Papers

We combine Reimann's spectral typicality theorem – a modern formulation of quantum ergodicity – with the framework of Interval Quantum Mechanics (IQM). In IQM, quantum states are represented not by points but by quantum parcels: weak open convex sets of density matrices defined by finitely many expectation intervals. Such parcels are the exact mathematical representation of the epistemic knowledge obtained from finite-precision measurements of macroscopic observables. We prove that for a single parcel in which every state has large effective dimension (a condition that ensures thermalization), the expectation interval of any bounded observable becomes concentrated around the microcanonical value for most late times. The asymptotic bound depends only on the minimal effective dimension within the parcel, not on its detailed shape. For a double parcel \((O_1,O_2)\) with both components contained in an energy shell, separated by a conserved quantity \(Q^*\) that is supported on the range of the measurement projector, we show that the expectation intervals of both parcels become concentrated near the microcanonical values of bounded observables, the separation is preserved exactly, and the updated double parcel after a fuzzy measurement remains valid.

This paper investigates the optimization mechanisms of non-convex Model Predictive Control (MPC) using the Maximum Entropy Differential Dynamic Programming (ME-DDP) framework. Navigating non-convex cost landscapes induced by nonlinear dynamics, multiple obstacles, etc. remains a fundamental challenge in robotics, where gradient-based methods frequently converge to suboptimal local minima. We demonstrate a dual-step optimization mechanism designed to overcome these traps. (1) an initial phase of using DDP to exploit the gradient of the cost landscape, followed by (2) disruption of the optimization via sampling from policies characterized by the inverse Hessian of the action-value function. We provide a rigorous analysis of this sampling mechanism of three ME-DDP variants: Unimodal Gaussian ME-DDP, Multimodal Gaussian ME-DDP, and Stein Variational DDP. Furthermore, with navigation tasks of four robotic systems under cluttered environments, we conduct extensive benchmarking of three variants of the ME-DDP, against deterministic DDP, and one of the most successful sampling-based schemes, Model Predictive Path Integral (MPPI) control with three policy parameterizations and update laws that correspond to those of ME-DDPs. The results show that in low-dimensional systems where the cost landscapes are relatively simple and local information is sufficiently representative, our framework consistently outperforms MPPIs. In high-dimensional systems, MPPI can occasionally discover aggressive maneuvers that enable it to steer the systems faster than DDP-based methods, whereas our method maintains a higher, more stable success rate. Finally, we validate the practical efficacy of the framework through hardware experiments with a quadrotor navigating a dense, non-convex obstacle field, confirming the robustness of the proposed framework for real-world deployment.

We prove that, over any ring $R$, the supremum of the projective dimensions of the flat left $R$-modules coincides with the supremum of the Gorenstein projective dimensions of the Gorenstein flat left $R$-modules. As a consequence, we obtain new characterizations of left $n$-perfect rings in terms of Gorenstein projective, Ding projective, and projectively coresolved Gorenstein flat dimensions, extending results by Emmanouil and Dalezios and by Christensen, Estrada, and Thompson. We also introduce Gorenstein analogues of several classical homological invariants and study their relationships with the classical ones, identifying conditions under which they coincide with the classical invariants. Finally, we obtain characterizations of left weakly $n$-$\Sigma$-cotorsion rings introduced by Cortés-Izurdiaga, Estrada and Fresneda in terms of Gorenstein classes of modules.

In this paper, we introduce and study the notion of Q-filters in bounded lattices.

Using the concepts of Eulerian-spanning set and coboundary operator, we generalize Hadlock's conversion of the maxcut problem on planar graphs to one on general graphs with non-negative weights. Using our conversion, we can explore algorithms for maxcut beyond the class of planar graphs. We obtain a Fixed-Parameter Tractable algorithm for $k$-contraction apex graphs. Specifically, our algorithm can be applied to graphs with crossing number $k$, giving an $O(2^k(n+k)^{3/2}\log (n+k))$-time algorithm that matches the best known results when restricted to non-negative weights.

Let $\kappa^{\prime}(G)$ be the edge-connectivity of the graph $G$. The strength of $G$, denoted by $\overline{\kappa}^{\prime}(G)$, is the maximum edge-connectivity of its subgraphs. A simple graph $G$ is called $k$-edge-maximal if $\overline{\kappa}^{\prime}(G) \leq k$ but for any edge $e$ not in $G$, $\overline{\kappa}^{\prime}(G+e) \geq k+1$. In this paper, we propose the concepts of kernel and closure of a graph and discuss the properties of closure. Utilizing these properties, we present the necessary and sufficient condition for a graph to be $k$-edge-maximal, which refines the results in [J. Graph Theory 14 (1990) 187–197], and prove that there exists a $k$-edge-maximal graph of order $n$ with $m$ edges if and only if $m=(n-1)k-\binom{k}{2}r$, for some integer $r$ with $1\leq r\leq \left\lfloor \frac{n}{k+2}\right\rfloor$. Furthermore, we characterize the structure of $k$-edge-maximal graphs with a given number of edges.

While Large Language Models (LLMs) have recently shown promise in Automated Heuristic Design (AHD), existing methods typically generate and evolve heuristics as a single operator or search strategy, limiting their ability to model strong coupling among multiple decision substructures in problems such as the Traveling Thief Problem (TTP) and the Traveling Purchaser Problem (TPP). In this work, we propose CoEvo-AHD, an LLM-driven dual-population co-evolutionary framework for automated heuristic design in coupled combinatorial optimization. Unlike prior methods that evolve individual heuristics in isolation, CoEvo-AHD leverages LLMs to co-evolve two closely related operator populations. A cooperative evaluation mechanism explicitly captures interactions between route and selection operators, while pairwise scoring and synergistic joint crossover help discover complementary operator logic for joint improvement across coupled decision subspaces. We further design a tool-invocation environment library that encapsulates frequently used core operations, such as local-search delta computation, into callable functions, enabling LLM-generated operators to use standardized interfaces instead of reimplementing inefficient and error-prone problem-specific loops. Experiments on TTP and TPP show that CoEvo-AHD automatically discovers cooperative heuristic combinations and achieves competitive solution quality against traditional heuristics.

This paper is concerned with the Liouville-type problem for the stationary fractional compressible magnetohydrodynamics (MHD) equations. The main difficulty comes from the nonlocal fractional Laplace operator $(-\Delta)^s$. To overcome it, we combine the Caffarelli-Silvestre extension technique with truncation arguments. Under suitable regularity and decay conditions, we prove that the only solution is trivial, establishing a Liouville-type theorem.

High-dimensional environmental systems contain variables that may be predictive, causally informative, physically coupled, or redundant, and these roles need not coincide. We study this distinction in precipitation dynamics using High-Resolution Rapid Refresh atmospheric fields and Multi-Radar Multi-Sensor precipitation observations over the Southwestern United States. We introduce a projection-based, variable-level formulation of entropic regression that identifies candidate causal parents without constructing a global nonlinear expansion library. Ten physical variables are selected sequentially by conditional-information forward selection using linear regression projections. A quadratic library is then formed only over those variables, followed by two sequential variable-block eliminations that produce an eight-variable local representation. Applied across 1227 precipitation-guided superpixels, the method recovers a compact and spatially recurrent causal structure. Under the same final cardinality, entropic regression yields a substantially more concentrated recurrence profile than transfer entropy and causation entropy. Six variables exceed a recurrence threshold of 0.25: land-surface moisture availability, composite reflectivity, geometric vertical velocity, wind speed, convective available potential energy, and maximum upward vertical velocity. Predictive models restricted to these variables achieve strong one-hour discrimination of precipitation occurrence, with an area under the receiver operating characteristic curve of 0.948, while pointwise intensity prediction remains more limited. The results provide a scalable variable-level procedure for high-dimensional causal discovery and show that recurrent causal relevance and predictive sufficiency are distinct properties of a reduced dynamical representation.

Motivated by the small-scale viewpoint of Roff and Yoshinaga, we study finite metric spaces whose scaled copies collapse to a single point while their magnitude remembers how the collapse takes place. The limit metric space is geometrically indistinguishable from a point, but the magnitude function can detect differences in the path of collapse. We introduce a four-parameter family of cyclic two-chunk finite metric spaces, compute their magnitude explicitly, and use the formula to construct balanced examples whose small-scale magnitude is less than one. In particular, we exhibit a twelve-point finite metric space satisfying lim_{t -> 0+} Mag(tX) = 44/59 < 1. The guiding question and the terminology around the one-point property come from Leinster's magnitude of finite metric spaces and from Roff–Yoshinaga's work on

Let $a$, $m$ be positive integers, $1<a<m$, $\gcd(a,m)=1$. We determine the location of a shortest vector in the $2$-dimensional lattices $$ \Lambda(a,m) = \{(x, y)\in\mathbb{Z}\times\mathbb{Z}\mid ax + y\equiv 0~(\bmod\,m)\}. $$ This confirms a conjecture of Han Wu and Guangwu Xu.

Low-precision pretraining (FP8, MXFP4, NVFP4) is now standard for frontier language models, yet the literature is almost entirely achievability – algorithms and empirical scaling laws – with no matching characterization of what is information-theoretically possible. We study a B-bit quantized stochastic first-order oracle: an optimizer interacts for T rounds and receives, each round, a B-bit adaptive public-coin description of its stochastic gradient. Our main contribution is an exact reduction from optimizing a strongly convex quadratic family to interactively compressed Gaussian mean estimation – under the B-bit oracle the query carries no information, so optimization collapses exactly onto a sequential distributed-estimation problem. This yields two unconditional lower bounds, a communication bound TB = Omega(d) and a statistical bound T = Omega(sigma^2 d / eps^2), and the sharp product-form bound T = Omega((sigma^2 d / eps^2) max{1, d/B}). The product form is also unconditional: a B-bit transcript carries at most O(TB / sigma^2) of Fisher trace about the mean, so bits rather than dimension limit the recoverable information, and combined with the multivariate van Trees inequality this gives the bound directly, without bounded-likelihood-ratio truncation. We give a near-matching achievability result with exact per-round bit accounting under a bounded-dynamic-range oracle, tight up to a logarithmic factor; the lower bound is for truly Gaussian (unbounded) gradients, and closing this oracle gap is left open. A sequential rate-distortion perspective extends the reduction to correlated and drifting oracles and corrects an earlier conjecture: positive noise correlation raises the bound by (1+rho)/(1-rho) rather than relaxing it. The bounds give an information-theoretic baseline for any low-bit gradient path, not an optimality claim about deployed FP4 systems.

We define a bi-invariant word metric on a group using keis. We discuss whether such a word metric is trivial or non-trivial in various examples coming from group theory, dynamical systems, as well as complex and symplectic geometry.

We solve, for all sufficiently large even orders, the problem proposed by Chen et al. on sharp $A_\alpha$-spectral conditions for the existence of odd $[1,b]$-factors when $\alpha>1/2$. Chen et al. showed that every connected graph of even order $n$ with no odd $[1,b]$-factor has $A_\alpha$-spectral radius at most $\max_{1\le s\le k}\rho_\alpha(G_s)$, where $G_s=K_s\nabla\left(K_{n-(b+1)s-1}\cup(bs+1)K_1\right)$ and $k=\lfloor(n-2)/(b+1)\rfloor$. Thus the problem reduces to finding the graph with the largest $A_\alpha$-spectral radius among these obstruction graphs. We prove that, for every $\alpha\in(1/2,1)$, $\max_{1\le s\le k}\rho_\alpha(G_s)=\max\{\rho_\alpha(G_1),\rho_\alpha(G_k)\}$. Moreover, for each fixed odd $b\ge 3$ and every even $n\ge N_b=(b+1)\max\{2b+3,14\}+2$, there exists a unique $\alpha=\alpha_\ast(n,b)\in(1/2,1)$ at which $\rho_\alpha(G_1)=\rho_\alpha(G_k)$. Consequently, $G_1$ is the unique extremal graph for $1/2<\alpha<\alpha_\ast(n,b)$, both $G_1$ and $G_k$ are extremal at $\alpha=\alpha_\ast(n,b)$, and $G_k$ is the unique extremal graph for $\alpha_\ast(n,b)<\alpha<1$. This gives the exact $A_\alpha$-spectral threshold, together with the sharp exceptional graphs, for odd $[1,b]$-factors when $\alpha>1/2$ and $n\ge N_b$.

From a generating function for a Legendrian in a $1$-jet bundle, we may extract the following topological information: (1) a trivialization of the stable Gauss map, (2) the sheaf of sub-level-set stable cohomotopies, and (3) an identification of the microlocalization of the latter with the J-homomorphism image of the former. Here we show that in fact (1), (2), (3) completely classify generating functions up to the classical equivalence relations of stabilization and fiberwise diffeomorphism.

We give a spectral realization of the Robinson-Schensted-Knuth (RSK) correspondence in terms of the representation theory of the symmetric group $S_n$ and the degenerate affine Hecke algebra (AHA) $H_n$. We view RSK, which builds a pair of standard Young tableaux from a permutation, as a special case of rectification, also known as Jeu de Taquin, which turns skew tableaux into straight ones. In this framing, the initial permutation corresponds to a skew tableau of staircase shape. To interpret this in terms of representation theory, take permutations to label weight vectors in a generic $H_n$-module $V(a_1, \ldots , a_n)$, which is isomorphic to $\mathbb{C}[S_n]$ as an $S_n$-module. Writing permutations as staircases amounts to placing these weight vectors inside the regular representation of a larger symmetric group containing $S_n$; more geometrically, we push $S_n$ to the right toward infinity so its Jucys-Murphy (JM) elements have enough room to represent the external translations of $H_n$. Then, rectification corresponds to squeezing out this extra room from the left, leaving only $S_n$ and its regular JM elements as the limit of the external translations. By expressing slides via sequences of exchanges of consecutive values inside the tableau, we can model rectification by an operator acting on the regular representation. This lets us explicitly write down the change of basis between $H_n$-weight vectors and $S_n$-weight vectors, where the latter are eigenvectors of the JM elements in $S_n$ acting both on the left and on the right, and hence labeled by pairs of standard tableaux. The resulting correspondence between the labels of the weight vectors is exactly RSK.

Semantic communications which can significantly reduce spectrum consumption in wireless networks, have recently become a popular research area. When combined with wireless power transfer (WPT), semantic communications can help achieve high spectral efficiency for energy-limited devices in wireless communications. In energy-constrained and link budget-limited scenarios such as UAV networks, the integration of semantic communications and WPT enables highly energyefficient transmission mechanisms. In this paper, we investigate semantic communications in UAV-enabled WPT networks. To achieve adaptability to varying signal-to-noise ratio (SNR) and task requirements, we introduce a multi-layer hybrid bit and semantic communication framework. We adopt a semantic communication efficiency metric and aim to maximize it by jointly optimizing UAV trajectory, energy harvesting base station (EHBS) selection, user association, semantic mode selection, and energy harvesting time allocation. To address this complex longterm optimization problem, we introduce the distributional soft actor-critic (DSAC) algorithm and introduce a decision assistant to further enhance the convergence performance of DSAC. Simulation results validate the effectiveness of the proposed method and framework and demonstrate that our algorithm can achieve superior long-term optimization performance in dynamic network environments.

A gradient flow for the concentration and a $2\times 2$ tensor is constructed to describe smectic liquid crystals. The free energy consists of the entropy term and interaction term involving squared second order spatial derivatives. The entropy term incorporates the concentration in the quasi-entropy originally proposed for the tensor only, which is a strictly convex and lower semicontinuous function imposing coupled constraints between the concentration and the tensor. An evolution equation for the boundary normal derivative of the concentration is proposed in addition to the equations for the concentration and the tensor, giving an energy dissipation system. Numerical schemes are designed with emphases on using the entropy term to keep the coupled constraints, and the discretization of the boundary normal derivatives satisfying summation by parts. Existence, uniqueness, energy dissipation and error estimates are established. Numerical results indicate the efficiency and robustness of the scheme. Configurations of defects different from other layer structures are observed.

Let $G$ be a simple connected graph, and let $T_{G}(x,y)$ be the Tutte polynomial of $G$. Motivated by the works in \cite{Ma}, we, in this paper, introduce the even-left spanning forests of $G$ and odd $G$-partitionable permutations, and show that $T_{G}(2,-1)$ is equal to both the number of even-left spanning forests of $G$ and the number of odd $G$-partitionable permutations. In particular, for a complete graph $K_n$, we prove that $T_{K_{n}}(2,-1)$ is the number of alternating permutations on $\{1,2,\dots,n+1\}$, using two distinct techniques: a recurrence relation and an explicit bijection construction.

We develop a deterministic framework showing that a power-law form of semi-uniform localization of eigenfunctions (SULE) imposes strong structural constraints on lattice operators, with consequences of both spectral and dynamical nature. For instance, as spectral consequences we prove that power-law SULE yields geometric constraints on localization centers (such as their equidistribution) and quantitative bounds on eigenfunction correlators. As a dynamical consequence we obtain power-law localization in the sense of finite $q$-moments (up to a certain power $q$) of the position operator. Conversely, suitable bounds on eigenfunction correlators imply a corresponding form of power-law SULE, establishing a close connection between these notions. This highlights the role of power-law SULE as a structural mechanism governing localization beyond the exponential regime, including features typically associated with random operators, such as Anderson-type models. Our results reveal that power-law localization is intrinsically geometric: the spatial distribution of localization centers directly influences eigenfunction correlators and transport properties. As an application, we obtain power-law localization for long-range lattice operators with Stark-type potentials of sublinear growth whose spectral regime exhibits asymptotically collapsing spectral gaps and quasi-resonant structures, without relying on perturbative methods. Applications to long-range random operators are also discussed.

We study multiple point ranges for random walks on graphs, extending known asymptotic results obtained for random walks on groups. A distinctive feature is that algebraic and translation-invariance assumptions are replaced by a uniform tail condition on the first return time to the starting point. Under this condition, we obtain upper and lower bounds of linear order for the expectations of the number of sites visited at least a given number of times and the number of sites visited exactly that number of times. We also prove the corresponding almost sure bounds under a stronger condition. In spatially homogeneous transient cases, these bounds coincide and yield a strong law of large numbers. We apply these estimates to derive asymptotic results for functions of the local times.

Motivated by a recent conjecture of Bsila, Cox, Hugo, Styron and Zhuang concerning fixed points and pixed points on pattern-avoiding permutations, we prove a bivariate refinement involving descent statistics. Given a set of permutations $\Pi$, let $\mathfrak{S}_n(\Pi)$ denote the set of permutations in the symmetric group $\mathfrak{S}_n$ that avoid every element of $\Pi$ in the sense of pattern avoidance. For each set $\Pi$ appearing in their conjecture, we show that the pairs of statistics $(\mathrm{des},\mathrm{fix})$ and $(\mathrm{ides},\mathrm{pix})$ are equidistributed over $\mathfrak{S}_n(\Pi)$. Our proof is based on explicit ordinary generating functions for the corresponding pattern-avoiding classes.

Physics-Informed Neural Networks (PINNs) often train slowly or fail to converge on challenging partial differential equations (PDEs), a behavior recently linked to severely ill-conditioned loss landscapes inherited from the underlying differential operator. We study PINNs augmented with a pointwise data-fidelity term, added at a few points in the domain to the standard residual and boundary losses. We show that this supervision term acts as an operator-level preconditioner: for suitable weights, our comparison bounds guarantee a substantially smaller condition number than under the standard PINN loss, independently of how the pointwise labels are obtained. For a broad class of PDEs admitting a Feynman-Kac (FK) representation, we generate such labels by Monte Carlo averages of the FK functional, resulting in what we call “FK-PINNs", and using the excess risk decomposition approach, we derive non-asymptotic $L^2(\Omega)$-error bounds for FK-PINNs with $\tanh$ activation trained by finitely many steps of gradient descent. Along the way, we establish pseudo-dimension bounds for first- and second-order derivatives of $\tanh$ neural networks, which are of independent interest and, to the best of our knowledge, new. Numerical experiments on Poisson, Schrödinger, mean exit time, and committor problems corroborate the theory, and show that FK-PINNs can successfully solve PDEs for which standard PINNs exhibit severe failure modes.

We apply ideas of geometric measure theory and Baire category theory to topological problems, namely, to topological embeddings of compact sets into Euclidean spaces. In 1947, Borsuk constructed a Cantor set in $\mathbb R^N$, $N\geqslant 3$, such that its projection onto any $(N-1)$-plane contains an $(N-1)$-dimensional ball. This can be strengthened: a desired Cantor set can be obtained from an arbitrary Cantor set by an arbitrarily small isotopy of the space $\mathbb R^N$. The question arises: how do the dimensions of the projections of a compact set $X\subset \mathbb R^N$ behave under a typical ambient isotopy or under a typical ambient homeomorphism? (Typical in the sense of the Baire category.) We solve this problem. As a consequence, we get new criteria of tameness and wildness of a Cantor set in terms of its projections. Our main result strengthens Väisälä's theorem (1979) connecting Hausdorff dimension and Shtan'ko embedding dimension. In its turn, Väisälä's theorem extends results of Nöbeling (1931) and Szpilrajn (1937) on relationship between Hausdorff dimension and topological dimension.

We consider traveling wave solutions to a reaction–diffusion–convection equation with a combustion-type reaction term. While a necessary condition for the existence of traveling waves is $c \geq H^*:=\sup_{0<u \leq \theta} \big(-\frac{1}{u} \int_0^u h(\sigma)\,d\sigma \big)$, where $c$ denotes the wave speed, $\theta\in(0,1)$ the ignition threshold, and $h$ the convective term, the available results in \cite{DZ25,MM03} establish existence and nonexistence only under the restriction $c \geq -\min_{u\in[0,1]} h(u)$. In this note, we close this gap by covering the entire range $c\ge H^*$.

The $P(t)$-adic Littlewood conjecture is a function field analogue of the famous $p$-adic Littlewood conjecture in Diophantine approximation. In this paper, we prove that the $P(t)$-adic Littlewood conjecture fails for any irreducible polynomial $P(t)$ over any ground field of odd characteristic.

Control science is a core representative of the third industrial revolution and is so important to modern civilization. Control systems are the main subject of control science and may involve many aspects of consideration, such as hardware consideration, software consideration, operation consideration, maintenance consideration, economy consideration, society consideration. However, besides all such aspects of consideration, one aspect that is most essential to the control system is methodology consideration in mathematical sense, knowledge on which is what we refer to as control theory. Besides its importance from the mathematical perspective, control theory is even more charming as it is deeply rooted in practical applications. Charms of control theory consist in both know-why and know-how and it is the fusion of control theory and practical applications that highlights such charms. Control theory for practical applications, especially when somewhat with so-called “advanced” flavour, involves several fundamental aspects. This article introduces the Handling Control System Optimality aspect of Advanced Control Theory for Practical Applications [1,2].

In this paper, we investigate the large time behavior of solutions to the classical Timoshenko system in the whole space $\mathbb{R}$. Although the system is conservative and its natural energy is conserved in time, the transversal displacement $\varphi$ and the rotation angle $\psi$ exhibit intrinsic polynomial growths. We establish sharp $L^p-L^q$ estimates for the solutions and show that the growth mechanism originates from the interaction between quadratic oscillations and singular low-frequency amplitudes of different orders. Furthermore, we prove the optimality of the obtained growth rates under a nontrivial zeroth-moment condition on the initial data, while additional moment cancellations with a nontrivial first-moment condition lead to lower-order growth regimes. As a consequence, we derive large time asymptotic profiles related to an effective plate-type dispersive structure hidden in the low-frequency regime of the classical Timoshenko system. We also discuss the relation with the dissipative Timoshenko system through a large time vanishing dissipation limit for time-normalized solutions.

We establish a convolution formula for the characteristic polynomial of a finite geometric semilattice $M$: \[ \chi(M,st)=\sum_{X\in \underline{M}} s^{r-{\rm rk}_{\underline{M}}(X)}\chi(\underline{M}^X,t)\,\chi(M_{(X)},s), \] where $\underline{M}$ denotes the centralization of $M$, and $M_{(X)}$ denotes the localization at $X$. This generalizes a nice formula of Southerland, Southern, and Zhou, which is recovered at $s=1$. When specialized to hyperplane arrangements, the identity yields a new expansion closely related to Wang's convolution formula. We further provide a combinatorial interpretation of the convolution formula using the finite field method over $\mathbb{F}_{p^2}$ and $\mathbb{F}_p$.

We propose an energy-based nonlocal $p$-Laplacian interface problem. Neumann interface conditions are naturally formulated via the energy, while Dirichlet conditions are enforced through a penalty term. A key feature is that the model retains a sharp interface, which facilitates extension to other interface problems; we illustrate this by developing a nonlocal approximation for the $p$-Laplacian interface problem with membrane conditions. By establishing $\Gamma$-convergence and compactness, we prove that as the nonlocal horizon vanishes, minimizers of the nonlocal functionals converge to those of the local counterparts. Numerical experiments using an efficient finite element method confirm the convergence.