Machine Learning
Accurate inference of crowdsourcing properties when using efficient allocation strategies (1903.03104v1)
Abigail Hotaling, James P. Bagrow
2019-03-07
Allocation strategies improve the efficiency of crowdsourcing by decreasing the work needed to complete individual tasks accurately. However, these algorithms introduce bias by preferentially allocating workers onto easy tasks, leading to sets of completed tasks that are no longer representative of all tasks. This bias challenges inference of problem-wide properties such as typical task difficulty or crowd properties such as worker completion times, important information that goes beyond the crowd responses themselves. Here we study inference about problem properties when using an allocation algorithm to improve crowd efficiency. We introduce Decision-Explicit Probability Sampling (DEPS), a method to perform inference of problem properties while accounting for the potential bias introduced by an allocation strategy. Experiments on real and synthetic crowdsourcing data show that DEPS outperforms baseline inference methods while still leveraging the efficiency gains of the allocation method. The ability to perform accurate inference of general properties when using non-representative data allows crowdsourcers to extract more knowledge out of a given crowdsourced dataset.
Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examples (1903.03096v1)
Eleni Triantafillou, Tyler Zhu, Vincent Dumoulin, Pascal Lamblin, Kelvin Xu, Ross Goroshin, Carles Gelada, Kevin Swersky, Pierre-Antoine Manzagol, Hugo Larochelle
2019-03-07
Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle this recently, we find the current procedure and datasets that are used to systematically assess progress in this setting lacking. To address this, we propose Meta-Dataset: a new benchmark for training and evaluating few-shot classifiers that is large-scale, consists of multiple datasets, and presents more natural and realistic tasks. The aim is to measure the ability of state-of-the-art models to leverage diverse sources of data to achieve higher generalization, and to evaluate that generalization ability in a more challenging setting. We additionally measure robustness of current methods to variations in the number of available examples and the number of classes. Finally our extensive empirical evaluation leads us to identify weaknesses in Prototypical Networks and MAML, two popular few-shot classification methods, and to propose a new method, Proto-MAML, which achieves improved performance on our benchmark.
Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions (1903.03088v1)
Matthew MacKay, Paul Vicol, Jon Lorraine, David Duvenaud, Roger Grosse
2019-03-07
Hyperparameter optimization can be formulated as a bilevel optimization problem, where the optimal parameters on the training set depend on the hyperparameters. We aim to adapt regularization hyperparameters for neural networks by fitting compact approximations to the best-response function, which maps hyperparameters to optimal weights and biases. We show how to construct scalable best-response approximations for neural networks by modeling the best-response as a single network whose hidden units are gated conditionally on the regularizer. We justify this approximation by showing the exact best-response for a shallow linear network with L2-regularized Jacobian can be represented by a similar gating mechanism. We fit this model using a gradient-based hyperparameter optimization algorithm which alternates between approximating the best-response around the current hyperparameters and optimizing the hyperparameters using the approximate best-response function. Unlike other gradient-based approaches, we do not require differentiating the training loss with respect to the hyperparameters, allowing us to tune discrete hyperparameters, data augmentation hyperparameters, and dropout probabilities. Because the hyperparameters are adapted online, our approach discovers hyperparameter schedules that can outperform fixed hyperparameter values. Empirically, our approach outperforms competing hyperparameter optimization methods on large-scale deep learning problems. We call our networks, which update their own hyperparameters online during training, Self-Tuning Networks (STNs).
Quantum Latent Semantic Analysis (1903.03082v1)
Fabio A. González, Juan C. Caicedo
2019-03-07
The main goal of this paper is to explore latent topic analysis (LTA), in the context of quantum information retrieval. LTA is a valuable technique for document analysis and representation, which has been extensively used in information retrieval and machine learning. Different LTA techniques have been proposed, some based on geometrical modeling (such as latent semantic analysis, LSA) and others based on a strong statistical foundation. However, these two different approaches are not usually mixed. Quantum information retrieval has the remarkable virtue of combining both geometry and probability in a common principled framework. We built on this quantum framework to propose a new LTA method, which has a clear geometrical motivation but also supports a well-founded probabilistic interpretation. An initial exploratory experimentation was performed on three standard data sets. The results show that the proposed method outperforms LSA on two of the three datasets. These results suggests that the quantum-motivated representation is an alternative for geometrical latent topic modeling worthy of further exploration.
RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm for Continuous Control of Nonlinear Dynamical Systems (1903.03064v1)
Ekaterina Abramova, Luke Dickens, Daniel Kuhn, Aldo Faisal
2019-03-07
Nonlinear optimal control problems are often solved with numerical methods that require knowledge of system's dynamics which may be difficult to infer, and that carry a large computational cost associated with iterative calculations. We present a novel neurobiologically inspired hierarchical learning framework, Reinforcement Learning Optimal Control, which operates on two levels of abstraction and utilises a reduced number of controllers to solve nonlinear systems with unknown dynamics in continuous state and action spaces. Our approach is inspired by research at two levels of abstraction: first, at the level of limb coordination human behaviour is explained by linear optimal feedback control theory. Second, in cognitive tasks involving learning symbolic level action selection, humans learn such problems using model-free and model-based reinforcement learning algorithms. We propose that combining these two levels of abstraction leads to a fast global solution of nonlinear control problems using reduced number of controllers. Our framework learns the local task dynamics from naive experience and forms locally optimal infinite horizon Linear Quadratic Regulators which produce continuous low-level control. A top-level reinforcement learner uses the controllers as actions and learns how to best combine them in state space while maximising a long-term reward. A single optimal control objective function drives high-level symbolic learning by providing training signals on desirability of each selected controller. We show that a small number of locally optimal linear controllers are able to solve global nonlinear control problems with unknown dynamics when combined with a reinforcement learner in this hierarchical framework. Our algorithm competes in terms of computational cost and solution quality with sophisticated control algorithms and we illustrate this with solutions to benchmark problems.
Analysis Dictionary Learning: An Efficient and Discriminative Solution (1903.03058v1)
Wen Tang, Ashkan Panahi, Hamid Krim, Liyi Dai
2019-03-07
Discriminative Dictionary Learning (DL) methods have been widely advocated for image classification problems. To further sharpen their discriminative capabilities, most state-of-the-art DL methods have additional constraints included in the learning stages. These various constraints, however, lead to additional computational complexity. We hence propose an efficient Discriminative Convolutional Analysis Dictionary Learning (DCADL) method, as a lower cost Discriminative DL framework, to both characterize the image structures and refine the interclass structure representations. The proposed DCADL jointly learns a convolutional analysis dictionary and a universal classifier, while greatly reducing the time complexity in both training and testing phases, and achieving a competitive accuracy, thus demonstrating great performance in many experiments with standard databases.
Fast Graph Representation Learning with PyTorch Geometric (1903.02428v2)
Matthias Fey, Jan Eric Lenssen
2019-03-06
We introduce PyTorch Geometric, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch. In addition to general graph data structures and processing methods, it contains a variety of recently published methods from the domains of relational learning and 3D data processing. PyTorch Geometric achieves high data throughput by leveraging sparse GPU acceleration, by providing dedicated CUDA kernels and by introducing efficient mini-batch handling for input examples of different size. In this work, we present the library in detail and perform a comprehensive comparative study of the implemented methods in homogeneous evaluation scenarios.
Efficient and Effective Quantization for Sparse DNNs (1903.03046v1)
Yiren Zhao, Xitong Gao, Daniel Bates, Robert Mullins, Cheng-Zhong Xu
2019-03-07
Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs poses a challenge in deploying them on constrained devices. Existing compression techniques show promising performance in reducing the size and computation complexity of CNNs for efficient inference, but there lacks a method to integrate them effectively. In this paper, we attend to the statistical properties of sparse CNNs and present focused quantization, a novel quantization strategy based on powers-of-two values, which exploits the weight distributions after fine-grained pruning. The proposed method dynamically discovers the most effective numerical representation for weights in layers with varying sparsities, to minimize the impact of quantization on the task accuracy. Multiplications in quantized CNNs can be replaced with much cheaper bit-shift operations for efficient inference. Coupled with lossless encoding, we build a compression pipeline that provides CNNs high compression ratios (CR) and minimal loss in accuracies. In ResNet-50, we achieve a
CR with only
loss in top-5 accuracy, outperforming existing compression pipelines.
Deterministic Variational Inference for Robust Bayesian Neural Networks (1810.03958v2)
Anqi Wu, Sebastian Nowozin, Edward Meeds, Richard E. Turner, José Miguel Hernández-Lobato, Alexander L. Gaunt
2018-10-09
Bayesian neural networks (BNNs) hold great promise as a flexible and principled solution to deal with uncertainty when learning from finite data. Among approaches to realize probabilistic inference in deep neural networks, variational Bayes (VB) is theoretically grounded, generally applicable, and computationally efficient. With wide recognition of potential advantages, why is it that variational Bayes has seen very limited practical use for BNNs in real applications? We argue that variational inference in neural networks is fragile: successful implementations require careful initialization and tuning of prior variances, as well as controlling the variance of Monte Carlo gradient estimates. We provide two innovations that aim to turn VB into a robust inference tool for Bayesian neural networks: first, we introduce a novel deterministic method to approximate moments in neural networks, eliminating gradient variance; second, we introduce a hierarchical prior for parameters and a novel Empirical Bayes procedure for automatically selecting prior variances. Combining these two innovations, the resulting method is highly efficient and robust. On the application of heteroscedastic regression we demonstrate good predictive performance over alternative approaches.
Characterization of Posidonia Oceanica Seagrass Aerenchyma through Whole Slide Imaging: A Pilot Study (1903.03044v1)
Olivier Debeir, Justine Allard, Christine Decaestecker, Jean-Pierre Hermand
2019-03-07
Characterizing the tissue morphology and anatomy of seagrasses is essential to predicting their acoustic behavior. In this pilot study, we use histology techniques and whole slide imaging (WSI) to describe the composition and topology of the aerenchyma of an entire leaf blade in an automatic way combining the advantages of X-ray microtomography and optical microscopy. Paraffin blocks are prepared in such a way that microtome slices contain an arbitrarily large number of cross sections distributed along the full length of a blade. The sample organization in the paraffin block coupled with whole slide image analysis allows high throughput data extraction and an exhaustive characterization along the whole blade length. The core of the work are image processing algorithms that can identify cells and air lacunae (or void) from fiber strand, epidermis, mesophyll and vascular system. A set of specific features is developed to adequately describe the convexity of cells and voids where standard descriptors fail. The features scrutinize the local curvature of the object borders to allow an accurate discrimination between void and cell through machine learning. The algorithm allows to reconstruct the cells and cell membrane features that are relevant to tissue density, compressibility and rigidity. Size distribution of the different cell types and gas spaces, total biomass and total void volume fraction are then extracted from the high resolution slices to provide a complete characterization of the tissue along the leave from its base to the apex.
