works on

From the 1 of 5 linked papers with an AI index.

collaborators

5 papers

cs.DS2026

The Extremum Stack as Optimal Memory for Rate-Independent Sequence Models: Information-Theoretic Foundations and Online Complexity

Piotr Frydrych

The paper shows that the extremum stack used in Preisach attention fully characterizes rate‑independent sequence models and is the minimal representation both in Kolmogorov and Sha…

cs.LG2026

Worker Utility as Hysteresis: A Preisach Model of Transaction Acceptance in Gig Labour Markets

Piotr Frydrych

Worker utility is not observed -- only its consequence is. Each gig transaction produces a single bit: accepted or rejected. We argue this structure points directly to the Preisach…

cs.IT2026

The Preisach Extremum Stack is a Shannon-Minimal Sufficient Statistic for Rate-Independent Functionals

Piotr Frydrych

Let R denote the class of all computable, causal functionals that are rate-independent in the classical sense (invariant under monotone time reparametrizations), and let Pi_n be th…

cs.LG2026

Preisach Attention: A Hysteretic Model of Sequential Memory

Piotr Frydrych

We introduce the Preisach Attention Layer (PAL), a novel sequence modelling architecture grounded in the classical Preisach hysteresis operator from mathematical physics. PAL repla…

cs.IT2026

The Extremum Stack is a Minimal Sufficient Statistic for Rate-Independent Functionals: A Kolmogorov Complexity Characterisation

Piotr Frydrych

We prove that the extremum stack of a discrete sequence is a minimal sufficient statistic for the class of all computable, causal, rate-independent functionals, in the sense of Kol…