Elad Aigner-Horev

collaborators

5 papers

cs.LG2026

The Sample Complexity of Distributionally Robust PAC Learning under Cressie--Read Divergences

Elad Aigner-Horev, Daniel Rosenberg, Roi Weiss

We study distributionally robust PAC learning for the $0$ -- $1$ -loss, where adversarial perturbations of the data distribution are constrained by a Cressie--Read divergence of order…

math.PR2025

Resilience of Rademacher chaos of low degree

Elad Aigner-Horev, Daniel Rosenberg, Roi Weiss

The {\em resilience} of a Rademacher chaos is the maximum number of adversarial sign-flips that the chaos can sustain without having its largest atom probability significantly alte…

math.PR2025

Smoothed analysis in compressed sensing

Elad Aigner-Horev, Dan Hefetz, Michael Trushkin

Arbitrary matrices $M \in R^{m \times n}$ , randomly perturbed in an additive manner using a random matrix $R \in R^{m \times n}$ , are shown to asymptotically almo…

math.CO2025

Ramsey properties of randomly perturbed hypergraphs

Elad Aigner-Horev, Dan Hefetz, Mathias Schacht

We study Ramsey properties of randomly perturbed $3$ -uniform hypergraphs. For~ $t \geq 2$ , write $K ~_{t}^{(3)}$ to denote the $3$ -uniform {\it expanded} clique hypergraph obtaine…

math.CO2024

Smoothed Analysis of the KomlÃ³s Conjecture: Rademacher Noise

Elad Aigner-Horev, Dan Hefetz, Michael Trushkin

The {\em discrepancy} of a matrix $M \in R^{d \times n}$ is given by $DISC (M) := min_{x \in {- 1, 1}^{n}} ∥ M x ∥_{\infty}$ . An outstanding…