A2PO) algorithm to improve the sample efficiency and retain the guarantees of monotonic improvement for each agent during training. We justify the tightness of the monotonic improvement bound compared with other trust region algorithms. From the perspective of sequentially updating agents, we further consider the effect of agent updating order and extend the theory of non-stationarity into the sequential update scheme. To evaluate A2PO, we conduct a comprehensive empirical study on four benchmarks: StarCraftII, Multi-agent MuJoCo, Multi-agent Particle Environment, and Google Research Football full game scenarios. A2PO consistently outperforms strong baselines.

cs.AI↗

arXiv2023

Incentive-boosted Federated Crowdsourcing

Crowdsourcing is a favorable computing paradigm for processing computer-hard tasks by harnessing human intelligence. However, generic crowdsourcing systems may lead to privacy-leakage through the sharing of worker data. To tackle this problem, we propose a novel approach, called iFedCrowd (incentive-boosted Federated Crowdsourcing), to manage the privacy and quality of crowdsourcing projects. iFedCrowd allows participants to locally process sensitive data and only upload encrypted training models, and then aggregates the model parameters to build a shared server model to protect data privacy. To motivate workers to build a high-quality global model in an efficacy way, we introduce an incentive mechanism that encourages workers to constantly collect fresh data to train accurate client models and boosts the global model training. We model the incentive-based interaction between the crowdsourcing platform and participating workers as a Stackelberg game, in which each side maximizes its own profit. We derive the Nash Equilibrium of the game to find the optimal solutions for the two sides. Experimental results confirm that iFedCrowd can complete secure crowdsourcing projects with high quality and efficiency.

cs.GT↗

arXiv2023

Dual Representation Learning for One-Step Clustering of Multi-View Data

Multi-view data are commonly encountered in data mining applications. Effective extraction of information from multi-view data requires specific design of clustering methods to cater for data with multiple views, which is non-trivial and challenging. In this paper, we propose a novel one-step multi-view clustering method by exploiting the dual representation of both the common and specific information of different views. The motivation originates from the rationale that multi-view data contain not only the consistent knowledge between views but also the unique knowledge of each view. Meanwhile, to make the representation learning more specific to the clustering task, a one-step learning framework is proposed to integrate representation learning and clustering partition as a whole. With this framework, the representation learning and clustering partition mutually benefit each other, which effectively improve the clustering performance. Results from extensive experiments conducted on benchmark multi-view datasets clearly demonstrate the superiority of the proposed method.

cs.LG↗

arXiv2023

Which country is this picture from? New data and methods for DNN-based country recognition

Recognizing the country where a picture has been taken has many potential applications, such as identification of fake news and prevention of disinformation campaigns. Previous works focused on the estimation of the geo-coordinates where a picture has been taken. Yet, recognizing in which country an image was taken could be more critical, from a semantic and forensic point of view, than estimating its spatial coordinates. In the above framework, this paper provides two contributions. First, we introduce the VIPPGeo dataset, containing 3.8 million geo-tagged images. Secondly, we used the dataset to train a model casting the country recognition problem as a classification problem. The experiments show that our model provides better results than the current state of the art. Notably, we found that asking the network to identify the country provides better results than estimating the geo-coordinates and then tracing them back to the country where the picture was taken.

cs.CV↗

arXiv2023

Online Double Oracle

Solving strategic games with huge action space is a critical yet under-explored topic in economics, operations research and artificial intelligence. This paper proposes new learning algorithms for solving two-player zero-sum normal-form games where the number of pure strategies is prohibitively large. Specifically, we combine no-regret analysis from online learning with Double Oracle (DO) methods from game theory. Our method -- \emph{Online Double Oracle (ODO)} -- is provably convergent to a Nash equilibrium (NE). Most importantly, unlike normal DO methods, ODO is \emph{rationale} in the sense that each agent in ODO can exploit strategic adversary with a regret bound of $\mathcal{O}(\sqrt{T k \log(k)})$ where $k$ is not the total number of pure strategies, but rather the size of \emph{effective strategy set} that is linearly dependent on the support size of the NE. On tens of different real-world games, ODO outperforms DO, PSRO methods, and no-regret algorithms such as Multiplicative Weight Update by a significant margin, both in terms of convergence rate to a NE and average payoff against strategic adversaries.

cs.AI↗

arXiv2023

Building Intelligence in the Mechanical Domain -- Harvesting the Reservoir Computing Power in Origami to Achieve Information Perception Tasks

In this paper, we experimentally examine the cognitive capability of a simple, paper-based Miura-ori -- using the physical reservoir computing framework -- to achieve different information perception tasks. The body dynamics of Miura-ori (aka. its vertices displacements), which is excited by a simple harmonic base excitation, can be exploited as the reservoir computing resource. By recording these dynamics with a high-resolution camera and image processing program and then using linear regression for training, we show that the origami reservoir has sufficient computing capacity to estimate the weight and position of a payload. It can also recognize the input frequency and magnitude patterns. Furthermore, multitasking is achievable by simultaneously applying two targeted functions to the same reservoir state matrix. Therefore, we demonstrate that Miura-ori can assess the dynamic interactions between its body and ambient environment to extract meaningful information -- an intelligent behavior in the mechanical domain. Given that Miura-ori has been widely used to construct deployable structures, lightweight materials, and compliant robots, enabling such information perception tasks can add a new dimension to the functionality of such a versatile structure.

cs.ET↗

arXiv2023

Learning to Shape Rewards using a Game of Two Partners

Reward shaping (RS) is a powerful method in reinforcement learning (RL) for overcoming the problem of sparse or uninformative rewards. However, RS typically relies on manually engineered shaping-reward functions whose construction is time-consuming and error-prone. It also requires domain knowledge which runs contrary to the goal of autonomous learning. We introduce Reinforcement Learning Optimising Shaping Algorithm (ROSA), an automated reward shaping framework in which the shaping-reward function is constructed in a Markov game between two agents. A reward-shaping agent (Shaper) uses switching controls to determine which states to add shaping rewards for more efficient learning while the other agent (Controller) learns the optimal policy for the task using these shaped rewards. We prove that ROSA, which adopts existing RL algorithms, learns to construct a shaping-reward function that is beneficial to the task thus ensuring efficient convergence to high performance policies. We demonstrate ROSA's properties in three didactic experiments and show its superior performance against state-of-the-art RS algorithms in challenging sparse reward environments.

cs.LG↗