arXiv subjects

Daniel J. Zhang

Publications and source records attributed to Daniel J. Zhang.

3 recordsLinked to original sources

arXiv2026

Convergence to Radial Symmetry in Iterative Convolution-Thresholding Dynamics

We study a discrete-time spatially extended dynamical system motivated by the continuum limit of binary neuron networks on geometric random graphs. The model evolves a function $ψ:\mathbb{R}^d\rightarrow[0,1]$ by iterative smoothing and sharpening; that is, $ψ_{t+1} = γ_t\circ (g * ψ_t)$, where $g$ is a radial convolution kernel and $γ_t$ is a monotone map. Under mild regularity conditions on $g$ and $γ_t$, we prove that $ψ_t$ tends toward radial symmetry as $t \rightarrow \infty$. Notably, a special case of this process recovers the Merriman-Bence-Osher (MBO) scheme for the motion of interfaces by mean curvature, and we provide a novel analysis of its behavior. Our results connect the dynamics of spatial binary neuron networks with classical models of interface motion, and we establish general conditions under which spatial dependence drives activity toward radial symmetry.

math.DS↗

arXiv2026

Dynamic Rank, Basis, and Matching

We study dynamic algorithms for maintaining fundamental algebraic properties of matrices, specifically, rank, basis, and full-rank submatrices, with applications to maximum matching on dynamic graphs. Prior dynamic algorithms for rank achieve subquadratic update times but scale with the matrix dimension $n$, and could not always maintain the corresponding objects such as a basis or maximum full-rank submatrix. We present the first dynamic rank algorithms whose update time scales with the matrix rank $r$, achieving $\tilde O(r^{1.405})$ time per entry-update and $\tilde O(r^{1.528}+ z)$ per column-update, where $z$ is the number of changed entries. This extends to $\tilde O(|M|^{1.405})$ edge-update time to maintain the size $|M|$ of a maximum matching. We also give dynamic algorithms for maintaining a column-basis subject to column-updates and a maximum full-rank submatrix subject to entry-updates.

cs.DS↗

arXiv2026

Sampling Sphere Packings with Continuum Glauber Dynamics

Continuum Glauber dynamics is a spatial birth-death process whose stationary distribution is a Gibbs distribution. We establish a spectral gap for Continuum Glauber dynamics applied to Gibbs point processes with repulsive pair potentials, a well-known special case of which is the hard sphere model. For arbitrary-range repulsive pair potentials, we show that a continuous version of Spectral Independence suffices to establish a spectral gap. This extends the regime of activity for which Continuum Glauber dynamics is known to mix, yielding a simple efficient sampling algorithm for arbitrary-range pair potentials that matches the known efficient sampling regime for finite-range pair potentials currently based on specialized algorithms. As a consequence, we also improve the threshold up to which packings of fixed size/density can be efficiently sampled from a bounded domain, the first improvement since Kannan, Mahoney and Montenegro (2003). To prove these results, we develop continuous analogs of Spectral Independence and negative fields localization. We show that a stronger variant of zero-freeness implies Spectral Independence, which in turn allows us to run the localization scheme to boost the spectral gap of Continuum Glauber dynamics from smaller activity to larger activity. While this follows the high-level blueprint of Chen and Eldan (2022) for the discrete setting, we have to address several novel difficulties due to the continuous setting. Notably, we avoid discretization in the algorithm and the analysis and work directly in the continuous setting.

cs.DS↗