ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Let Xn=(xi1n,⋯ ,xipn)X^n=(x^n_{i_1},\cdots,x^n_{i_p}) be a vector composed of one representative neuron in each of the PP populations, and let

B={(μ1,⋯ ,μP)∈M1(Rd)P: ∀xp∈Supp⁡(μp), ∑q=1Pgp,q∫Rdbp,q(xp,y)μq(dy)=0}\mathcal{B}=\{(\mu^1,\cdots,\mu^P)\in\mathcal{M}^1(\mathbb{R}^d)^P:\ \forall x_p\in\operatorname{Supp}(\mu^p),\ \sum_{q=1}^P g_{p,q}\int_{\mathbb{R}^d}b_{p,q}(x_p,y)\mu^q(dy)=0\}

be the balanced regime. The associated deterministic dynamics are

dxpdt=∑q=1Pgp,q∫Rdbp,q(xp,y)μq(dy).\frac{dx_p}{dt}=\sum_{q=1}^{P}g_{p,q}\int_{\mathbb{R}^d}b_{p,q}(x_p,y)\mu_q(dy).

Balanced-regime confinement and collapse conjecture. If the set B\mathcal{B} is nonempty, there exist asymptotic solutions confined to the balanced regime for all times. Moreover, if B\mathcal{B} is attractive for the deterministic dynamical system, in the sense that solutions with initial conditions xp0x_p^0 near the support of μp\mu_p converge to that support, then even initial conditions outside B\mathcal{B} lead to collapse onto B\mathcal{B} at a timescale inversely proportional to γ(n)\gamma(n); that is, for any t>0t>0, P[Xtn∈B]→1\mathbb{P}[X^n_t\in\mathcal{B}]\to1 as n→∞n\to\infty. This conjecture predicts whether divergent interactions produce confinement to, or rapid attraction toward, the zero-net-input manifold; its resolution depends on establishing asymptotic dynamics and stability for the strongly coupled network.

Record

Comments

Nothing has been published against this problem yet, and nothing has been said about it.

Sign in with an institutional address to take part in the discussion. Reading every thread stays open to everyone.

Sign in

Solve with an agent

Open the statement in a chat, with the problem and the ground rules already written into the prompt.

This opens a third-party site. Nothing is posted back to ProbXiv and nothing you write there is recorded here — what a model gives you is an attempt, which a person still has to check.