arXiv subjects

Lukang Sun

Publications and source records attributed to Lukang Sun.

14 recordsLinked to original sources

arXiv2026

The nonlocal attraction-repulsion transport equation with power kernels

We study a nonlocal continuity equation on $\mathbb{R}^d$ in which a probability density is driven by the competition between attraction toward a prescribed background measure $\omega$ and self-repulsion among particles, governed respectively by the power-law kernels $\psi_a(x) = |x|^{1+a}$ and $\psi_r(x) = |x|^{1+r}$ with exponents $a, r \in [0,1)$. We establish global Lagrangian well-posedness via a squared-radius regularization, obtaining uniform $L^\infty$ and moment bounds, $W^{n,\infty}$ regularity, and uniqueness in the Lagrangian class. When the initial data is compactly supported and attraction dominates ($a > r$, or $a = r$ with $\omega(\mathbb{R}^d) > 1$), we prove that the support remains uniformly bounded at all time; a counterexample shows this fails for $a = r > 1$. For the attractive-dominant nonquadratic range $0 \leq r \leq a < 1$, we characterize zero-flux stationary states via a free-boundary problem involving a fractional Laplacian operator, reducing the stationarity condition to a fractional exterior Dirichlet problem. This characterization allow us to exhibit explicit examples of stationary measures in dimensions $d \in \{1,2,3\}$. Numerical particle simulations confirm agreement with the theoretical stationary profiles. Finally, we prove that every global solution with bounded energy and uniform moment bounds converges to a zero-flux stationary state.

math.AP↗

arXiv2026

Concavity of Tsallis Entropy and Tsallis Entropy Power along Heat Flow

We study the evolution of Tsallis entropy along the heat flow and establish concavity results in arbitrary dimensions. Extending earlier one-dimensional results, we prove that Tsallis entropy is concave along the heat flow for $q\in(0,3]$ in dimension one and for $q\in[1,3]$ in higher dimensions. The upper endpoint $q=3$ is sharp in every dimension. The proof is based on a nonlinear transformation of the heat equation, a sharp dimension-free functional inequality with constant $C_u=3$, and a rigorous justification of the integration-by-parts identities used in the argument. The sharp inequality is proved by an explicit integration-by-parts sum-of-squares identity, rather than by a computer-assisted semidefinite-programming search. As consequences, we recover a generalized de Bruijn identity, prove monotonicity of the associated $q$-Fisher information along the heat flow, and establish concavity results for Tsallis entropy power, including the Shannon entropy-power case and Costa's EPI as an endpoint. We also obtain an asymptotic entropy-power concavity statement for general initial data and a sharp auxiliary functional inequality which may be of independent analytic interest.

cs.IT↗

arXiv2025

Large-Time Analysis of the Langevin Dynamics for Energies Fulfilling Polyak-{\L}ojasiewicz Conditions

In this work, we take a step towards understanding overdamped Langevin dynamics for the minimization of a general class of objective functions $\mathcal{L}$. We establish well-posedness and regularity of the law $\rho_t$ of the process through novel a priori estimates, and, very importantly, we characterize the large-time behavior of $\rho_t$ under truly minimal assumptions on $\mathcal{L}$. In the case of integrable Gibbs density, the law converges to the normalized Gibbs measure. In the non-integrable case, we prove that the law diffuses. The rate of convergence is $\mathcal{O}(1/t)$. Under a Polyak-Lojasiewicz (PL) condition on $\mathcal{L}$, we also derive sharp exponential contractivity results toward the set of global minimizers. Combining these results we provide the first systematic convergence analysis of Langevin dynamics under PL conditions in non-integrable Gibbs settings: a first phase of exponential in time contraction toward the set of minimizers and then a large-time exploration over it with rate $\mathcal{O}(1/t)$.

math.AP↗

arXiv2025

Well-posedness and $L^1-L^p$ Smoothing Effect of the Porous Media Equation under Poincar\'e Inequality

We study the Cauchy problem for a weighted porous medium equation on $\R$ associated with a Gibbs probability measure $\pi=e^{-V}$. Under a Poincar\'e inequality for $\pi$ and the convexity assumption on $V$, we prove well-posedness and uniqueness of non-negative weak solutions with initial data in $L^1(\R,\pi)$. We also establish an $L^1$--$L^p$ smoothing effect at every positive time. More precisely, for every admissible $p>1$, we show that the logarithm of the ratio between the $L^p(\R,\pi)$ norm of the solution and its conserved $L^1(\R,\pi)$ mass first decays at a super-exponential rate and then decays exponentially to zero. In particular, even if the initial datum belongs only to $L^1(\R,\pi)$, the solution belongs to $L^p(\R,\pi)$ for every finite $p>1$ and every $t>0$.

math.AP↗

arXiv2025

Faithful global convergence for the rescaled Consensus-Based Optimization

We analyze the Consensus-Based Optimization (CBO) algorithm with a consensus point rescaled by a small fixed parameter $\kappa \in (0,1)$. Under minimal assumptions on the objective function and the initial data, we establish its unconditional convergence to the global minimizer. Our results hold in the asymptotic regime where both the time--horizon $t \to \infty$ and the inverse--temperature $\alpha \to \infty$, providing a rigorous theoretical foundation for the algorithm's global convergence. Furthermore, our findings extend to the case of multiple and non--discrete set of minimizers.

math.OC↗

arXiv2025

Regularity and positivity of solutions of the Consensus-Based Optimization equation: unconditional global convergence

Introduced in 2017 \cite{B1-pinnau2017consensus}, Consensus-Based Optimization (CBO) has rapidly emerged as a significant breakthrough in global optimization. This straightforward yet powerful multi-particle, zero-order optimization method draws inspiration from Simulated Annealing and Particle Swarm Optimization. Using a quantitative mean-field approximation, CBO dynamics can be described by a nonlinear Fokker-Planck equation with degenerate diffusion, which does not follow a gradient flow structure. In this paper, we demonstrate that solutions to the CBO equation remain positive and maintain full support. Building on this foundation, we establish the {\it unconditional} global convergence of CBO methods to global minimizers. Our results are derived through an analysis of solution regularity and the proof of existence for smooth, classical solutions to a broader class of drift-diffusion equations, despite the challenges posed by degenerate diffusion.

math.AP↗

arXiv2024

A PDE Framework of Consensus-Based Optimization for Objectives with Multiple Global Minimizers

Consensus-based optimization (CBO) is an agent-based derivative-free method for non-smooth global optimization that has been introduced in 2017, leveraging a surprising interplay between stochastic exploration and Laplace principle. In addition to its versatility and effectiveness in handling high-dimensional, non-convex, and non-smooth optimization problems, this approach lends itself well to theoretical analysis. Indeed, its dynamics is governed by a degenerate nonlinear Fokker--Planck equation, whose large time behavior explains the convergence of the method. Recent results provide guarantees of convergence under the restrictive assumption of a unique global minimizer for the objective function. In this work, we propose a novel and simple variation of CBO to tackle non-convex optimization problems with multiple global minimizers. Despite the simplicity of this new model, its analysis is particularly challenging because of its nonlinearity and nonlocal nature. We prove the existence of solutions of the corresponding nonlinear Fokker--Planck equation and we show exponential concentration in time to the set of minimizers made of multiple smooth, convex, and compact components. Our proofs require combining several ingredients, such as delicate geometrical arguments, new variants of a quantitative Laplace principle, ad hoc regularizations and approximations, and regularity theory for parabolic equations. Ultimately, this result suggests that the corresponding CBO algorithm, formulated as an Euler-Maruyama discretization of the underlying empirical stochastic process, tends to converge to multiple global minimizers.

math.AP↗

arXiv2023

Consensus-Based Optimization with Truncated Noise

Consensus-based optimization (CBO) is a versatile multi-particle metaheuristic optimization method suitable for performing nonconvex and nonsmooth global optimizations in high dimensions. It has proven effective in various applications while at the same time being amenable to a theoretical convergence analysis. In this paper, we explore a variant of CBO, which incorporates truncated noise in order to enhance the well-behavedness of the statistics of the law of the dynamics. By introducing this additional truncation in the noise term of the CBO dynamics, we achieve that, in contrast to the original version, higher moments of the law of the particle system can be effectively bounded. As a result, our proposed variant exhibits enhanced convergence performance, allowing in particular for wider flexibility in choosing the noise parameter of the method as we confirm experimentally. By analyzing the time-evolution of the Wasserstein-$2$ distance between the empirical measure of the interacting particle system and the global minimizer of the objective function, we rigorously prove convergence in expectation of the proposed CBO variant requiring only minimal assumptions on the objective function and on the initialization. Numerical evidences demonstrate the benefit of truncating the noise in CBO.

math.OC↗

arXiv2022

Improved Stein Variational Gradient Descent with Importance Weights

Stein Variational Gradient Descent (SVGD) is a popular sampling algorithm used in various machine learning tasks. It is well known that SVGD arises from a discretization of the kernelized gradient flow of the Kullback-Leibler divergence $D_{KL}\left(\cdot\mid\pi\right)$, where $\pi$ is the target distribution. In this work, we propose to enhance SVGD via the introduction of importance weights, which leads to a new method for which we coin the name $\beta$-SVGD. In the continuous time and infinite particles regime, the time for this flow to converge to the equilibrium distribution $\pi$, quantified by the Stein Fisher information, depends on $\rho_0$ and $\pi$ very weakly. This is very different from the kernelized gradient flow of Kullback-Leibler divergence, whose time complexity depends on $D_{KL}\left(\rho_0\mid\pi\right)$. Under certain assumptions, we provide a descent lemma for the population limit $\beta$-SVGD, which covers the descent lemma for the population limit SVGD when $\beta\to 0$. We also illustrate the advantages of $\beta$-SVGD over SVGD by experiments.

cs.LG↗

arXiv2022

A Note on the Convergence of Mirrored Stein Variational Gradient Descent under $(L_0,L_1)-$Smoothness Condition

In this note, we establish a descent lemma for the population limit Mirrored Stein Variational Gradient Method~(MSVGD). This descent lemma does not rely on the path information of MSVGD but rather on a simple assumption for the mirrored distribution $\nabla\Psi_{\#}\pi\propto\exp(-V)$. Our analysis demonstrates that MSVGD can be applied to a broader class of constrained sampling problems with non-smooth $V$. We also investigate the complexity of the population limit MSVGD in terms of dimension $d$.

math.OC↗

arXiv2022

Sharper Rates and Flexible Framework for Nonconvex SGD with Client and Data Sampling

We revisit the classical problem of finding an approximately stationary point of the average of $n$ smooth and possibly nonconvex functions. The optimal complexity of stochastic first-order methods in terms of the number of gradient evaluations of individual functions is $\mathcal{O}\left(n + n^{1/2}\varepsilon^{-1}\right)$, attained by the optimal SGD methods $\small\sf\color{green}{SPIDER}$(arXiv:1807.01695) and $\small\sf\color{green}{PAGE}$(arXiv:2008.10898), for example, where $\varepsilon$ is the error tolerance. However, i) the big-$\mathcal{O}$ notation hides crucial dependencies on the smoothness constants associated with the functions, and ii) the rates and theory in these methods assume simplistic sampling mechanisms that do not offer any flexibility. In this work we remedy the situation. First, we generalize the $\small\sf\color{green}{PAGE}$ algorithm so that it can provably work with virtually any (unbiased) sampling mechanism. This is particularly useful in federated learning, as it allows us to construct and better understand the impact of various combinations of client and data sampling strategies. Second, our analysis is sharper as we make explicit use of certain novel inequalities that capture the intricate interplay between the smoothness constants and the sampling procedure. Indeed, our analysis is better even for the simple sampling procedure analyzed in the $\small\sf\color{green}{PAGE}$ paper. However, this already improved bound can be further sharpened by a different sampling scheme which we propose. In summary, we provide the most general and most accurate analysis of optimal SGD in the smooth nonconvex regime. Finally, our theoretical findings are supposed with carefully designed experiments.

cs.LG↗

arXiv2022

Federated Learning with a Sampling Algorithm under Isoperimetry

Federated learning uses a set of techniques to efficiently distribute the training of a machine learning algorithm across several devices, who own the training data. These techniques critically rely on reducing the communication cost -- the main bottleneck -- between the devices and a central server. Federated learning algorithms usually take an optimization approach: they are algorithms for minimizing the training loss subject to communication (and other) constraints. In this work, we instead take a Bayesian approach for the training task, and propose a communication-efficient variant of the Langevin algorithm to sample a posteriori. The latter approach is more robust and provides more knowledge of the \textit{a posteriori} distribution than its optimization counterpart. We analyze our algorithm without assuming that the target distribution is strongly log-concave. Instead, we assume the weaker log Sobolev inequality, which allows for nonconvexity.

cs.LG↗

arXiv2022

Convergence of Stein Variational Gradient Descent under a Weaker Smoothness Condition

Stein Variational Gradient Descent (SVGD) is an important alternative to the Langevin-type algorithms for sampling from probability distributions of the form $\pi(x) \propto \exp(-V(x))$. In the existing theory of Langevin-type algorithms and SVGD, the potential function $V$ is often assumed to be $L$-smooth. However, this restrictive condition excludes a large class of potential functions such as polynomials of degree greater than $2$. Our paper studies the convergence of the SVGD algorithm for distributions with $(L_0,L_1)$-smooth potentials. This relaxed smoothness assumption was introduced by Zhang et al. [2019a] for the analysis of gradient clipping algorithms. With the help of trajectory-independent auxiliary conditions, we provide a descent lemma establishing that the algorithm decreases the $\mathrm{KL}$ divergence at each iteration and prove a complexity bound for SVGD in the population limit in terms of the Stein Fisher information.

math.ST↗

arXiv2021

A Convergence Theory for SVGD in the Population Limit under Talagrand's Inequality T1

Stein Variational Gradient Descent (SVGD) is an algorithm for sampling from a target density which is known up to a multiplicative constant. Although SVGD is a popular algorithm in practice, its theoretical study is limited to a few recent works. We study the convergence of SVGD in the population limit, (i.e., with an infinite number of particles) to sample from a non-logconcave target distribution satisfying Talagrand's inequality T1. We first establish the convergence of the algorithm. Then, we establish a dimension-dependent complexity bound in terms of the Kernelized Stein Discrepancy (KSD). Unlike existing works, we do not assume that the KSD is bounded along the trajectory of the algorithm. Our approach relies on interpreting SVGD as a gradient descent over a space of probability measures.

cs.LG↗