Related papers: A Competitive Algorithm for Agnostic Active Learni…
We consider interactive learning in the realizable setting and develop a general framework to handle problems ranging from best arm identification to active classification. We begin our investigation with the observation that agnostic…
We analyze the problem of active covering, where the learner is given an unlabeled dataset and can sequentially label query examples. The objective is to label query all of the positive examples in the fewest number of total label queries.…
Existing active learning studies typically work in the closed-set setting by assuming that all data examples to be labeled are drawn from known classes. However, in real annotation tasks, the unlabeled data usually contains a large amount…
We present $L^{\#}$, a new and simple approach to active automata learning. Instead of focusing on equivalence of observations, like the $L^{\ast}$ algorithm and its descendants, $L^{\#}$ takes a different perspective: it tries to establish…
In this work we discuss the problem of active learning. We present an approach that is based on A-optimal experimental design of ill-posed problems and show how one can optimally label a data set by partially probing it, and use it to train…
We propose a novel active learning strategy for regression, which is model-agnostic, robust against model mismatch, and interpretable. Assuming that a small number of initial samples are available, we derive the optimal training density…
We develop an online learning algorithm for identifying unlabeled data points that are most informative for training (i.e., active learning). By formulating the active learning problem as the prediction with sleeping experts problem, we…
In distributed learning settings such as federated learning, the training algorithm can be potentially biased towards different clients. Mohri et al. (2019) proposed a domain-agnostic learning algorithm, where the model is optimized for any…
In machine learning, active class selection (ACS) algorithms aim to actively select a class and ask the oracle to provide an instance for that class to optimize a classifier's performance while minimizing the number of requests. In this…
An active learning (AL) algorithm seeks to construct an effective classifier with a minimal number of labeled examples in a bootstrapping manner. While standard AL heuristics, such as selecting those points for annotation for which a…
This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness. We introduce supervised contrastive active learning by leveraging the contrastive…
While the predictive performance of modern statistical dependency parsers relies heavily on the availability of expensive expert-annotated treebank data, not all annotations contribute equally to the training of the parsers. In this paper,…
Deep learning algorithms are often said to be data hungry. The performance of such algorithms generally improve as more and more annotated data is fed into the model. While collecting unlabelled data is easier (as they can be scraped easily…
Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure. Active learning addresses this challenge by striving for optimum…
Conventional active learning algorithms assume a single labeler that produces noiseless label at a given, fixed cost, and aim to achieve the best generalization performance for given classifier under a budget constraint. However, in many…
Neural network pretraining is gaining attention due to its outstanding performance in natural language processing applications. However, pretraining usually leverages predefined task sequences to learn general linguistic clues. The lack of…
Agnostic learning of Boolean halfspaces is a fundamental problem in computational learning theory, but it is known to be computationally hard even for weak learning. Recent work [CKKMK24] proposed smoothed analysis as a way to bypass such…
In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in…
Active learning aims to develop label-efficient algorithms by querying the most informative samples to be labeled by an oracle. The design of efficient training methods that require fewer labels is an important research direction that…
A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often. In this work, we exactly characterize the best achievable tradeoff between…