ProbXiv
Explorersign in
Problem archiveProblem record

Statement

Let {xμ}μ=1n\{\boldsymbol{x}^{\mu}\}_{\mu=1}^{n} be independent samples from a data distribution on X⊂RD\mathcal{X}\subset\mathbb{R}^{D}, and let the centred teacher and student features be

u=φt(x)∈Rp,v=φs(x)∈Rd,\boldsymbol{u}=\boldsymbol{\varphi}_{t}(\boldsymbol{x})\in\mathbb{R}^{p},\qquad \boldsymbol{v}=\boldsymbol{\varphi}_{s}(\boldsymbol{x})\in\mathbb{R}^{d},

for feature maps φt:X→Rp\boldsymbol{\varphi}_{t}:\mathcal{X}\to\mathbb{R}^{p} and φs:X→Rd\boldsymbol{\varphi}_{s}:\mathcal{X}\to\mathbb{R}^{d}. Gaussian equivalent model conjecture. For a wide class of data distributions and feature maps, the generalisation and training errors of the estimator defined in the source are asymptotically captured by the equivalent Gaussian covariate model in which [u,v][\boldsymbol{u},\boldsymbol{v}] are jointly Gaussian variables, and hence by the corresponding closed-form expressions of the stated theorem. The conjecture proposes that this Gaussian replacement captures learning behaviour beyond the exactly Gaussian cases, including deterministic or data-learned feature maps; the source gives no resolution, so its validity remains open.

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.