Zobrazeno 1 - 10
of 56
pro vyhledávání: '"Orbanz, Peter"'
Accurate uncertainty quantification for causal effects is essential for robust decision making in complex systems, but remains challenging in non-parametric settings. One promising framework represents conditional distributions in a reproducing kerne
Externí odkaz:
http://arxiv.org/abs/2410.14483
Mechanical meta-materials are solids whose geometric structure results in exotic nonlinear behaviors that are not typically achievable via homogeneous materials. We show how to drastically expand the design space of a class of mechanical meta-materia
Externí odkaz:
http://arxiv.org/abs/2410.02385
Autor:
Huang, Kevin Han, Orbanz, Peter
We construct examples of degree-two U- and V-statistics of $n$ i.i.d.~heavy-tailed random vectors in $\mathbb{R}^{d(n)}$, whose $\nu$-th moments exist for ${\nu > 2}$, and provide tight bounds on the error of approximating both statistics by a quadra
Externí odkaz:
http://arxiv.org/abs/2406.12437
We establish an invariance principle for polynomial functions of $n$ independent high-dimensional random vectors, and also show that the obtained rates are nearly optimal. Both the dimension of the vectors and the degree of the polynomial are permitt
Externí odkaz:
http://arxiv.org/abs/2403.10711
Autor:
Orbanz, Peter
Consider a convex function that is invariant under an group of transformations. If it has a minimizer, does it also have an invariant minimizer? Variants of this problem appear in nonparametric statistics and in a number of adjacent fields. The answe
Externí odkaz:
http://arxiv.org/abs/2402.07613
Publikováno v:
NeurIPS 2023
In this work, we describe a method that determines an exact map from a finite set of subgraph densities to the parameters of a stochastic block model (SBM) matching these densities. Given a number $K$ of blocks, the subgraph densities of a finite num
Externí odkaz:
http://arxiv.org/abs/2402.00188
Autor:
Adams, Ryan P., Orbanz, Peter
Crystallographic groups describe the symmetries of crystals and other repetitive structures encountered in nature and the sciences. These groups include the wallpaper and space groups. We derive linear and nonlinear representations of functions that
Externí odkaz:
http://arxiv.org/abs/2306.05261
We provide results that exactly quantify how data augmentation affects the variance and limiting distribution of estimates, and analyze several specific models in detail. The results confirm some observations made in machine learning practice, but al
Externí odkaz:
http://arxiv.org/abs/2202.09134
Autor:
Austern, Morgane, Orbanz, Peter
A distributional symmetry is invariance of a distribution under a group of transformations. Exchangeability and stationarity are examples. We explain that a result of ergodic theory provides a law of large numbers: If the group satisfies suitable con
Externí odkaz:
http://arxiv.org/abs/1806.10661
Empirical risk minimization is the main tool for prediction problems, but its extension to relational data remains unsolved. We solve this problem using recent ideas from graph sampling theory to (i) define an empirical risk for relational data and (
Externí odkaz:
http://arxiv.org/abs/1806.10701