SearcharxivSearch

arXiv subjects

Christophe Troestler

Publications and source records attributed to Christophe Troestler.

15 recordsLinked to original sources

Blow-up analysis and a priori bounds for NLS equations on metric graphs

We consider, on a connected metric graph $\mathcal{G}$, a family of nonlinear Schr\"odinger equations $$ -u'' + W_n(x) u + \lambda_n u = \rho_n(x)|u|^{p-2}u, \quad n \in \mathbb{N}. \qquad (*) $$ We assume that $p > 2$, $(W_n)$, $(\rho_n) \subseteq L^{\infty}(\mathcal{G})$ with $\rho_n \geq 0$, $|W_n|_{L^\infty(\mathcal{G})}$ and $|\rho_n|_{L^\infty(\mathcal{G})}$ are bounded and $\lambda_n \to +\infty$. Given $n \in \mathbb{N}$, we call "solution" a function $u_n \in H^1(\mathcal{G})$ which satisfies (*) for that $n\in \mathbb{N}$ together with the Kirchhoff conditions at the vertices. Focusing on the limiting behavior of sequences $(u_n) \subseteq H^1(\mathcal{G})$ of solutions as $\lambda_n \to + \infty$ and assuming that the Morse index $m(u_n)$ of $u_n$ is uniformly bounded, we establish, the existence of a finite subset of blow-up points away from which, up to a subsequence, $|u_n|$ has a global exponential decay. These points are generally a strict subset of the blow-up points, and their number is estimated by the bound on the Morse index of $(u_n)$. It is the first time that this global exponential decay property is established on graphs even if one consider only signed solutions. In the last part of the paper we derive various results of a priori bounds on the solutions in $L^\infty$ and $L^2$. Our blow-up analysis, combined with ODE arguments allows, for frequently considered classes of graphs, to obtain a fairly complete picture of the relationships between the number of nodal regions, Morse index, $L^\infty$ and $L^2$ norms of solutions.

math.AP

Normalized vector solutions of nonlinear Schrödinger systems

Given $μ>0$ we look for solutions $ λ\in\mathbb{R}$ and $v_1,\dots,v_k\in H^1(\mathbb{R}^N)$ of the system \[ \begin{cases} \displaystyle -Δv_i+ λv_i+V_i(x)v_i = \sum_{\substack{j=1}}^kβ_{ij} v_iv_j^2 &\text{ in } \mathbb{R}^N, \text{ } i=1,\dots,k,\newline \displaystyle \int_{\mathbb{R}^N} \left(v_1^2+\dots+v_k^2 \right)\mathrm{d} x = μ, \end{cases}\] where $N=1,2,3$, $V_i:\mathbb R^N\to \mathbb R$ and $β_{ij}\in\mathbb{R}$ satisfy $β_{ij}=β_{ji}$ and $β_{ii}>0$. Under suitable assumptions on the $β_{ij}$'s, given a non-degenerate critical point $ξ_0$ of a suitable linear combination of the potentials $V_i$, we build solutions whose components concentrate at $ξ_0$ as the prescribed global mass $μ$ is either large (when $N=1$) or small (when $N=3$) or it approaches some critical threshold (when $N=2$).

math.AP

Uniqueness, non-degeneracy, and exact multiplicity of positive solutions for superlinear elliptic problems

In this paper, we focus our attention on the positive solutions to second-order nonlinear ordinary differential equations of the form $u''+q(t)g(u)=0$, where $q$ is a sign-changing weight and $g$ is a superlinear function. We exploit the classical shooting approach and the comparison theorem to present non-degeneracy and exact multiplicity results for positive solutions. This completes the multiplicity results obtained by Feltrin and Zanolin. Numerical examples and some related open problems are also discussed.

math.AP

Constant sign and sign changing NLS ground states on noncompact metric graphs

We investigate existence and nonexistence of action ground states and nodal action ground states for the nonlinear Schrödinger equation on noncompact metric graphs with rather general boundary conditions. We first obtain abstract sufficient conditions for existence, typical of problems with lack of compactness, in terms of ``levels at infinity'' for the action functional associated with the problems. Then we analyze in detail two relevant classes of graphs. For noncompact graphs with finitely many edges, we detect purely topological sharp conditions preventing the existence of ground states or of nodal ground states. We also investigate analogous conditions of metrical nature. The negative results are complemented by several sufficient conditions to ensure existence, either of topological or metrical nature, or a combination of the two. For graphs with infinitely many edges, all bounded, we focus on periodic graphs and infinite trees. In these cases, our results completely describe the phenomenology. Furthermore, we study nodal domains and nodal sets of nodal ground states and we show that the situation on graphs can be totally different from that on domains of $\mathbb{R}^N$.

math.AP

Entire radial and nonradial solutions for systems with critical growth

In this paper we establish existence of radial and nonradial solutions to the system $$ \begin{array}{ll} -Δu_1 = F_1(u_1,u_2) &\text{in }\mathbb{R}^N,\newline -Δu_2 = F_2(u_1,u_2) &\text{in }\mathbb{R}^N,\newline u_1\geq 0,\ u_2\geq 0 &\text{in }\mathbb{R}^N,\newline u_1,u_2\in D^{1,2}(\mathbb{R}^N), \end{array} $$ where $F_1,F_2$ are nonlinearities with critical behavior.

math.AP

Spectral analysis of a generalized buckling problem on a ball

In this paper, the spectrum of the following fourth order problem \begin{equation*} \begin{cases} Δ^2 u+νu=-λΔu &\text{in } D_1,\newline u=\partial_r u= 0 &\text{on } \partial D_1, \end{cases} \end{equation*} where $D_1$ is the unit ball in ${\mathbb R}^N$, is determined for $ν< 0$ as well as the nodal properties of the corresponding eigenfunctions. In particular, we show that the first eigenvalue is simple and that the corresponding eigenfunction is radial and (up to a multiplicative factor) positive and decreasing with respect to the radius. This completes earlier results obtained for $ν\ge 0$ and for $ν<0$.

math.AP

Multiple radial positive solutions of semilinear elliptic problems with Neumann boundary conditions

Assuming $B_{R}$ is a ball in $\mathbb R^{N}$, we analyze the positive solutions of the problem \[ \begin{cases} -Δu+u= |u|^{p-2}u, &\text{ in } B_{R},\newline \partial_νu=0,&\text{ on } \partial B_{R}, \end{cases} \] that branch out from the constant solution $u=1$ as $p$ grows from $2$ to $+\infty$. The non-zero constant positive solution is the unique positive solution for $p$ close to $2$. We show that there exist arbitrarily many positive solutions as $p\to\infty$ (in particular, for supercritical exponents) or as $R \to \infty$ for any fixed value of $p>2$, answering partially a conjecture in [Bonheure-Noris-Weth]. We give the explicit lower bounds for $p$ and $R$ so that a given number of solutions exist. The geometrical properties of those solutions are studied and illustrated numerically. Our simulations motivate additional conjectures. The structure of the least energy solutions (among all or only among radial solutions) and other related problems are also discussed.

math.AP

A non-variational system involving the critical Sobolev exponent. The radial case

In this paper we consider the non-variational system $$ \begin{cases} -Δu_i = \sum\limits_{j=1}^k a_{ij} u_j^{(N+2)/(N-2)} &\text{in }\mathbb R^N,\newline u_i>0 &\text{in }\mathbb R^N,\newline u_i\in D^{1,2}(\mathbb R^N). \end{cases} $$ and we give some sufficient conditions on the matrix $(a_{ij})_{i,j=1,\dotsc ,k}$ which ensure the existence of solutions bifurcating from the bubble of the critical Sobolev equation.

math.AP

Nodal properties of eigenfunctions of a generalized buckling problem on balls

In this paper we are interested in the following fourth order eigenvalue problem coming from the buckling of thin films on liquid substrates: \begin{equation*} \begin{cases} Δ^2 u+ κ^2 u=-λΔu &\text{in } B_1,\newline u=\partial_r u= 0 &\text{on } \partial B_1, \end{cases} \end{equation*} where $B_1$ is the unit ball in $\mathbb{R}^N$. When $κ> 0$ is small, we show that the first eigenvalue is simple and the first eigenfunction, which gives the shape of the film for small displacements, is positive. However, when $κ$ increases, we establish that the first eigenvalue is not always simple and the first eigenfunction may change sign. More precisely, for any $κ\in (0,+\infty)$, we give the exact multiplicity of the first eigenvalue and the number of nodal regions of the first eigenfunction.

math.AP

Convergence of a mountain pass type algorithm for strongly indefinite problems and systems

For a functional $\E$ and a peak selection that picks up a global maximum of $\E$ on varying cones, we study the convergence up to a subsequence to a critical point of the sequence generated by a mountain pass type algorithm. Moreover, by carefully choosing stepsizes, we establish the convergence of the whole sequence under a "localization" assumption on the critical point. We illustrate our results with two problems: an indefinite Schr\"odinger equation and a superlinear Schr\"odinger system.

math.AP

Bifurcation into spectral gaps for a noncompact semilinear Schrödinger equation with nonconvex potential

This paper shows that the nonlinear periodic eigenvalue problem $${cases} -Δu + V(x) u - f(x,u) = λu, u \in H^1(\IR^N), {cases}$$ has a nontrivial branch of solutions emanating from the upper bound of every spectral gap of $-Δ+ V$. No convexity condition is assumed. The following result of independent interest is also proven: the direct sum $Y \oplus Z$ in $H^1(\IR^N)$ associated to a decomposition of the spectrum of $-Δ+V$ remains "topologically direct" in the $L^p$'s (in the sense that the projections from $Y+Z$ onto $Y$ and $Z$ are $L^p$-continuous).

math.AP