arXiv research

The paper tackles noisy multi-armed bandit problems with improved regret guarantees.

New method uses noisy function evaluations for sampling Langevin diffusions.

We address the problem of maximizing an unknown submodular function that can only be accessed via noisy evaluations. Our work is motivated by the task of summarizing content, e.g., image collections, by leveraging users' feedback in form of clicks or ratings. For summarization tasks with the goal of maximizing coverage…

A scalable portfolio approach speeds up Bayesian optimization for noisy functions.

Tree-search algorithm optimizes noisy black-box functions with multi-fidelity queries.

VBMC+VIQR outperforms noisy models in Bayesian inference.

This paper provides lower bounds on the convergence rate of Derivative Free Optimization (DFO) with noisy function evaluations, exposing a fundamental and unavoidable gap between the performance of algorithms with access to gradients and those with access to only function evaluations. However, there are situations in w…

Bayesian optimisation tackles uncertain inputs in noisy function evaluations.

Parallel Gaussian process surrogate for noisy likelihood evaluations in Bayesian inference.

New algorithm POO optimizes noisy, unknown-smooth functions.

NES improves robust optimization with noisy inputs.

We propose a Bayesian optimization algorithm for objective functions that are sums or integrals of expensive-to-evaluate functions, allowing noisy evaluations. These objective functions arise in multi-task Bayesian optimization for tuning machine learning hyperparameters, optimization via simulation, and sequential des…

New method approximates non-submodular functions, offering first guarantees.

Study improves estimation of functions from noisy data using convex penalties.

New method estimates Riemannian derivatives from noisy function evaluations.

In this paper we propose a modified version of the simulated annealing algorithm for solving a stochastic global optimization problem. More precisely, we address the problem of finding a global minimizer of a function with noisy evaluations. We provide a rate of convergence and its optimized parametrization to ensure a…

This paper proposes automatic tuning of Bayesian Optimization's acquisition function.

New algorithm optimizes convex functions with noisy evaluations in one dimension.

New algorithm improves efficiency and cost of noisy optimization.

Survey on deep learning robust training methods for noisy labels.

Study tackles nonlinear factor models with unknown monotone links from incomplete and noisy data.

Agents learning to act autonomously in real-world domains must acquire a model of the dynamics of the domain in which they operate. Learning domain dynamics can be challenging, especially where an agent only has partial access to the world state, and/or noisy external sensors. Even in standard STRIPS domains, existing …

Efficiently recovers piecewise linear functions from noisy samples.

PCTS optimizes noisy, delayed, multi-fidelity feedbacks in black-box optimization.

This paper tackles safe global optimization of noisy functions with a Lipschitz condition.

The paper studies estimating the normalizing constant using queries to a black-box function in RKHS.

Reconstructing polytopes with fixed facet directions from support function evaluations.

Randomized experiments are the gold standard for evaluating the effects of changes to real-world systems. Data in these tests may be difficult to collect and outcomes may have high variance, resulting in potentially large measurement error. Bayesian optimization is a promising technique for efficiently optimizing multi…

New algorithm optimizes noisy function evaluations with delayed feedback.

ML surrogates speed up Bayesian inverse problem solving.

Optimizes noisy IS with better proposal densities.

Bayesian optimization surveys information-theoretic acquisition functions.

We consider the problem of global optimization of an unknown non-convex smooth function with zeroth-order feedback. In this setup, an algorithm is allowed to adaptively query the underlying function at different locations and receives noisy evaluations of function values at the queried points (i.e. the algorithm has ac…

BOSH optimizes functions with stochastic evaluations more efficiently and precisely.

Proposes an ensemble loss function for robust regression.

DDPMs are robust to noisy score estimates and achieve optimal convergence rates in Wasserstein-2 distance.

The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers, and approaches such as importance re-weighting and bootstrap have been proposed …

In many applications of black-box optimization, one can evaluate multiple points simultaneously, e.g. when evaluating the performances of several different neural network architectures in a parallel computing environment. In this paper, we develop a novel batch Bayesian optimization algorithm --- the parallel knowledge…

Paper introduces a noisy-labeled audio tagging challenge.

This paper studies continuum-armed bandits under Besov smoothness conditions and derives minimax rates.

CbMLC improves multi-label classification with noisy labels.

Deep models can fit noisy labels, but robustness and reliability are still issues.

Algorithm identifies Pareto optimal designs efficiently for noisy, multi-objective functions.

Online knowledge repositories typically rely on their users or dedicated editors to evaluate the reliability of their content. These evaluations can be viewed as noisy measurements of both information reliability and information source trustworthiness. Can we leverage these noisy evaluations, often biased, to distill a…

Flow Annealing Posterior Sampling unifies stochastic-process regression and PDE inverse problems.

Framework for Bayesian inference using GP emulated MH sampler for noisy likelihoods.

We consider the problem of adaptive stratified sampling for Monte Carlo integration of a noisy function, given a finite budget n of noisy evaluations to the function. We tackle in this paper the problem of adapting to the function at the same time the number of samples into each stratum and the partition itself. More p…

Proposes a new PBO method with theoretical guarantees.