arXiv subjects

Yang Yu

Publications and source records attributed to Yang Yu.

At least 199 records · Page 11Linked to original sources

arXiv2024

Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning

Combining offline and online reinforcement learning (RL) techniques is indeed crucial for achieving efficient and safe learning where data acquisition is expensive. Existing methods replay offline data directly in the online phase, resulting in a significant challenge of data distribution shift and subsequently causing inefficiency in online fine-tuning. To address this issue, we introduce an innovative approach, \textbf{E}nergy-guided \textbf{DI}ffusion \textbf{S}ampling (EDIS), which utilizes a diffusion model to extract prior knowledge from the offline dataset and employs energy functions to distill this knowledge for enhanced data generation in the online phase. The theoretical analysis demonstrates that EDIS exhibits reduced suboptimality compared to solely utilizing online data or directly reusing offline data. EDIS is a plug-in approach and can be combined with existing methods in offline-to-online RL setting. By implementing EDIS to off-the-shelf methods Cal-QL and IQL, we observe a notable 20% average improvement in empirical performance on MuJoCo, AntMaze, and Adroit environments. Code is available at \url{https://github.com/liuxhym/EDIS}.

cs.LG↗

arXiv2024

The cumulation of debris clouds around a fast-rotating asteroid

The rotational mass loss has been realized to be a prevalent mechanism to produce low-speed debris near the asteroid, and the size composition of the asteroid's surface regolith has been closely measured by in situ explorations. However, the full-scale evolution of the shedding debris has not been examined using the observed particle sizes, which may hold vital clues to the initial growth of an asteroid moonlet, and help us to understand the general mechanisms that dominate the formation of asteroid systems. This paper presented our study on the cumulative evolution of the debris cloud formed by a rotationally unstable asteroid. A semi-analytical model is developed to characterize the spatial-temporal evolution of the debris cloud posterior to a shedding event. Large-scale DEM simulations are performed to quantify the clustering behavior of the debris particles in the mechanical environment near the asteroid. As a result, we found the cumulation of a steady debris cloud is dominated by large pieces of debris, and the shedding particles follow a common migration trend, which fundamentally determines the mass distribution of the debris cloud. For the accretion analysis, we sketched the life cycle of a debris cluster, and showed its dependency on particle size. The DEM simulations adopt physical parameters estimated from observations and asteroid missions. The results confirm porous fluffy cluster structures can form shortly after a shedding event with magnitudes as the observed shedding activities. Measurements to these structures show they possess certain strength and adsorption capacity to collisions from dissociative debris particles.

astro-ph.EP↗

arXiv2024

Denoising of Imaginary Time Response Functions with Hankel projections

Imaginary-time response functions of finite-temperature quantum systems are often obtained with methods that exhibit stochastic or systematic errors. Reducing these errors comes at a large computational cost -- in quantum Monte Carlo simulations, the reduction of noise by a factor of two incurs a simulation cost of a factor of four. In this paper, we relate certain imaginary-time response functions to an inner product on the space of linear operators on Fock space. We then show that data with noise typically does not respect the positive definiteness of its associated Gramian. The Gramian has the structure of a Hankel matrix. As a method for denoising noisy data, we introduce an alternating projection algorithm that finds the closest positive definite Hankel matrix consistent with noisy data. We test our methodology at the example of fermion Green's functions for continuous-time quantum Monte Carlo data and show remarkable improvements of the error, reducing noise by a factor of up to 20 in practical examples. We argue that Hankel projections should be used whenever finite-temperature imaginary-time data of response functions with errors is analyzed, be it in the context of quantum Monte Carlo, quantum computing, or in approximate semianalytic methodologies.

cond-mat.str-el↗

arXiv2024

ZipGait: Bridging Skeleton and Silhouette with Diffusion Model for Advancing Gait Recognition

Current gait recognition research predominantly focuses on extracting appearance features effectively, but the performance is severely compromised by the vulnerability of silhouettes under unconstrained scenes. Consequently, numerous studies have explored how to harness information from various models, particularly by sufficiently utilizing the intrinsic information of skeleton sequences. While these model-based methods have achieved significant performance, there is still a huge gap compared to appearance-based methods, which implies the potential value of bridging silhouettes and skeletons. In this work, we make the first attempt to reconstruct dense body shapes from discrete skeleton distributions via the diffusion model, demonstrating a new approach that connects cross-modal features rather than focusing solely on intrinsic features to improve model-based methods. To realize this idea, we propose a novel gait diffusion model named DiffGait, which has been designed with four specific adaptations suitable for gait recognition. Furthermore, to effectively utilize the reconstructed silhouettes and skeletons, we introduce Perception Gait Integration (PGI) to integrate different gait features through a two-stage process. Incorporating those modifications leads to an efficient model-based gait recognition framework called ZipGait. Through extensive experiments on four public benchmarks, ZipGait demonstrates superior performance, outperforming the state-of-the-art methods by a large margin under both cross-domain and intra-domain settings, while achieving significant plug-and-play performance improvements.

cs.CV↗

arXiv2024

TS-SAM: Fine-Tuning Segment-Anything Model for Downstream Tasks

Adapter based fine-tuning has been studied for improving the performance of SAM on downstream tasks. However, there is still a significant performance gap between fine-tuned SAMs and domain-specific models. To reduce the gap, we propose Two-Stream SAM (TS-SAM). On the one hand, inspired by the side network in Parameter-Efficient Fine-Tuning (PEFT), we designed a lightweight Convolutional Side Adapter (CSA), which integrates the powerful features from SAM into side network training for comprehensive feature fusion. On the other hand, in line with the characteristics of segmentation tasks, we designed Multi-scale Refinement Module (MRM) and Feature Fusion Decoder (FFD) to keep both the detailed and semantic features. Extensive experiments on ten public datasets from three tasks demonstrate that TS-SAM not only significantly outperforms the recently proposed SAM-Adapter and SSOM, but achieves competitive performance with the SOTA domain-specific models. Our code is available at: https://github.com/maoyangou147/TS-SAM.

cs.CV↗

arXiv2024

Reinforcement Learning With Sparse-Executing Actions via Sparsity Regularization

Reinforcement learning (RL) has demonstrated impressive performance in decision-making tasks like embodied control, autonomous driving and financial trading. In many decision-making tasks, the agents often encounter the problem of executing actions under limited budgets. However, classic RL methods typically overlook the challenges posed by such sparse-executing actions. They operate under the assumption that all actions can be taken for a unlimited number of times, both in the formulation of the problem and in the development of effective algorithms. To tackle the issue of limited action execution in RL, this paper first formalizes the problem as a Sparse Action Markov Decision Process (SA-MDP), in which specific actions in the action space can only be executed for a limited time. Then, we propose a policy optimization algorithm, Action Sparsity REgularization (ASRE), which adaptively handles each action with a distinct preference. ASRE operates through two steps: First, ASRE evaluates action sparsity by constrained action sampling. Following this, ASRE incorporates the sparsity evaluation into policy learning by way of an action distribution regularization. We provide theoretical identification that validates the convergence of ASRE to a regularized optimal value function. Experiments on tasks with known sparse-executing actions, where classical RL algorithms struggle to train policy efficiently, ASRE effectively constrains the action sampling and outperforms baselines. Moreover, we present that ASRE can generally improve the performance in Atari games, demonstrating its broad applicability.

cs.LG↗

arXiv2024

Spatially covariant gravity with nonmetricity

Scalar fields play an important role in constructing modified gravity theories. In the case of a single scalar field with timelike gradient, the corresponding Lagrangian in the unitary gauge takes the form of spatially covariant gravity (SCG), which is proved useful in analyzing and extending the generally covariant theories. In this work, we apply the SCG method to the scalar-nonmetricity theory, of which the Lagrangian is built of the nonmetricity tensor and a scalar field. We derive the 3+1 decomposition of the geometric quantities and especially covariant derivatives of the scalar field up to the third order in the presence of a nonvanishing nonmetricity tensor. By fixing the unitary gauge, the resulting Lagrangian takes the form of a SCG with nonmetricity, in which all the ingredients are spatial tensors. We then exhaust the scalar monomials of SCG with nonmetricity up to $d=3$ with $d$ the total number of derivatives. Since the disformation tensor plays as an auxiliary variable, we take the Lagrangian with $d=2$ as an example to show that after solving the disformation tensor, we can get an effective SCG theory for the metric variables but with modified coefficients. Our results provides a novel approach to extending the scalar-nonmetricity theory.

gr-qc↗

arXiv2024

Contact interaction study of proton parton distributions

Using a symmetry-preserving formulation of a vector$\,\times\,$vector contact interaction (SCI) and treating the proton as a quark + interacting-diquark bound state, whose structure is obtained by solving a Poincaré-covariant Faddeev equation, we provide a comprehensive, coherent set of predictions for unpolarised and polarised proton parton distribution functions (DFs): valence, glue, and four-flavour separated sea. The results enable many themes to be addressed, including: the asymmetry of antimatter in the proton; the neutron:proton structure function ratio; helicity retention in hard scattering processes; the charm quark momentum fraction; the sign and size of the polarised gluon DF; and the origin of the proton spin. In all cases where sound analyses of data are available, SCI predictions are semiquantitatively in agreement with the results. Those mismatches which exist are typically attributable to the momentum-independence of the underlying interaction. Judiciously interpreted, the SCI delivers a sound and insightful explanation of proton structure as expressed in DFs.

hep-ph↗

arXiv2024

UnmixingSR: Material-aware Network with Unsupervised Unmixing as Auxiliary Task for Hyperspectral Image Super-resolution

Deep learning-based (DL-based) hyperspectral image (HIS) super-resolution (SR) methods have achieved remarkable performance and attracted attention in industry and academia. Nonetheless, most current methods explored and learned the mapping relationship between low-resolution (LR) and high-resolution (HR) HSIs, leading to the side effect of increasing unreliability and irrationality in solving the ill-posed SR problem. We find, quite interestingly, LR imaging is similar to the mixed pixel phenomenon. A single photodetector in sensor arrays receives the reflectance signals reflected by a number of classes, resulting in low spatial resolution and mixed pixel problems. Inspired by this observation, this paper proposes a component-aware HSI SR network called UnmixingSR, in which the unsupervised HU as an auxiliary task is used to perceive the material components of HSIs. We regard HU as an auxiliary task and incorporate it into the HSI SR process by exploring the constraints between LR and HR abundances. Instead of only learning the mapping relationship between LR and HR HSIs, we leverage the bond between LR abundances and HR abundances to boost the stability of our method in solving SR problems. Moreover, the proposed unmixing process can be embedded into existing deep SR models as a plug-in-play auxiliary task. Experimental results on hyperspectral experiments show that unmixing process as an auxiliary task incorporated into the SR problem is feasible and rational, achieving outstanding performance. The code is available at

eess.IV↗

arXiv2024

Hindsight Preference Learning for Offline Preference-based Reinforcement Learning

Offline preference-based reinforcement learning (RL), which focuses on optimizing policies using human preferences between pairs of trajectory segments selected from an offline dataset, has emerged as a practical avenue for RL applications. Existing works rely on extracting step-wise reward signals from trajectory-wise preference annotations, assuming that preferences correlate with the cumulative Markovian rewards. However, such methods fail to capture the holistic perspective of data annotation: Humans often assess the desirability of a sequence of actions by considering the overall outcome rather than the immediate rewards. To address this challenge, we propose to model human preferences using rewards conditioned on future outcomes of the trajectory segments, i.e. the hindsight information. For downstream RL optimization, the reward of each step is calculated by marginalizing over possible future outcomes, the distribution of which is approximated by a variational auto-encoder trained using the offline dataset. Our proposed method, Hindsight Preference Learning (HPL), can facilitate credit assignment by taking full advantage of vast trajectory data available in massive unlabeled datasets. Comprehensive empirical studies demonstrate the benefits of HPL in delivering robust and advantageous rewards across various domains. Our code is publicly released at https://github.com/typoverflow/WiseRL.

cs.LG↗

arXiv2024

Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models

Low sample efficiency is an enduring challenge of reinforcement learning (RL). With the advent of versatile large language models (LLMs), recent works impart common-sense knowledge to accelerate policy learning for RL processes. However, we note that such guidance is often tailored for one specific task but loses generalizability. In this paper, we introduce a framework that harnesses LLMs to extract background knowledge of an environment, which contains general understandings of the entire environment, making various downstream RL tasks benefit from one-time knowledge representation. We ground LLMs by feeding a few pre-collected experiences and requesting them to delineate background knowledge of the environment. Afterward, we represent the output knowledge as potential functions for potential-based reward shaping, which has a good property for maintaining policy optimality from task rewards. We instantiate three variants to prompt LLMs for background knowledge, including writing code, annotating preferences, and assigning goals. Our experiments show that these methods achieve significant sample efficiency improvements in a spectrum of downstream tasks from Minigrid and Crafter domains.

cs.CL↗

arXiv2024

Quantum voting machine encoded with microwave photons

We propose a simple quantum voting machine using microwave photon qubit encoding, based on a setup comprising multiple microwave cavities and a coupled superconducting flux qutrit. This approach primarily relies on a multi-control single-target quantum phase gate. The scheme offers operational simplicity, requiring only a single step, while ensuring verifiability through the measurement of a single qubit phase information to obtain the voting results. And it provides voter anonymity, as the voting outcome is solely tied to the total number of affirmative votes. Our quantum voting machine also has scalability in terms of the number of voters. Additionally, the physical realization of the quantum voting machine is general and not limited to circuit QED. Quantum voting machine can be implemented as long as the multi-control single-phase quantum phase gate is realized in other physical systems. Numerical simulations indicate the feasibility of this quantum voting machine within the current quantum technology.

quant-ph↗

arXiv2024

Transferable Reward Learning by Dynamics-Agnostic Discriminator Ensemble

Recovering reward function from expert demonstrations is a fundamental problem in reinforcement learning. The recovered reward function captures the motivation of the expert. Agents can imitate experts by following these reward functions in their environment, which is known as apprentice learning. However, the agents may face environments different from the demonstrations, and therefore, desire transferable reward functions. Classical reward learning methods such as inverse reinforcement learning (IRL) or, equivalently, adversarial imitation learning (AIL), recover reward functions coupled with training dynamics, which are hard to be transferable. Previous dynamics-agnostic reward learning methods rely on assumptions such as that the reward function has to be state-only, restricting their applicability. In this work, we present a dynamics-agnostic discriminator-ensemble reward learning method (DARL) within the AIL framework, capable of learning both state-action and state-only reward functions. DARL achieves this by decoupling the reward function from training dynamics, employing a dynamics-agnostic discriminator on a latent space derived from the original state-action space. This latent space is optimized to minimize information on the dynamics. We moreover discover the policy-dependency issue of the AIL framework that reduces the transferability. DARL represents the reward function as an ensemble of discriminators during training to eliminate policy dependencies. Empirical studies on MuJoCo tasks with changed dynamics show that DARL better recovers the reward function and results in better imitation performance in transferred environments, handling both state-only and state-action reward scenarios.

cs.LG↗

arXiv2024

Green/WeakCoupling: Implementation of fully self-consistent finite-temperature many-body perturbation theory for molecules and solids

The accurate ab initio simulation of molecules and periodic solids with diagrammatic perturbation theory is an important task in quantum chemistry, condensed matter physics, and materials science. In this article, we present the WeakCoupling module of the open-source software package Green, which implements fully self-consistent diagrammatic weak coupling simulations, capable of dealing with real materials in the finite-temperature formalism. The code is licensed under the permissive MIT license. We provide self-consistent GW (scGW) and self-consistent second-order Green's function perturbation theory (GF2) solvers, analysis tools, and post-processing methods. This paper summarizes the theoretical methods implemented and provides background, tutorials and practical instructions for running simulations.

cond-mat.mtrl-sci↗

arXiv2024

Topological Directional Coupler

Interferometers and beam splitters are fundamental building blocks for photonic neuromorphic and quantum computing machinery. In waveguide-based photonic integrated circuits, beam-splitting is achieved with directional couplers that rely on transition regions where the waveguides are adiabatically bent to suppress back-reflection. We present a novel, compact approach to introducing guided mode coupling. By leveraging multimodal domain walls between microwave topological photonic crystals, we use the photonic-spin-conservation to suppress back-reflection while relaxing the topological protection of the valley degree of freedom to implement tunable beam splitting. Rapid advancements in chip-scale topological photonics suggest that the proposed simultaneous utilization of multiple topological degrees of freedom could benefit the development of novel photonic computing platforms.

cond-mat.mes-hall↗

arXiv2024

Asteroid Kamo`oalewa's journey from the lunar Giordano Bruno crater to Earth 1:1 resonance

Among the nearly 30,000 known near-Earth asteroids (NEAs), only tens of them possess Earth co-orbital characteristics with semi-major axes $\sim$1 au. In particular, 469219 Kamo`oalewa (2016 HO3), upcoming target of China's Tianwen-2 asteroid sampling mission, exhibits a meta-stable 1:1 mean-motion resonance with Earth. Intriguingly, recent ground-based observations show that Kamo`oalewa has spectroscopic characteristics similar to space-weathered lunar silicates, hinting at a lunar origin instead of an asteroidal one like the vast majority of NEAs. Here we use numerical simulations to demonstrate that Kamo`oalewa's physical and orbital properties are compatible with a fragment from a crater larger than 10--20 km formed on the Moon in the last few million years. The impact could have ejected sufficiently large fragments into heliocentric orbits, some of which could be transferred to Earth 1:1 resonance and persist today. This leads us to suggest the young lunar crater Giordano Bruno (22 km diameter, 1--10 Ma age) as the most likely source, linking a specific asteroid in space to its source crater on the Moon. The hypothesis will be tested by the Tianwen-2 mission when it returns a sample of Kamo`oalewa. And the upcoming NEO Surveyor mission will possibly help us to identify such a lunar-derived NEA population.

astro-ph.EP↗

arXiv2024

Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning

Model-based methods in reinforcement learning offer a promising approach to enhance data efficiency by facilitating policy exploration within a dynamics model. However, accurately predicting sequential steps in the dynamics model remains a challenge due to the bootstrapping prediction, which attributes the next state to the prediction of the current state. This leads to accumulated errors during model roll-out. In this paper, we propose the Any-step Dynamics Model (ADM) to mitigate the compounding error by reducing bootstrapping prediction to direct prediction. ADM allows for the use of variable-length plans as inputs for predicting future states without frequent bootstrapping. We design two algorithms, ADMPO-ON and ADMPO-OFF, which apply ADM in online and offline model-based frameworks, respectively. In the online setting, ADMPO-ON demonstrates improved sample efficiency compared to previous state-of-the-art methods. In the offline setting, ADMPO-OFF not only demonstrates superior performance compared to recent state-of-the-art offline approaches but also offers better quantification of model uncertainty using only a single ADM.

cs.LG↗

arXiv2024

BWArea Model: Learning World Model, Inverse Dynamics, and Policy for Controllable Language Generation

Large language models (LLMs) have catalyzed a paradigm shift in natural language processing, yet their limited controllability poses a significant challenge for downstream applications. We aim to address this by drawing inspiration from the neural mechanisms of the human brain, specifically Broca's and Wernicke's areas, which are crucial for language generation and comprehension, respectively. In particular, Broca's area receives cognitive decision signals from Wernicke's area, treating the language generation as an intricate decision-making process, which differs from the fully auto-regressive language generation of existing LLMs. In a similar vein, our proposed system, the BWArea model, conceptualizes language generation as a decision-making task. This model has three components: a language world model, an inverse dynamics model, and a cognitive policy. Like Wernicke's area, the inverse dynamics model is designed to deduce the underlying cognitive intentions, or latent actions, behind each token. The BWArea model is amenable to both pre-training and fine-tuning like existing LLMs. With 30B clean pre-training tokens, we have trained a BWArea model, which achieves competitive performance with LLMs of equal size (1B parameters). Unlike fully auto-regressive LLMs, its pre-training performance does not degenerate if dirty data unintentionally appears. This shows the advantage of a decomposed structure of BWArea model in reducing efforts in laborious data selection and labeling. Finally, we reveal that the BWArea model offers enhanced controllability via fine-tuning the cognitive policy with downstream reward metrics, thereby facilitating alignment with greater simplicity. On 9 out of 10 tasks from two suites, TextWorld and BigBench Hard, our method shows superior performance to auto-regressive LLMs.

cs.CL↗