New method optimises worst-case risk under model uncertainty.
problem Minimizing expected risk under posterior beliefs leads to sub-optimal decisions due to model uncertainty.
method Distributionally Robust Optimisation with Bayesian Ambiguity Sets (DRO-BAS)
result Improved out-of-sample robustness in the Newsvendor problem.
This work explores robust multi-objective optimisation with scalarisation and robustification.
problem Optimizing functions with uncertainty and varying objectives.
method Identifies the importance of robustification and scalarisation in multi-objective optimisation.
result Different orders of scalarisation and robustification lead to different solutions.
Paper improves robustness of Optimisation Monte Carlo method.
problem Overconfident approximations in Optimisation Monte Carlo.
method Robust Optimisation Monte Carlo (Robust OMC) method.
result Corrects overconfident approximations by collapsing regions of similar likelihood.
Paper develops robust SGLD for solving non-convex DRO problems.
problem Solving non-convex distributionally robust optimisation problems with adversarially corrupted samples.
method Developed a Stochastic Gradient Langevin Dynamics (SGLD) algorithm with non-asymptotic convergence bounds.
result The robust SGLD estimator outperforms vanilla SGLD in terms of test accuracy.
Vroom optimizes in unpredictable conditions without derivatives.
problem Optimizing in non-stationary, adversarial environments.
method Zeroth-order online learning with vanishing regret.
result Achieves favorable rates in stochastic settings.
We extend Relative Robust Portfolio Optimisation models to allow portfolios to optimise their distance to a set of benchmarks. Portfolio managers are also given the option of computing regret in a way which is more in line with market practices than other approaches suggested in the literature. In addition, they are gi…
Paper proposes robust reinforcement learning method for better real-world application.
problem Overfitting in reinforcement learning algorithms limits their applicability to real-world scenarios.
method Formalizes robust reinforcement learning as a min-max game with a Wasserstein constraint and proposes an efficient solver.
result Significant gains in performance on high-dimensional MuJuCo environments compared to standard and robust algorithms.
Dragonfly optimizes complex functions without needing grad students.
problem Challenging real-world optimisation tasks where conventional BO methods fail.
method Scalable and robust Bayesian Optimisation with multiple advanced methods.
result Significant improvements in BO performance when integrating new methods.
Bayesian method finds robust optima in expensive black-box functions.
problem Optimizing expensive black-box functions with sensitivity to inputs.
method Bayesian optimisation using Gaussian process prior and evolutionary algorithm for sampling and evaluation.
result Locating a region of design space with relatively insensitive performance to inputs.
Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and ran…
Bayesian optimisation outperforms standard ML-II in small samples.
problem Standard ML-II fails in small-sample trials.
method Adopting fully Bayesian optimisation (FBO) as an alternative.
result FBO is more robust and practical than ML-II.
EDRBO optimizes Bayesian optimization with continuous contexts using ensemble models and robust methods.
problem Bayesian optimization with unknown and continuous contextual distributions leads to suboptimal results.
method EDRBO uses ensemble surrogate models and Wasserstein ball ambiguity sets to handle uncertainty and maintain computational tractability.
result EDRBO achieves sublinear cumulative regret guarantees of order O ( γ T T ) \mathcal{O}(γ_T \sqrt{T}) O ( γ T T ) . Paper proposes a new Bayesian optimisation method to handle aleatoric uncertainty.
problem Representing and minimizing aleatoric noise in Bayesian optimisation.
method Heteroscedastic Gaussian process (GP) surrogate model with AEI and ANPEI acquisition functions.
result Improved performance on toy problems and real-world datasets compared to homoscedastic methods.
Bayesian surrogate models reduce uncertainty in high-dimensional design optimisation problems.
problem Uncertainty in high-dimensional inputs for complex computational models.
method Variational Bayesian inference for constructing statistical surrogates with Gaussian process priors and KL divergence for approximation.
result The RDVGP surrogate provides accurate and versatile approximations for robust structural optimisation.
Investigates portfolio optimization with and without gearing constraints.
problem Improving portfolio weights for better alignment with expected returns.
method Extends the alpha-weight angle bound to include gearing constraints and uses theoretical arguments and simulations.
result Equally weighted portfolios are not preferable to mean-variance portfolios even with poor forecast ability and a badly conditioned covariance matrix.
A new method solves general elliptical mixture models using approximate Wasserstein distance.
problem Estimating general elliptical mixture models with robust and stable optimization.
method Adaptive optimisation method on a statistical manifold defined under an approximate Wasserstein distance.
result The method provides a stable and superior optimum for EMMs, improving upon Kullback-Leibler divergence.
Techniques known as Nonlinear Set Membership prediction, Kinky Inference or Lipschitz Interpolation are fast and numerically robust approaches to nonparametric machine learning that have been proposed to be utilised in the context of system identification and learning-based control. They utilise presupposed Lipschitz p…
New methods improve global optimisation for expensive functions using lookahead strategies.
problem Optimising expensive functions without gradient info in high dimensions.
method Nonmyopic acquisition strategies based on approximate dynamic programming.
result Nonmyopic methods outperform myopic approaches in various applications.
Paper introduces robust Gaussian process regression without sacrificing computational efficiency.
problem Violation of independent and identically distributed Gaussian observation noise assumption in Gaussian process regression.
method Proves robust and conjugate Gaussian process regression (RCGP) at no additional cost using generalised Bayesian inference.
result RCGP enables exact conjugate closed form updates in all settings where standard GPs admit them.
Bayesian optimisation method targets graph classification models against adversarial attacks.
problem Adversarial attacks on graph classification models, especially for graph-level tasks.
method Bayesian optimisation-based attack method for graph classification models.
result Effectiveness and flexibility of the proposed method validated on various graph classification tasks.
Backdoor attacks are found to be effective against robust machine learning models trained with PGD.
problem Injecting and defending against backdoor attacks in robust machine learning models.
method Study and detection of backdoor attacks on PGD-trained robust models using feature clustering.
result AEGIS effectively detects PGD-trained robust DNNs infected with backdoors with 91.6% accuracy.
Policy gradient methods ignore the potential value of adjusting environment variables: unobservable state features that are randomly determined by the environment in a physical setting, but are controllable in a simulator. This can lead to slow learning, or convergence to suboptimal policies, if the environment variabl…
New method optimizes black-box functions using generative models and Wasserstein distance.
problem Optimizing black-box functions with stochastic responses in high dimensions.
method Deep generative surrogate models and Wasserstein distance for uncertainty estimation.
result Method outperforms state-of-the-art methods in robustness to function shape and stochasticity.
A risk-aware RL approach using RDEU and Wasserstein ball for robust performance.
problem Optimizing risk-aware performance criteria in uncertain environments.
method Rank dependent expected utility (RDEU) for risk assessment, Wasserstein ball for robustness, actor/agent framework.
result Explicit policy gradient formulae for robust optimization.
Regularisation improves ML classifier stability against poisoning attacks.
problem Poisoning attacks degrade ML algorithms' performance; current attacks ignore hyperparameters.
method Proposed a multiobjective bilevel optimisation problem to consider hyperparameter effects.
result L 2 L_2 L 2 regularisation enhances learning algorithm stability and mitigates poisoning attacks. A new algorithm for deep Q-learning with robustness to state transition uncertainty.
problem Model uncertainty in state transitions for non-tabular, continuous state spaces.
method Distributionally robust approach using worst-case transition ball and dualized Bellman operator with Sinkhorn distance.
result Optimal policy found through solving non-linear Bellman equation with neural network parameterization.
Geometric methods solve sampling, optimisation, inference, and adaptive decision-making.
problem Efficient solutions for sampling, optimisation, inference, and adaptive decision-making.
method Derive algorithms exploiting geometric structures of Hamiltonian systems, Hilbertian subspaces, and information geometry.
result Wide range of geometric theories emerge in these fields, enabling efficient solutions.
We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly be related to our derivation. We develop two off-policy algorithms and demonstrate that they are com…
Despite the improved accuracy of deep neural networks, the discovery of adversarial examples has raised serious safety concerns. In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the …
Efficient algorithms compute lambda quantiles for robust portfolio optimization.
problem Computing lambda quantiles efficiently and robustly.
method Λ-Newton-Bis algorithm combining Newton's method and bisection, interval analysis for multiple roots.
result Demonstrated computational efficiency and practical relevance in portfolio optimization.
Improves DRO with Bayesian Ambiguity Sets for model misspecification.
problem Overly conservative decisions due to misspecified models in DRO.
method Introduces DRO-RoBAS with robust posterior predictive distribution.
result Outperforms other Bayesian and empirical DRO approaches in out-of-sample performance.
Mixture modelling using elliptical distributions promises enhanced robustness, flexibility and stability over the widely employed Gaussian mixture model (GMM). However, existing studies based on the elliptical mixture model (EMM) are restricted to several specific types of elliptical probability density functions, whic…
New method calibrates ambiguity sets for robust decision-making under contamination.
problem Minimizing worst-case expected loss over distributional shifts in out-of-sample environments.
method Bulk-calibrated credal ambiguity sets that learn a high-mass bulk set from data and bound tail contributions.
result Closed-form, finite robust objective and tractable optimization for various losses and geometries.
MEMe efficiently approximates large-scale ML problems with hundreds of moments.
problem Efficient approximation in large-scale machine learning.
method Maximum entropy algorithm with hundreds of moments for computationally efficient approximations.
result Superior to existing approaches in fast log determinant estimation and Bayesian optimisation.
Overlay framework simplifies exotic derivative pricing.
problem Inconsistent pricing models for exotics.
method Combines path reweighting and conic optimisation.
result Practically model-independent price bands for exotics.
Improved portfolio optimization using GAM factor models.
problem Enhancing CVaR portfolio optimization performance.
method Combines autoregressive filters with factor regressions to predict stock returns.
result Substantial improvement in portfolio performances with GAM models.
This paper explores optimising acquisition functions in Bayesian optimisation.
problem Optimising acquisition functions in Bayesian optimisation is challenging due to their non-convex nature.
method The authors derive compositional forms for acquisition functions and use them to recast maximisation as a compositional optimisation problem.
result The compositional approach to maximising acquisition functions shows empirical advantages across various tasks.
Deep Gaussian processes on manifolds improve performance on complex data.
problem Complex data on manifolds that shallow models struggle with.
method Residual deep Gaussian processes on Riemannian manifolds.
result Significant improvement in prediction quality and uncertainty calibration.
Study uses RL to hedge financial derivatives, showing robust strategies outperform non-robust ones.
problem Risk mitigation and gain-seeking in hedging path-dependent financial derivatives.
method Robust risk-aware reinforcement learning (RL) with policy gradient approach.
result Robust hedging strategies outperform non-robust ones under varying data generating processes.
New framework converts multi-objective to single-objective optimisation.
problem Solving multi-objective optimisation problems.
method Formalises scalarisation into mathematical framework, uses R2 utilities.
result R2 utilities are monotone and submodular, optimised by greedy algorithms.
Develops a neural surrogate for proton dose calculation using Monte Carlo dropout uncertainty.
problem Computational demand in proton therapy workflows requiring repeated evaluations.
method Integrates Monte Carlo dropout into a neural network surrogate for fast, differentiable dose predictions and uncertainty quantification.
result Shows significant speedups over MC while retaining uncertainty information.
We present a probabilistic viewpoint to multiple kernel learning unifying well-known regularised risk approaches and recent advances in approximate Bayesian inference relaxations. The framework proposes a general objective function suitable for regression, robust regression and classification that is lower bound of the…
New algorithm robust to outliers in Bayesian Optimization.
problem Vulnerability of Bayesian Optimization to extreme outliers.
method Introduces a new adversary with a frequency-bounded corruption budget and derives RCGP-UCB algorithm.
result Achieves sublinear regret in the presence of up to O ( T 1 / 4 ) O(T^{1/4}) O ( T 1/4 ) and O ( T 1 / 7 ) O(T^{1/7}) O ( T 1/7 ) corruptions with possibly infinite magnitude. Paper uses variational inference to estimate nonlinear models.
problem Parameter estimation for nonlinear state-space models.
method Variational inference approach for nonlinear state-space models.
result The method provides robust parameter estimates and outperforms alternatives.
Unified Bayesian Optimisation for mixed variables improves performance.
problem Efficient optimisation of problems with both categorical and continuous variables.
method Derive value proposals from the Expected Improvement criterion to optimise both categorical and continuous variables under a single acquisition metric.
result Unified approach significantly outperforms existing methods across mixed-variable tasks.
A new method learns priors for Bayesian optimisation to improve performance.
problem Bayesian optimisation tasks often assume strong similarity, which is violated in many cases.
method Replace strong similarity assumption with shape similarity, learn priors for hyperparameters.
result PLeBO and prior transfer find good inputs in fewer evaluations.
Develops a two-layer model to design mortgage assistance products.
problem Designing effective mortgage assistance products to improve household resilience.
method Two-layer approach: simulation and optimization.
result Shows how the approach can design and evaluate mortgage assistance products.
Neural FGP learns portfolio generating functions from data.
problem Portfolio optimisation challenges in estimating drifts and covariances.
method Neural network approach to learn G ( ⋅ ) G(\cdot) G ( ⋅ ) from market data. result Neural FGP outperforms classical benchmarks.