arXiv subjects

Kai Shao

Publications and source records attributed to Kai Shao.

11 recordsLinked to original sources

arXiv2026

Suppression of Non-Hermitian Skin Effect by Pseudomagnetic Field in Honeycomb Lattice

Magnetic suppression of the non-Hermitian skin effect (NHSE) offers a viable route for its control. While the NHSE has been realized in various classical-wave platforms, only pseudomagnetic fields (PMFs), which preserve time-reversal symmetry, can be engineered in such systems; however, their interplay with the NHSE remains underexplored. Here, we investigate this interplay in a non-Hermitian honeycomb lattice by considering two distinct mechanisms for generating PMFs: monotonically increasing strain and spatially modulated gain and loss. We show that in both scenarios, PMFs can efficiently suppress the NHSE by driving skin modes into the bulk, accompanied by a reduction of the skin topological area and a contraction of the complex-energy spectrum under periodic boundary conditions. This mechanism is insensitive to boundary details and holds for various edge terminations, including zigzag, bearded, armchair, and twig edges. Our results establish PMFs as a versatile and effective means to control the NHSE, and point toward feasible implementations in a broad range of artificial platforms, including photonic and acoustic metamaterials as well as topolectrical circuits.

cond-mat.other↗

arXiv2025

Altermagnetic Spin Precession and Spin Transistor

Altermagnets hold great potential for spintronic applications, yet their intrinsic spin dynamics and associated transport properties remain largely unexplored. Here, we investigate spin-resolved quantum transport in a multi-terminal setup based on a $d$-wave altermagnet. It is found that the altermagnetic spin splitting in momentum space induces an interesting spin precession in two-dimensional real space, giving rise to characteristic spin patterns. This altermagnetic spin precession manifests as a spatial modulation of the transverse Hall-like voltage, whose oscillation period provides a direct measure of the spin-splitting strength. When the altermagnetism is electrically tunable, the proposed setup functions as a prototype for a highly efficient spin transistor. The key physical effects are shown to be robust against dephasing and crystalline warping. Our work not only identifies a fingerprint signature of altermagnets, offering a direct probe of the altermagnetic spin splitting, but also represents an important step toward bridging their fundamental physics with practical spintronic applications.

cond-mat.mes-hall↗

arXiv2025

Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics

Mean field games (MFGs) have emerged as a powerful framework for modeling interactions in large-scale multi-agent systems. Despite recent advancements in reinforcement learning (RL) for MFGs, existing methods are typically limited to finite spaces or stationary models, hindering their applicability to real-world problems. This paper introduces a novel deep reinforcement learning (DRL) algorithm specifically designed for non-stationary continuous MFGs. The proposed approach builds upon a Fictitious Play (FP) methodology, leveraging DRL for best-response computation and supervised learning for average policy representation. Furthermore, it learns a representation of the time-dependent population distribution using a Conditional Normalizing Flow. To validate the effectiveness of our method, we evaluate it on three different examples of increasing complexity. By addressing critical limitations in scalability and density approximation, this work represents a significant advancement in applying DRL techniques to complex MFG problems, bringing the field closer to real-world multi-agent systems.

cs.LG↗

arXiv2025

Universal valley filtering via uniform dissipation and velocity contrast

Valley, as a ubiquitous degree of freedom in lattices, has found wide applications in both electronic and classical-wave devices in recent years. However, achieving valley-polarized states, a prerequisite for valley-based operations, still remains challenging. Here, we propose and experimentally demonstrate a universal non-Hermitian mechanism for valley filtering using only uniform background dissipation, which creates a propagation length contrast between valleys through their intrinsic group velocity differences. We implement this concept in an acoustic crystal, observing switchable and robust valley polarization of sound through large-scale field mapping. Remarkably, our approach is solely based on uniform loss, without the need for any special lattice structures, tailored excitations, or external fields. We further provide designs of our non-Hermitian valley filter on photonic and electronic platforms. Our results offer a simple and effective solution to valley-polarized state generation and may advance the development of novel valley-based devices in both classical and quantum regimes.

cond-mat.mes-hall↗

arXiv2025

Reinforcement Learning for Finite Space Mean-Field Type Games

Mean field type games (MFTGs) describe Nash equilibria between large coalitions: each coalition consists of a continuum of cooperative agents who maximize the average reward of their coalition while interacting non-cooperatively with a finite number of other coalitions. Although the theory has been extensively developed, we are still lacking efficient and scalable computational methods. Here, we develop reinforcement learning methods for such games in a finite space setting with general dynamics and reward functions. We start by proving that the MFTG solution yields approximate Nash equilibria in finite-size coalition games. We then propose two algorithms. The first is based on the quantization of mean-field spaces and Nash Q-learning. We provide convergence and stability analysis. We then propose a deep reinforcement learning algorithm, which can scale to larger spaces. Numerical experiments in 4 environments with mean-field distributions of dimension up to $200$ show the scalability and efficiency of the proposed method.

cs.GT↗

arXiv2024

Multimodal Physiological Signals Representation Learning via Multiscale Contrasting for Depression Recognition

Depression recognition based on physiological signals such as functional near-infrared spectroscopy (fNIRS) and electroencephalogram (EEG) has made considerable progress. However, most existing studies ignore the complementarity and semantic consistency of multimodal physiological signals under the same stimulation task in complex spatio-temporal patterns. In this paper, we introduce a multimodal physiological signals representation learning framework using Siamese architecture via multiscale contrasting for depression recognition (MRLMC). First, fNIRS and EEG are transformed into different but correlated data based on a time-domain data augmentation strategy. Then, we design a spatio-temporal contrasting module to learn the representation of fNIRS and EEG through weight-sharing multiscale spatio-temporal convolution. Furthermore, to enhance the learning of semantic representation associated with stimulation tasks, a semantic consistency contrast module is proposed, aiming to maximize the semantic similarity of fNIRS and EEG. Extensive experiments on publicly available and self-collected multimodal physiological signals datasets indicate that MRLMC outperforms the state-of-the-art models. Moreover, our proposed framework is capable of transferring to multimodal time series downstream tasks.

cs.LG↗

arXiv2024

A Non-Hermitian Moiré Valley Filter

A valley filter capable of generating a valley-polarized current is a crucial element in valleytronics, yet its implementation remains challenging. Here, we propose a valley filter made of a graphene bilayer which exhibits a 1D moiré pattern in the overlapping region of the two layers controlled by heterostrain. In the presence of a lattice modulation between layers, electrons propagating in one layer can have valley-dependent dissipation due to valley asymmetric interlayer coupling, thus giving rise to a valley-polarized current. Such a process can be described by an effective non-Hermitian theory, in which the valley filter is driven by a valley-resolved non-Hermitian skin effect. Nearly 100\% valley-polarization can be achieved within a wide parameter range and the functionality of the valley filter is electrically tunable. The non-Hermitian topological scenario of the valley filter ensures high tolerance against imperfections such as disorder and edge defects. Our work opens a new route for efficient and robust valley filters while significantly relaxing the stringent implementation requirements.

cond-mat.mes-hall↗

arXiv2022

Vis2Mus: Exploring Multimodal Representation Mapping for Controllable Music Generation

In this study, we explore the representation mapping from the domain of visual arts to the domain of music, with which we can use visual arts as an effective handle to control music generation. Unlike most studies in multimodal representation learning that are purely data-driven, we adopt an analysis-by-synthesis approach that combines deep music representation learning with user studies. Such an approach enables us to discover \textit{interpretable} representation mapping without a huge amount of paired data. In particular, we discover that visual-to-music mapping has a nice property similar to equivariant. In other words, we can use various image transformations, say, changing brightness, changing contrast, style transfer, to control the corresponding transformations in the music domain. In addition, we released the Vis2Mus system as a controllable interface for symbolic music generation.

cs.SD↗

arXiv2022

Vortices and cosmic strings in a generalized Born-Infeld model

In this paper, we consider two types of topological solitons in a generalized Born-Infeld-Higgs model. We explore the self-dual structure of the model and prove the existence of planar vortex solutions. Furthermore, we couple the system with the Einstein equations and study the cosmic strings problem over $\mathbb R^{1,1}\times S$, where $S$ is a Riemann surface. We prove the existence of cosmic string solutions when $S$ is noncompact. We also discuss the decay estimates for vortices and cosmic strings at infinity and show that the minimal energy is quantized and depends on the number of vortices and strings, respectively.

math-ph↗

arXiv2022

Cyclotron quantization and mirror-time transition on nonreciprocal lattices

Unidirectional transport and localized cyclotron motion are two opposite physical phenomena. Here, we study the interplay effects between them on nonreciprocal lattices subject to a magnetic field. We show that, in the long-wavelength limit, the trajectories of the wave packets always form closed orbits in four-dimensional (4D) complex space. Therefore, the semiclassical quantization rules persist despite the nonreciprocity, which preserves real Landau levels. We predict a different type of non-Hermitian spectral transition induced by the spontaneous breaking of the combined mirror-time reversal ($\mathcal{MT}$) symmetry, which generally exists in such systems. An order parameter is proposed to describe the $\mathcal{MT}$ phase transition, not only to determine the $\mathcal{MT}$ phase boundary but also to quantify the degree of $\mathcal{MT}$-symmetry breaking. Such an order parameter can be generally applied to all types of non-Hermitian phase transitions.

cond-mat.mes-hall↗

arXiv2022

On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning

A simple and natural algorithm for reinforcement learning (RL) is Monte Carlo Exploring Starts (MCES), where the Q-function is estimated by averaging the Monte Carlo returns, and the policy is improved by choosing actions that maximize the current estimate of the Q-function. Exploration is performed by "exploring starts", that is, each episode begins with a randomly chosen state and action, and then follows the current policy to the terminal state. In the classic book on RL by Sutton & Barto (2018), it is stated that establishing convergence for the MCES algorithm is one of the most important remaining open theoretical problems in RL. However, the convergence question for MCES turns out to be quite nuanced. Bertsekas & Tsitsiklis (1996) provide a counter-example showing that the MCES algorithm does not necessarily converge. Tsitsiklis (2002) further shows that if the original MCES algorithm is modified so that the Q-function estimates are updated at the same rate for all state-action pairs, and the discount factor is strictly less than one, then the MCES algorithm converges. In this paper we make headway with the original and more efficient MCES algorithm given in Sutton & Barto (1998), establishing almost sure convergence for Optimal Policy Feed-Forward MDPs, which are MDPs whose states are not revisited within any episode when using an optimal policy. Such MDPs include a large class of environments such as all deterministic environments and all episodic environments with a timestep or any monotonically changing values as part of the state. Different from the previous proofs using stochastic approximations, we introduce a novel inductive approach, which is very simple and only makes use of the strong law of large numbers.

cs.LG↗