Search for: All records

In the adaptive sampling model of online learning, future prediction tasks can be arbitrarily dependent on the past. Every round, an adversary selects an instance to test the learner. After the learner makes a prediction, a noisy label is drawn from an underlying conditional label distribution and is revealed to both learner and adversary. A learner is consistent if it eventually performs no worse than the Bayes predictor. We study the kn-nearest neighbor learner within this setting. In the worst-case, the learner will fail because an adaptive process can generate spurious patterns out of noise. However, under the mild smoothing assumption that the process generating the instances is uniformly absolutely continuous and that choice of (kn)n is reasonable, the kn-nearest neighbor rule is online consistent. 

In the realizable online setting, a learner is tasked with making predictions for a stream of instances, where the correct answer is revealed after each prediction. A learning rule is online consistent if its mistake rate eventually vanishes. The nearest neighbor rule (Fix and Hodges, 1951) is a fundamental prediction strategy, but it is only known to be consistent under strong statistical or geometric assumptions—the instances come i.i.d. or the label classes are well-separated. We prove online consistency for all measurable functions in doubling metric spaces under the mild assumption that the instances are generated by a process that is uniformly absolutely continuous with respect to a finite, upper doubling measure. 

Labeling data via rules-of-thumb and minimal label supervision is central to Weak Supervision, a paradigm subsuming subareas of machine learning such as crowdsourced learning and semi-supervised ensemble learning. By using this labeled data to train modern machine learning methods, the cost of acquiring large amounts of hand labeled data can be ameliorated. Approaches to combining the rules-of-thumb falls into two camps, reflecting different ideologies of statistical estimation. The most common approach, exemplified by the Dawid-Skene model, is based on probabilistic modeling. The other, developed in the work of Balsubramani-Freund and others, is adversarial and game-theoretic. We provide a variety of statistical results for the adversarial approach under log-loss: we characterize the form of the solution, relate it to logistic regression, demonstrate consistency, and give rates of convergence. On the other hand, we find that probabilistic approaches for the same model class can fail to be consistent. Experimental results are provided to corroborate the theoretical results. 

Constructing knowledge graphs from heterogeneous data sources and evaluating their quality and consistency are important research questions in the field of knowledge graphs. We propose mapping rules to guide users to translate data from relational and graph sources into a meaningful knowledge graph and design a user-friendly language to specify the mapping rules. Given the mapping rules and constraints on source data, equivalent constraints on the target graph can be inferred, which is referred to as data source constraints. Besides this type of constraint, we design other two types: user-specified constraints and general rules that a high-quality knowledge graph should adhere to. We translate the three types of constraints into uniform expressions in the form of graph functional dependencies and extended graph dependencies, which can be used for consistency checking. Our approach provides a systematic way to build and evaluate knowledge graphs from diverse data sources. 

We consider k-means clustering in an online setting where each new data point is assigned to its closest cluster center and incurs a loss equal to the squared distance to that center, after which the algorithm is allowed to update its centers. The goal over a data stream X is to achieve a total loss that is not too much larger than L(X, OPT), the best possible loss using k fixed centers in hindsight. We give the first algorithm to achieve polynomial space and time complexity in the online setting. 

We consider k-means clustering in an online setting where each new data point is assigned to its closest cluster center and incurs a loss equal to the squared distance to that center, after which the algorithm is allowed to update its centers. The goal over a data stream X is to achieve a total loss that is not too much larger than the best possible loss using k fixed centers in hindsight. Ours is the first algorithm to achieve polynomial space and time complexity in the online setting. We note that our results have implications to the related streaming setting, where one final clustering is outputted, and the no-substitution setting, where center selections are permanent. We show a general reduction between the no-substitution cost of a blackbox algorithm and its online cost. Finally, we translate our algorithm to the no-substitution setting and streaming settings, and it competes with and can outperform existing work in the areas. 

Within machine learning, active learning studies the gains in performance made possible by adaptively selecting data points to label. In this work, we show through upper and lower bounds, that for a simple benign setting of well-specified logistic regression on a uniform distribution over a sphere, the expected excess error of both active learning and random sampling have the same inverse proportional dependence on the number of samples. Importantly, due to the nature of lower bounds, any more general setting does not allow a better dependence on the number of samples. Additionally, we show a variant of uncertainty sampling can achieve a faster rate of convergence than random sampling by a factor of the Bayes error, a recent empirical observation made by other work. Qualitatively, this work is pessimistic with respect to the asymptotic dependence on the number of samples, but optimistic with respect to finding performance gains in the constants.