Optimal approximation for submodular and supermodular optimization with bounded curvature

M Sviridenko, J Vondrák… - Mathematics of Operations …, 2017 - pubsonline.informs.org
We design new approximation algorithms for the problems of optimizing submodular and
supermodular functions subject to a single matroid constraint. Specifically, we consider the …

Autoprognosis: Automated clinical prognostic modeling via bayesian optimization with structured kernel learning

A Alaa, M Schaar - International conference on machine …, 2018 - proceedings.mlr.press
Clinical prognostic models derived from largescale healthcare data can inform critical
diagnostic and therapeutic decisions. To enable off-theshelf usage of machine learning (ML) …

Monte Carlo Markov chain algorithms for sampling strongly Rayleigh distributions and determinantal point processes

N Anari, SO Gharan, A Rezaei - Conference on Learning …, 2016 - proceedings.mlr.press
Strongly Rayleigh distributions are natural generalizations of product and determinantal
probability distributions and satisfy the strongest form of negative dependence properties …

Batched gaussian process bandit optimization via determinantal point processes

T Kathuria, A Deshpande… - Advances in neural …, 2016 - proceedings.neurips.cc
Gaussian Process bandit optimization has emerged as a powerful tool for optimizing noisy
black box functions. One example in machine learning is hyper-parameter optimization …

Tight bounds for volumetric spanners and applications

A Bhaskara, S Mahabadi… - Advances in Neural …, 2024 - proceedings.neurips.cc
Given a set of points of interest, a volumetric spanner is a subset of the points using which all
the points can be expressed using" small" coefficients (measured in an appropriate norm) …

Near-optimal discrete optimization for experimental design: A regret minimization approach

Z Allen-Zhu, Y Li, A Singh, Y Wang - Mathematical Programming, 2021 - Springer
The experimental design problem concerns the selection of k points from a potentially large
design pool of p-dimensional vectors, so as to maximize the statistical efficiency regressed …

Batch active learning using determinantal point processes

E Bıyık, K Wang, N Anari, D Sadigh - arXiv preprint arXiv:1906.07975, 2019 - arxiv.org
Data collection and labeling is one of the main challenges in employing machine learning
algorithms in a variety of real-world applications with limited data. While active learning …

Gaussian process landmarking on manifolds

T Gao, SZ Kovalsky, I Daubechies - SIAM Journal on Mathematics of Data …, 2019 - SIAM
As a means of improving analysis of biological shapes, we propose an algorithm for
sampling a Riemannian manifold by sequentially selecting points with maximum uncertainty …

Proportional Volume Sampling and Approximation Algorithms for -Optimal Design

A Nikolov, M Singh… - … of Operations Research, 2022 - pubsonline.informs.org
We study optimal design problems in which the goal is to choose a set of linear
measurements to obtain the most accurate estimate of an unknown vector. We study the A …

Log-concave polynomials IV: approximate exchange, tight mixing times, and near-optimal sampling of forests

N Anari, K Liu, SO Gharan, C Vinzant… - Proceedings of the 53rd …, 2021 - dl.acm.org
We prove tight mixing time bounds for natural random walks on bases of matroids,
determinantal distributions, and more generally distributions associated with log-concave …