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 …
supermodular functions subject to a single matroid constraint. Specifically, we consider the …
Autoprognosis: Automated clinical prognostic modeling via bayesian optimization with structured kernel learning
Clinical prognostic models derived from largescale healthcare data can inform critical
diagnostic and therapeutic decisions. To enable off-theshelf usage of machine learning (ML) …
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
Strongly Rayleigh distributions are natural generalizations of product and determinantal
probability distributions and satisfy the strongest form of negative dependence properties …
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 …
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) …
the points can be expressed using" small" coefficients (measured in an appropriate norm) …
Near-optimal discrete optimization for experimental design: A regret minimization approach
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 …
design pool of p-dimensional vectors, so as to maximize the statistical efficiency regressed …
Batch active learning using determinantal point processes
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 …
algorithms in a variety of real-world applications with limited data. While active learning …
Gaussian process landmarking on manifolds
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 …
sampling a Riemannian manifold by sequentially selecting points with maximum uncertainty …
Proportional Volume Sampling and Approximation Algorithms for -Optimal Design
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 …
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
We prove tight mixing time bounds for natural random walks on bases of matroids,
determinantal distributions, and more generally distributions associated with log-concave …
determinantal distributions, and more generally distributions associated with log-concave …