works on

From the 1 of 7 linked papers with an AI index.

collaborators

7 papers

math.PR2026

Sharp Ternary Martingale Isoperimetry and -adic Takagi-Type Lower Bounds

Natanael Alpay

The paper computes the exact isoperimetric profile for the ternary (3‑adic) martingale filtration on [0,1) and establishes sharp logarithmic lower bounds and endpoint L^α estimates…

cs.LG2026

Complex Stochastic Gradient Descent and Directional Bias in Reproducing Kernel Hilbert Spaces

Natanael Alpay, Emeric Battaglia

Stochastic Gradient Descent (SGD) is a known stochastic iterative method popular for large-scale convex optimization problems due to its simple implementation and scalability. Some…

math.FA2026

Representer Theorem in Complex Reproducing Kernel Hilbert Spaces with Applications to Fock and Hardy Spaces and Superoscillations

Natanael Alpay, Antonino De Martino, Kamal Diki

We introduce a complex-valued counterpart of the representer theorem in machine learning. We study several learning and minimization problems in reproducing kernel Hilbert spaces (…

math.CA2026

Sharp Lower Bounds for Dyadic Square Functions of indicator functions of sets

Natanael Alpay, Paata Ivanisvili

We study lower bounds for dyadic square functions of indicator functions. In the case of the dyadic square function we obtain a sharp lower bound: for every measurable $A \…

math.FA2026

A new characterization of the Hardy space and of other spaces of analytic functions

Natanael Alpay

The Fock space can be characterized (up to a positive multiplicative factor) as the only Hilbert space of entire functions in which the adjoint of derivation is multiplication by t…

math.CA2026

Fractional Supershifts and their associated Cauchy Evolution problems

Natanael Alpay

In this work, we extend the notion of supershifts and superoscillation sequence to fractional Fock spaces based on Gelfond-Leontiev fractional derivatives. We first introduce the f…