Arman Rysmakhanov

collaborators

5 papers

stat.ML2026

In-context classification: Calibration and noise in linear attention with softmax readout

Arman Rysmakhanov, Mary Letey, Yue M. Lu +2

We study in-context binary classification in a simple attention model trained to minimise a logistic loss. Each prompt has a latent logistic teacher, and the learner must infer its…

stat.ML2026

What can linear attention learn from nonlinear teachers in-context?

Mary Letey, Arman Rysmakhanov, Yue M. Lu +2

Linear attention is a tractable model for understanding the mechanisms governing in-context learning in transformers. For linear regression tasks, recent asymptotic analyses have c…

math.PR2026

Spectral Properties of Dense Barabási-Albert Graphs

Steven J. Miller, Arman Rysmakhanov

Preferential attachment graphs model networks whose growth produces highly uneven degree distributions, describing many real-world systems. Their adjacency spectra are important be…

math.NT2025

Properties of Multidimensional Vector Zeckendorf Representations

Ivan Bortnovskyi, June Duvivier, Pedro Espinosa +7

Zeckendorf's Theorem says that for all $k \geq 3$ , every nonnegative integer has a unique $k$ -Zeckendorf representation as a sum of distinct $k$ -bonacci numbers, where no $k$ conse…

math.NT2025

Comparing Left and Right Quotient Sets in Groups

Julian Duvivier, Xiaoyao Huang, Ava Kennon +5

For a finite subset $A$ of a group $G$ , we define the right quotient set and the left quotient set of $A$ , respectively, as $A A^{- 1} := {a_{1} a_{2}^{- 1} : a_{1}, a_{2} \in A}$ , $A^{-1}A := \…