PyTorchKR Papers

최신 논문

총 2,847편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1605.09757

Towards ontology driven learning of visual concept detectors

The maturity of deep learning techniques has led in recent years to a breakthrough in object recognition in visual media. While for some specific benchmarks, neural techniques seem to match if not outperform human judgement, challenges are still open for detecting arbitrary concepts in arbitrary videos. In this paper, we propose a system that combines neural techniques, a large scale visual concepts ontology, and an active learning loop, to provide on the fly model learning of arbitrary concepts. We give an overview of the system as a whole, and focus on the central role of the ontology for guiding and bootstrapping the learning of new concepts, improving the recall of concept detection, and, on the user end, providing semantic search on a library of annotated videos.

arXiv:1606.01530

Adaptive Submodular Ranking and Routing

We study a general stochastic ranking problem where an algorithm needs to adaptively select a sequence of elements so as to "cover" a random scenario (drawn from a known distribution) at minimum expected cost. The coverage of each scenario is captured by an individual submodular function, where the scenario is said to be covered when its function value goes above a given threshold. We obtain a logarithmic factor approximation algorithm for this adaptive ranking problem, which is the best possible (unless P=NP). This problem unifies and generalizes many previously studied problems with applications in search ranking and active learning. The approximation ratio of our algorithm either matches or improves the best result known in each of these special cases. Furthermore, we extend our results to an adaptive vehicle routing problem, where costs are determined by an underlying metric. This routing problem is a significant generalization of the previously-studied adaptive traveling salesman and traveling repairman problems. Our approximation ratio nearly matches the best bound known for these special cases. Finally, we present experimental results for some applications of adaptive ranking.

arXiv:1605.07669

On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems

The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning. In real-world applications, using explicit user feedback as the reward signal is often unreliable and costly to collect. This problem can be mitigated if the user's intent is known in advance or data is available to pre-train a task success predictor off-line. In practice neither of these apply for most real world applications. Here we propose an on-line learning framework whereby the dialogue policy is jointly trained alongside the reward model via active learning with a Gaussian process model. This Gaussian process operates on a continuous space dialogue representation generated in an unsupervised fashion using a recurrent neural network encoder-decoder. The experimental results demonstrate that the proposed framework is able to significantly reduce data annotation costs and mitigate noisy user feedback in dialogue policy learning.

arXiv:1606.02638

Addressing Limited Data for Textual Entailment Across Domains

We seek to address the lack of labeled data (and high cost of annotation) for textual entailment in some domains. To that end, we first create (for experimental purposes) an entailment dataset for the clinical domain, and a highly competitive supervised entailment system, ENT, that is effective (out of the box) on two domains. We then explore self-training and active learning strategies to address the lack of labeled data. With self-training, we successfully exploit unlabeled data to improve over ENT by 15% F-score on the newswire domain, and 13% F-score on clinical data. On the other hand, our active learning experiments demonstrate that we can match (and even beat) ENT using only 6.6% of the training data in the clinical domain, and only 5.8% of the training data in the newswire domain.

arXiv:1602.01132

Interactive algorithms: from pool to stream

We consider interactive algorithms in the pool-based setting, and in the stream-based setting. Interactive algorithms observe suggested elements (representing actions or queries), and interactively select some of them and receive responses. Pool-based algorithms can select elements at any order, while stream-based algorithms observe elements in sequence, and can only select elements immediately after observing them. We assume that the suggested elements are generated independently from some source distribution, and ask what is the stream size required for emulating a pool algorithm with a given pool size. We provide algorithms and matching lower bounds for general pool algorithms, and for utility-based pool algorithms. We further show that a maximal gap between the two settings exists also in the special case of active learning for binary classification.

arXiv:1603.04118

Active Algorithms For Preference Learning Problems with Multiple Populations

In this paper we model the problem of learning preferences of a population as an active learning problem. We propose an algorithm can adaptively choose pairs of items to show to users coming from a heterogeneous population, and use the obtained reward to decide which pair of items to show next. We provide computationally efficient algorithms with provable sample complexity guarantees for this problem in both the noiseless and noisy cases. In the process of establishing sample complexity guarantees for our algorithms, we establish new results using a Nystr{\"o}m-like method which can be of independent interest. We supplement our theoretical results with experimental comparisons.

arXiv:1607.03182

Stream-based Online Active Learning in a Contextual Multi-Armed Bandit Framework

We study the stream-based online active learning in a contextual multi-armed bandit framework. In this framework, the reward depends on both the arm and the context. In a stream-based active learning setting, obtaining the ground truth of the reward is costly, and the conventional contextual multi-armed bandit algorithm fails to achieve a sublinear regret due to this cost. Hence, the algorithm needs to determine whether or not to request the ground truth of the reward at current time slot. In our framework, we consider a stream-based active learning setting in which a query request for the ground truth is sent to the annotator, together with some prior information of the ground truth. Depending on the accuracy of the prior information, the query cost varies. Our algorithm mainly carries out two operations: the refinement of the context and arm spaces and the selection of actions. In our algorithm, the partitions of the context space and the arm space are maintained for a certain time slots, and then become finer as more information about the rewards accumulates. We use a strategic way to select the arms and to request the ground truth of the reward, aiming to maximize the total reward. We analytically show that the regret is sublinear and in the same order with that of the conventional contextual multi-armed bandit algorithms, where no query cost

arXiv:1605.07334

Near-optimal Bayesian Active Learning with Correlated and Noisy Tests

We consider the Bayesian active learning and experimental design problem, where the goal is to learn the value of some unknown target variable through a sequence of informative, noisy tests. In contrast to prior work, we focus on the challenging, yet practically relevant setting where test outcomes can be conditionally dependent given the hidden target variable. Under such assumptions, common heuristics, such as greedily performing tests that maximize the reduction in uncertainty of the target, often perform poorly. In this paper, we propose ECED, a novel, computationally efficient active learning algorithm, and prove strong theoretical guarantees that hold with correlated, noisy tests. Rather than directly optimizing the prediction error, at each step, ECED picks the test that maximizes the gain in a surrogate objective, which takes into account the dependencies between tests. Our analysis relies on an information-theoretic auxiliary function to track the progress of ECED, and utilizes adaptive submodularity to attain the near-optimal bound. We demonstrate strong empirical performance of ECED on two problem instances, including a Bayesian experimental design task intended to distinguish among economic theories of how people make risky decisions, and an active preference learning task via pairwise comparisons.

arXiv:1607.04805

Inferring solutions of differential equations using noisy multi-fidelity data

For more than two centuries, solutions of differential equations have been obtained either analytically or numerically based on typically well-behaved forcing and boundary conditions for well-posed problems. We are changing this paradigm in a fundamental way by establishing an interface between probabilistic machine learning and differential equations. We develop data-driven algorithms for general linear equations using Gaussian process priors tailored to the corresponding integro-differential operators. The only observables are scarce noisy multi-fidelity data for the forcing and solution that are not required to reside on the domain boundary. The resulting predictive posterior distributions quantify uncertainty and naturally lead to adaptive solution refinement via active learning. This general framework circumvents the tyranny of numerical discretization as well as the consistency and stability issues of time-integration, and is scalable to high-dimensions.

arXiv:1608.00667

Can Active Learning Experience Be Transferred?

Active learning is an important machine learning problem in reducing the human labeling effort. Current active learning strategies are designed from human knowledge, and are applied on each dataset in an immutable manner. In other words, experience about the usefulness of strategies cannot be updated and transferred to improve active learning on other datasets. This paper initiates a pioneering study on whether active learning experience can be transferred. We first propose a novel active learning model that linearly aggregates existing strategies. The linear weights can then be used to represent the active learning experience. We equip the model with the popular linear upper- confidence-bound (LinUCB) algorithm for contextual bandit to update the weights. Finally, we extend our model to transfer the experience across datasets with the technique of biased regularization. Empirical studies demonstrate that the learned experience not only is competitive with existing strategies on most single datasets, but also can be transferred across datasets to improve the performance on future learning tasks.

arXiv:1608.05225

Active Learning for Approximation of Expensive Functions with Normal Distributed Output Uncertainty

When approximating a black-box function, sampling with active learning focussing on regions with non-linear responses tends to improve accuracy. We present the FLOLA-Voronoi method introduced previously for deterministic responses, and theoretically derive the impact of output uncertainty. The algorithm automatically puts more emphasis on exploration to provide more information to the models.

arXiv:1608.07159

Active Robust Learning

In many practical applications of learning algorithms, unlabeled data is cheap and abundant whereas labeled data is expensive. Active learning algorithms developed to achieve better performance with lower cost. Usually Representativeness and Informativeness are used in active learning algoirthms. Advanced recent active learning methods consider both of these criteria. Despite its vast literature, very few active learning methods consider noisy instances, i.e. label noisy and outlier instances. Also, these methods didn't consider accuracy in computing representativeness and informativeness. Based on the idea that inaccuracy in these measures and not taking noisy instances into consideration are two sides of a coin and are inherently related, a new loss function is proposed. This new loss function helps to decrease the effect of noisy instances while at the same time, reduces bias. We defined "instance complexity" as a new notion of complexity for instances of a learning problem. It is proved that noisy instances in the data if any, are the ones with maximum instance complexity. Based on this loss function which has two functions for classifying ordinary and noisy instances, a new classifier, named "Simple-Complex Classifier" is proposed. In this classifier there are a simple and a complex function, with the complex function responsible for selecting noisy instances. The resulting optimization problem for both learning and active learning is highly non-convex and very challenging. In order to solve it, a convex relaxation is proposed.

arXiv:1602.07120

Submodular Learning and Covering with Response-Dependent Costs

We consider interactive learning and covering problems, in a setting where actions may incur different costs, depending on the response to the action. We propose a natural greedy algorithm for response-dependent costs. We bound the approximation factor of this greedy algorithm in active learning settings as well as in the general setting. We show that a different property of the cost function controls the approximation factor in each of these scenarios. We further show that in both settings, the approximation factor of this greedy algorithm is near-optimal among all greedy algorithms. Experiments demonstrate the advantages of the proposed algorithm in the response-dependent cost setting.

arXiv:1609.00845

Graph-Based Active Learning: A New Look at Expected Error Minimization

In graph-based active learning, algorithms based on expected error minimization (EEM) have been popular and yield good empirical performance. The exact computation of EEM optimally balances exploration and exploitation. In practice, however, EEM-based algorithms employ various approximations due to the computational hardness of exact EEM. This can result in a lack of either exploration or exploitation, which can negatively impact the effectiveness of active learning. We propose a new algorithm TSA (Two-Step Approximation) that balances between exploration and exploitation efficiently while enjoying the same computational complexity as existing approximations. Finally, we empirically show the value of balancing between exploration and exploitation in both toy and real-world datasets where our method outperforms several state-of-the-art methods.

arXiv:1609.01044

Classifying and sorting cluttered piles of unknown objects with robots: a learning approach

We consider the problem of sorting a densely cluttered pile of unknown objects using a robot. This yet unsolved problem is relevant in the robotic waste sorting business. By extending previous active learning approaches to grasping, we show a system that learns the task autonomously. Instead of predicting just whether a grasp succeeds, we predict the classes of the objects that end up being picked and thrown onto the target conveyor. Segmenting and identifying objects from the uncluttered target conveyor, as opposed to the working area, is easier due to the added structure since the thrown objects will be the only ones present. Instead of trying to segment or otherwise understand the cluttered working area in any way, we simply allow the controller to learn a mapping from an RGBD image in the neighborhood of the grasp to a predicted result---all segmentation etc. in the working area is implicit in the learned function. The grasp selection operates in two stages: The first stage is hardcoded and outputs a distribution of possible grasps that sometimes succeed. The second stage uses a purely learned criterion to choose the grasp to make from the proposal distribution created by the first stage. In an experiment, the system quickly learned to make good pickups and predict correctly, in advance, which class of object it was going to pick up and was able to sort the objects from a densely cluttered pile by color.

arXiv:1512.07146

Refined Error Bounds for Several Learning Algorithms

This article studies the achievable guarantees on the error rates of certain learning algorithms, with particular focus on refining logarithmic factors. Many of the results are based on a general technique for obtaining bounds on the error rates of sample-consistent classifiers with monotonic error regions, in the realizable case. We prove bounds of this type expressed in terms of either the VC dimension or the sample compression size. This general technique also enables us to derive several new bounds on the error rates of general sample-consistent learning algorithms, as well as refined bounds on the label complexity of the CAL active learning algorithm. Additionally, we establish a simple necessary and sufficient condition for the existence of a distribution-free bound on the error rates of all sample-consistent learning rules, converging at a rate inversely proportional to the sample size. We also study learning in the presence of classification noise, deriving a new excess error rate guarantee for general VC classes under Tsybakov's noise condition, and establishing a simple and general necessary and sufficient condition for the minimax excess risk under bounded noise to converge at a rate inversely proportional to the sample size.

arXiv:1609.03628

Co-active Learning to Adapt Humanoid Movement for Manipulation

In this paper we address the problem of robot movement adaptation under various environmental constraints interactively. Motion primitives are generally adopted to generate target motion from demonstrations. However, their generalization capability is weak while facing novel environments. Additionally, traditional motion generation methods do not consider the versatile constraints from various users, tasks, and environments. In this work, we propose a co-active learning framework for learning to adapt robot end-effector's movement for manipulation tasks. It is designed to adapt the original imitation trajectories, which are learned from demonstrations, to novel situations with various constraints. The framework also considers user's feedback towards the adapted trajectories, and it learns to adapt movement through human-in-the-loop interactions. The implemented system generalizes trained motion primitives to various situations with different constraints considering user preferences. Experiments on a humanoid platform validate the effectiveness of our approach.

arXiv:1610.03995

Semi-Supervised Active Learning for Support Vector Machines: A Novel Approach that Exploits Structure Information in Data

In our today's information society more and more data emerges, e.g.~in social networks, technical applications, or business applications. Companies try to commercialize these data using data mining or machine learning methods. For this purpose, the data are categorized or classified, but often at high (monetary or temporal) costs. An effective approach to reduce these costs is to apply any kind of active learning (AL) methods, as AL controls the training process of a classifier by specific querying individual data points (samples), which are then labeled (e.g., provided with class memberships) by a domain expert. However, an analysis of current AL research shows that AL still has some shortcomings. In particular, the structure information given by the spatial pattern of the (un)labeled data in the input space of a classification model (e.g.,~cluster information), is used in an insufficient way. In addition, many existing AL techniques pay too little attention to their practical applicability. To meet these challenges, this article presents several techniques that together build a new approach for combining AL and semi-supervised learning (SSL) for support vector machines (SVM) in classification tasks. Structure information is captured by means of probabilistic models that are iteratively improved at runtime when label information becomes available. The probabilistic models are considered in a selection strategy based on distance, density, diversity, and distribution (4DS strategy) information for AL and in a kernel function (Responsibility Weighted Mahalanobis kernel) for SVM. The approach fuses generative and discriminative modeling techniques. With 20 benchmark data sets and with the MNIST data set it is shown that our new solution yields significantly better results than state-of-the-art methods.

arXiv:1605.08798

Asymptotic Analysis of Objectives based on Fisher Information in Active Learning

Obtaining labels can be costly and time-consuming. Active learning allows a learning algorithm to intelligently query samples to be labeled for efficient learning. Fisher information ratio (FIR) has been used as an objective for selecting queries in active learning. However, little is known about the theory behind the use of FIR for active learning. There is a gap between the underlying theory and the motivation of its usage in practice. In this paper, we attempt to fill this gap and provide a rigorous framework for analyzing existing FIR-based active learning methods. In particular, we show that FIR can be asymptotically viewed as an upper bound of the expected variance of the log-likelihood ratio. Additionally, our analysis suggests a unifying framework that not only enables us to make theoretical comparisons among the existing querying methods based on FIR, but also allows us to give insight into the development of new active learning approaches based on this objective.

arXiv:1605.06792

Active Nearest-Neighbor Learning in Metric Spaces

We propose a pool-based non-parametric active learning algorithm for general metric spaces, called MArgin Regularized Metric Active Nearest Neighbor (MARMANN), which outputs a nearest-neighbor classifier. We give prediction error guarantees that depend on the noisy-margin properties of the input sample, and are competitive with those obtained by previously proposed passive learners. We prove that the label complexity of MARMANN is significantly lower than that of any passive learner with similar error guarantees. MARMANN is based on a generalized sample compression scheme, and a new label-efficient active model-selection procedure.