activity
20172024
most citedEfficient Regularized Piecewise-Linear Regression Trees

2 citations · 2 across the 5 of their papers we have counts for

collaborators

6 papers

stat.ML2024

Kernel-Based Differentiable Learning of Non-Parametric Directed Acyclic Graphical Models

Yurou Liang, Oleksandr Zadorozhnyi, Mathias Drton

Causal discovery amounts to learning a directed acyclic graph (DAG) that encodes a causal model. This model selection problem can be challenging due to its large combinatorial sear…

math.PR2023

Moment inequalities for sums of weakly dependent random fields

Gilles Blanchard, Alexandra Carpentier, Oleksandr Zadorozhnyi

We derive both Azuma-Hoeffding and Burkholder-type inequalities for partial sums over a rectangular grid of dimension of a random field satisfying a weak dependency assumption…

math.ST2021

Online nonparametric regression with Sobolev kernels

Oleksandr Zadorozhnyi, Pierre Gaillard, Sebastien Gerschinovitz +1

In this work we investigate the variation of the online kernelized ridge regression algorithm in the setting of dimensional adversarial nonparametric regression. We derive the…

cs.LG2019★ 2 cited

Efficient Regularized Piecewise-Linear Regression Trees

Leonidas Lefakis, Oleksandr Zadorozhnyi, Gilles Blanchard

We present a detailed analysis of the class of regression decision tree algorithms which employ a regulized piecewise-linear node-splitting criterion and have regularized linear mo…

stat.ML2019

Restless dependent bandits with fading memory

Oleksandr Zadorozhnyi, Gilles Blanchard, Alexandra Carpentier

We study the stochastic multi-armed bandit problem in the case when the arm samples are dependent over time and generated from so-called weak $\cC$-mixing processes. We establish a…

stat.ML2017

Concentration of weakly dependent Banach-valued sums and applications to statistical learning methods

Gilles Blanchard, Oleksandr Zadorozhnyi

We obtain a Bernstein-type inequality for sums of Banach-valued random variables satisfying a weak dependence assumption of general type and under certain smoothness assumptions of…