arXiv research

A new method for learning to defer decisions with expert advice improves over standard methods.

New algorithm learns causal structure with advice, improving efficiency.

Adapts model-based advice to stabilize black-box policies for nonlinear control.

A key challenge in online learning is that classical algorithms can be slow to adapt to changing environments. Recent studies have proposed "meta" algorithms that convert any online learning algorithm to one that is adaptive to changing environments, where the adaptivity is analyzed in a quantity called the strongly-ad…

An adaptive dropout approach improves high-dimensional Bayesian optimization.

Advice-efficient prediction with expert advice (in analogy to label-efficient prediction) is a variant of prediction with expert advice game, where on each round of the game we are allowed to ask for advice of a limited number $M$ out of $N$ experts. This setting is especially interesting when asking for advice of ever…

A simple method improves batch active learning without high compute.

A2MT learns agents to select which modalities to acquire at test time.

NM-PPG optimizes adaptive feature acquisition in POMDPs for better predictions.

The paper tackles AI advice giving by considering adherence levels and defer options.

New algorithms reduce label collection for online prediction with expert advice.

This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least $\sqrt{\log(T)}$ better, where $T$ is the time horizon. Empirical results show tha…

Deep RL optimizes sensor placement in digital twins for dynamic data acquisition.

Improved learning of multivariate Gaussians with imperfect advice.

POLAR learns efficient data acquisition policies using pretrained belief representations.

Improves graph-based active learning for non-Gaussian models.

New algorithm uses imperfect advice to improve online bipartite matching performance.

Investigates fast prediction rates with limited expert advice.

Training deep reinforcement learning agents complex behaviors in 3D virtual environments requires significant computational resources. This is especially true in environments with high degrees of aliasing, where many states share nearly identical visual features. Minecraft is an exemplar of such an environment. We hypo…

New algorithms improve on consistency and robustness in convex function chasing with black-box advice.

Over the last few years, there has been growing interest in learning models for physically grounded language understanding tasks, such as the popular blocks world domain. These works typically view this problem as a single-step process, in which a human operator gives an instruction and an automated agent is evaluated …

Study finds optimal regret bound for multi-armed bandit problem with expert advice.

Model selection is treated as a standard performance boosting step in many machine learning applications. Once all other properties of a learning problem are fixed, the model is selected by grid search on a held-out validation set. This is strictly inapplicable to active learning. Within the standardized workflow, the …

Conventional learning with expert advice methods assumes a learner is always receiving the outcome (e.g., class labels) of every incoming training instance at the end of each trial. In real applications, acquiring the outcome from oracle can be costly or time consuming. In this paper, we address a new problem of active…

LIMEADE improves AI advice for opaque models, enhancing accuracy and user satisfaction.

New method improves forecast accuracy using CRPS for probabilistic predictions.

Improved regret bounds for bandits with expert advice.

CBDA improves active learning for semantic segmentation, especially with imbalanced classes.

A new method for student-initiated action advice using novelty detection.

Improved regret bounds for bandits with fixed expert advice using information theory.

CEGA addresses GNN security by enabling cost-effective model acquisition.

Bayesian Optimization (BO) has become a core method for solving expensive black-box optimization problems. While much research focussed on the choice of the acquisition function, we focus on online length-scale adaption and the choice of kernel function. Instead of choosing hyperparameters in view of maximum likelihood…

Sparse reward is one of the most challenging problems in reinforcement learning (RL). Hindsight Experience Replay (HER) attempts to address this issue by converting a failed experience to a successful one by relabeling the goals. Despite its effectiveness, HER has limited applicability because it lacks a compact and un…

This paper addresses the problem of prediction with expert advice for outcomes in a geodesic space with non-positive curvature in the sense of Alexandrov. Via geometric considerations, and in particular the notion of barycenters, we extend to this setting the definition and analysis of the classical exponentially weigh…

Unsupervised framework captures acquisition variability in structural connectomes.

Many fields of science and engineering rely on running simulations with complex and computationally expensive models to understand the involved processes in the system of interest. Nevertheless, the high cost involved hamper reliable and exhaustive simulations. Very often such codes incorporate heuristics that ironical…

In this paper, we study the behavior of the Hedge algorithm in the online stochastic setting. We prove that anytime Hedge with decreasing learning rate, which is one of the simplest algorithm for the problem of prediction with expert advice, is surprisingly both worst-case optimal and adaptive to the easier stochastic …

Bayesian optimization surveys information-theoretic acquisition functions.

Optimizing the acquisition matrix is useful for compressed sensing of signals that are sparse in overcomplete dictionaries, because the acquisition matrix can be adapted to the particular correlations of the dictionary atoms. In this paper a novel formulation of the optimization problem is proposed, in the form of a ra…

We provide the first algorithm for online bandit linear optimization whose regret after T rounds is of order sqrt{Td ln N} on any finite class X of N actions in d dimensions, and of order d*sqrt{T} (up to log factors) when X is infinite. These bounds are not improvable in general. The basic idea utilizes tools from con…

Study improves feature acquisition for static settings in AFAPE.

Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in most deep models. Column Networks, a deep architecture, can succinctl…

BOOST automates kernel and acquisition function selection in Bayesian optimization.

Study shows LLM-advisors match human performance in eliciting preferences but struggle with conflicting needs and trust.

Improves reward bounds for prediction with expert advice using abstention.

A new ensemble of Gaussian processes improves active learning efficiency.

VES-Gamma adapts EI using information-theoretic principles.

High quality reconstruction with interventional C-arm cone-beam computed tomography (CBCT) requires exact geometry information. If the geometry information is corrupted, e. g., by unexpected patient or system movement, the measured signal is misplaced in the backprojection operation. With prolonged acquisition times of…