The recent proposal by Polchinski and Susskind for the holographic flat space S– matrix is discussed. By using Feynman diagrams we argue that in principle all the information about the S–matrix in the interacting field theory in the bulk of the anti-de Sitter space is encoded into the data on the timelike boundary. The problem of locality of interpolating field is discussed and it is suggested ...

In this paper we studied the double scaling limit of a random unitary matrix ensemble near a singular point where a new cut is emerging from the support of the equilibrium measure. We obtained the asymptotic of the correlation kernel by using the Riemann-Hilbert approach. We have shown that the kernel near the critical point is given by the correlation kernel of a random unitary matrix ensemble...

In recent papers[1, 2] we proposed a group theoretical description of the Hilbert space for lattice gauge theories (LGT) in the Hamiltonian framework[3]. This approach, based on representation theory, allows to overcome the problem of selecting the gauge invariant Hilbert space. In particular, the difficulty of explicitly solving Mandelstam’s identities[5] in the context of Wilson loops[4] is c...

The purpose of this paper is to prove, by asymptotic center techniques and the methods of Hilbert spaces, the following theorem. Let H be a Hilbert space, let C be a nonempty bounded closed convex subset of H, and let M an,k n,k≥1 be a strongly ergodic matrix. If T : C → C is a lipschitzian mapping such that lim infn→∞infm 0,1,... ∑∞ k 1 an,k · ‖Tk m‖ 2 < 2, then the set of fixed points Fix T {...

We give dimension-free and data-dependent bounds for linear multi-task learning where a common linear operator is chosen to preprocess data for a vector of task specific linear-thresholding classifiers. The complexity penalty of multi-task learning is bounded by a simple expression involving the margins of the task-specific classifiers, the Hilbert-Schmidt norm of the selected preprocessor and ...

Each matrix representation : G ?! GL n (K) of a nite group G over a eld K induces an action of G on the module A n over the polynomial algebra A = Kx 1 ; ; x n ]. The graded A-submodule M() of A n generated by the orbit of (x 1 ; ; x n) is studied. A decomposition of M() into generic modules is given. Relations between the numerical invariants of and those of M(), the later being eeciently comp...

A finite dimensional system with a quadratic Hamiltonian constraint is Dirac quantized in holomorphic, antiholomorphic and mixed representations. A unique inner product is found by imposing Hermitian conjugacy relations on an operator algebra. The different representations yield drastically different Hilbert spaces. In particular, all the spaces obtained in the antiholomorphic representation vi...

Deformable template representations of observed imagery, model the variability of target pose via the actions of the matrix Lie groups on rigid templates. In this paper, we study the construction of minimum mean squared error estimators on the special orthogonal group, SO(n), for pose estimation. Due to the nonflat geometry of SO(n), the standard Bayesian formulation, of optimal estimators and ...

The problem of model selection is considerably important for acquiring higher levels of generalization capability in supervised learning. In this article, we propose a new criterion for model selection, the subspace information criterion (SIC), which is a generalization of Mallows's C(L). It is assumed that the learning target function belongs to a specified functional Hilbert space and the gen...

We present an algorithm for grouping families of probability density functions (pdfs). We exploit the fact that under the square-root re-parametrization, the space of pdfs forms a Riemannian manifold, namely the unit Hilbert sphere. An immediate consequence of this re-parametrization is that different families of pdfs form different submanifolds of the unit Hilbert sphere. Therefore, the proble...