Add to ORKGSubmodular function maximization is one of the key problems that arise in many machine learn-ing tasks. Greedy selection algorithms are the proven choice to solve such problems, where prior theoretical work guarantees (1 − 1/e) ap-proximation ratio. However, it has been empiri-cally observed that greedy selection provides al-most optimal solutions in practice. The main goal of this paper is to explore and answer why the greedy selection does significantly better than the theoretical guarantee of (1 − 1/e). Applica-tions include, but are not limited to, sensor se-lection tasks which use both entropy and mutual information as a maximization criteria. We give a theoretical justification for the nearly optimal approximation ratio via detailed a...
Many algorithms of machine learning use an entropy measure as optimization criterion. Among the wide...
We present an information-theoretic framework for solving global black-box optimization problems tha...
A wide variety of problems in machine learning, including exemplar clustering, document sum-marizati...
Submodular function maximization finds application in a variety of real-world decision-making proble...
Submodular function maximization finds application in a variety of real-world decision-making proble...
Submodular function maximization finds application in a variety of real-world decision-making proble...
We propose a novel information-theoretic approach for Bayesian optimization called Predictive Entrop...
Contemporary global optimization algorithms are based on local measures of utility, rather than a pr...
Entropy maximization and free energy minimization are general physical principles for modeling the d...
The quest for optimal sensing matrices is crucial in the design of efficient Compressed Sensing arch...
In the field of optimization using probabilistic models of the search space, this thesis identifies ...
When monitoring spatial phenomena, which are often modeled as Gaussian Processes (GPs), choosing se...
ICML-2023We address the challenge of exploration in reinforcement learning (RL) when the agent opera...
In many applications, one has to actively select among a set of expensive observations before making...
Optimal information gathering is a central challenge in machine learning and science in general. A c...
Many algorithms of machine learning use an entropy measure as optimization criterion. Among the wide...
We present an information-theoretic framework for solving global black-box optimization problems tha...
A wide variety of problems in machine learning, including exemplar clustering, document sum-marizati...
Submodular function maximization finds application in a variety of real-world decision-making proble...
Submodular function maximization finds application in a variety of real-world decision-making proble...
Submodular function maximization finds application in a variety of real-world decision-making proble...
We propose a novel information-theoretic approach for Bayesian optimization called Predictive Entrop...
Contemporary global optimization algorithms are based on local measures of utility, rather than a pr...
Entropy maximization and free energy minimization are general physical principles for modeling the d...
The quest for optimal sensing matrices is crucial in the design of efficient Compressed Sensing arch...
In the field of optimization using probabilistic models of the search space, this thesis identifies ...
When monitoring spatial phenomena, which are often modeled as Gaussian Processes (GPs), choosing se...
ICML-2023We address the challenge of exploration in reinforcement learning (RL) when the agent opera...
In many applications, one has to actively select among a set of expensive observations before making...
Optimal information gathering is a central challenge in machine learning and science in general. A c...
Many algorithms of machine learning use an entropy measure as optimization criterion. Among the wide...
We present an information-theoretic framework for solving global black-box optimization problems tha...
A wide variety of problems in machine learning, including exemplar clustering, document sum-marizati...