Active Learning

Active learning’s optimal rates are completely characterized, resolving an open problem and providing new algorithms achieving exponential and sublinear rates depending on combinatorial complexity mea…

This paper introduces transductive active learning, proving its efficiency in minimizing uncertainty and achieving state-of-the-art results in neural network fine-tuning and safe Bayesian optimization…

SEL-BALD tackles the challenge of human discretion in active learning by proposing novel algorithms that account for instance rejection, significantly boosting sample efficiency.

This paper introduces a novel offline active learning method for node-level tasks on graphs, incorporating network structure and node covariates to improve efficiency and robustness, especially in noi…

Numerous machine learning algorithms are unified under the novel paradigm of reciprocal learning, proven to converge at linear rates under specific conditions, enhancing sample efficiency.

PS-BAX, a novel Bayesian algorithm execution method using posterior sampling, efficiently selects evaluation points for complex tasks, outperforming existing methods in speed and scalability.

µPOCA: a new active learning approach maximizes model generalization using strategically acquired labels/features in data-scarce, costly scenarios with partial observability, leveraging LLMs for effic…

New active learning algorithm, Adaptive-Weight Sampling (AWS), achieves faster convergence with theoretical guarantees, improving data efficiency for machine learning.

LinUProp: Linearly scalable uncertainty quantification for graphical models, achieving higher accuracy with lower labeling budgets!

Proper learning of noisy halfspaces with margins is achievable with sample complexity matching random classification noise, defying prior expectations.

Evidential Mixture Machines (EMM) enhances multi-label active learning by deciphering label correlations for improved accuracy and uncertainty quantification in large, sparse label spaces.

This study introduces a novel active learning paradigm for 3D molecular graphs, significantly improving efficiency and accuracy by leveraging geometric graph isomorphisms and distributional representa…

CAMS, a novel contextual active model selection algorithm, minimizes labeling costs by strategically selecting pre-trained models and querying labels for data points, achieving significant improvement…

Bi-Level Active Finetuning Framework (BiLAF) revolutionizes sample selection for efficient model finetuning. Unlike existing methods, BiLAF incorporates both global diversity and local decision bounda…

BACON: a novel Bayesian adaptive calibration and optimal design algorithm maximizes information gain for data-efficient computer model calibration, significantly outperforming existing methods in synt…

Amortized Decision-Aware BED prioritizes maximizing downstream decision utility by instantly proposing informative experimental designs and inferring decisions, facilitating accurate decision-making.

AHA: Human-assisted OOD learning maximizes OOD generalization and detection by strategically labeling data in a novel maximum disambiguation region, significantly outperforming existing methods with o…

Adaptive labeling minimizes uncertainty in out-of-distribution model evaluation by strategically selecting which data points to label, leading to more efficient and reliable assessments.

ActSort: Active learning dramatically accelerates cell sorting in massive calcium imaging datasets, minimizing human effort and improving accuracy.

This paper introduces anytime-valid risk-controlling prediction sets for active learning, guaranteeing low risk even with adaptive data collection and limited label budgets.