Search Results for author:
Found 8 papers, 4 papers with code
Scalarisation-based risk concepts for robust multi-objective optimisation
Robustification refers to the strategy that is used to marginalise over the uncertainty in the problem.
Random Pareto front surfaces
As a motivating example, we investigate how these statistics can be used within a design of experiments setting, where the goal is to both infer and use the Pareto front surface distribution in order to make effective decisions.
Multi-objective optimisation via the R2 utilities
As part of our work, we show that these utilities are monotone and submodular set functions which can be optimised effectively using greedy optimisation algorithms.
Privacy Risk for anisotropic Langevin dynamics using relative entropy bounds
The privacy preserving properties of Langevin dynamics with additive isotropic noise have been extensively studied.
Joint Entropy Search for Multi-objective Bayesian Optimization
Many real-world problems can be phrased as a multi-objective optimization problem, where the goal is to identify the best set of compromises between the competing objectives.
On stochastic mirror descent with interacting particles: convergence properties and variance reduction
A second alternative is to use a fixed step-size and run independent replicas of the algorithm and average these.
The sharp, the flat and the shallow: Can weakly interacting agents learn to escape bad minima?
As a first step towards understanding this question we formalize it as an optimization problem with weakly interacting agents.
On Adaptive Estimation for Dynamic Bernoulli Bandits
In this paper, we overcome the shortcoming of slow response to change by deploying adaptive estimation in the standard methods and propose a new family of algorithms, which are adaptive versions of $\epsilon$-Greedy, UCB, and Thompson sampling.
