Machine Learning
Assessing Generalization in Deep Reinforcement Learning (1810.12282v2)
Charles Packer, Katelyn Gao, Jernej Kos, Philipp Krähenbühl, Vladlen Koltun, Dawn Song
2018-10-29
Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and experimental setups for evaluation. The literature lacks a controlled assessment of the merits of different generalization schemes. Our aim is to catalyze community-wide progress on generalization in deep RL. To this end, we present a benchmark and experimental protocol, and conduct a systematic empirical study. Our framework contains a diverse set of environments, our methodology covers both in-distribution and out-of-distribution generalization, and our evaluation includes deep RL algorithms that specifically tackle generalization. Our key finding is that `vanilla' deep RL algorithms generalize better than specialized schemes that were proposed specifically to tackle generalization.
Multi-Stage Fault Warning for Large Electric Grids Using Anomaly Detection and Machine Learning (1903.06700v1)
Sanjeev Raja, Ernest Fokoué
2019-03-15
In the monitoring of a complex electric grid, it is of paramount importance to provide operators with early warnings of anomalies detected on the network, along with a precise classification and diagnosis of the specific fault type. In this paper, we propose a novel multi-stage early warning system prototype for electric grid fault detection, classification, subgroup discovery, and visualization. In the first stage, a computationally efficient anomaly detection method based on quartiles detects the presence of a fault in real time. In the second stage, the fault is classified into one of nine pre-defined disaster scenarios. The time series data are first mapped to highly discriminative features by applying dimensionality reduction based on temporal autocorrelation. The features are then mapped through one of three classification techniques: support vector machine, random forest, and artificial neural network. Finally in the third stage, intra-class clustering based on dynamic time warping is used to characterize the fault with further granularity. Results on the Bonneville Power Administration electric grid data show that i) the proposed anomaly detector is both fast and accurate; ii) dimensionality reduction leads to dramatic improvement in classification accuracy and speed; iii) the random forest method offers the most accurate, consistent, and robust fault classification; and iv) time series within a given class naturally separate into five distinct clusters which correspond closely to the geographical distribution of electric grid buses.
Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly (1903.06694v1)
Kirthevasan Kandasamy, Karun Raju Vysyaraju, Willie Neiswanger, Biswajit Paria, Christopher R. Collins, Jeff Schneider, Barnabas Poczos, Eric P. Xing
2019-03-15
Bayesian Optimisation (BO), refers to a suite of techniques for global optimisation of expensive black box functions, which use introspective Bayesian models of the function to efficiently find the optimum. While BO has been applied successfully in many applications, modern optimisation tasks usher in new challenges where conventional methods fail spectacularly. In this work, we present Dragonfly, an open source Python library for scalable and robust BO. Dragonfly incorporates multiple recently developed methods that allow BO to be applied in challenging real world settings; these include better methods for handling higher dimensional domains, methods for handling multi-fidelity evaluations when cheap approximations of an expensive function are available, methods for optimising over structured combinatorial spaces, such as the space of neural network architectures, and methods for handling parallel evaluations. Additionally, we develop new methodological improvements in BO for selecting the Bayesian model, selecting the acquisition function, and optimising over complex domains with different variable types and additional constraints. We compare Dragonfly to a suite of other packages and algorithms for global optimisation and demonstrate that when the above methods are integrated, they enable significant improvements in the performance of BO. The Dragonfly library is available at dragonfly.github.io.
Efficient Inference in Multi-task Cox Process Models (1805.09781v3)
Virginia Aglietti, Theodoros Damoulas, Edwin Bonilla
2018-05-24
We generalize the log Gaussian Cox process (LGCP) framework to model multiple correlated point data jointly. The observations are treated as realizations of multiple LGCPs, whose log intensities are given by linear combinations of latent functions drawn from Gaussian process priors. The combination coefficients are also drawn from Gaussian processes and can incorporate additional dependencies. We derive closed-form expressions for the moments of the intensity functions and develop an efficient variational inference algorithm that is orders of magnitude faster than competing deterministic and stochastic approximations of multivariate LGCP, coregionalization models, and multi-task permanental processes. Our approach outperforms these benchmarks in multiple problems, offering the current state of the art in modeling multivariate point processes.
Improving Strong-Scaling of CNN Training by Exploiting Finer-Grained Parallelism (1903.06681v1)
Nikoli Dryden, Naoya Maruyama, Tom Benson, Tim Moon, Marc Snir, Brian Van Essen
2019-03-15
Scaling CNN training is necessary to keep up with growing datasets and reduce training time. We also see an emerging need to handle datasets with very large samples, where memory requirements for training are large. Existing training frameworks use a data-parallel approach that partitions samples within a mini-batch, but limits to scaling the mini-batch size and memory consumption makes this untenable for large samples. We describe and implement new approaches to convolution, which parallelize using spatial decomposition or a combination of sample and spatial decomposition. This introduces many performance knobs for a network, so we develop a performance model for CNNs and present a method for using it to automatically determine efficient parallelization strategies. We evaluate our algorithms with microbenchmarks and image classification with ResNet-50. Our algorithms allow us to prototype a model for a mesh-tangling dataset, where sample sizes are very large. We show that our parallelization achieves excellent strong and weak scaling and enables training for previously unreachable datasets.
A Review of Reinforcement Learning for Autonomous Building Energy Management (1903.05196v2)
Karl Mason, Santiago Grijalva
2019-03-12
The area of building energy management has received a significant amount of interest in recent years. This area is concerned with combining advancements in sensor technologies, communications and advanced control algorithms to optimize energy utilization. Reinforcement learning is one of the most prominent machine learning algorithms used for control problems and has had many successful applications in the area of building energy management. This research gives a comprehensive review of the literature relating to the application of reinforcement learning to developing autonomous building energy management systems. The main direction for future research and challenges in reinforcement learning are also outlined.
GEE: A Gradient-based Explainable Variational Autoencoder for Network Anomaly Detection (1903.06661v1)
Quoc Phong Nguyen, Kar Wai Lim, Dinil Mon Divakaran, Kian Hsiang Low, Mun Choon Chan
2019-03-15
This paper looks into the problem of detecting network anomalies by analyzing NetFlow records. While many previous works have used statistical models and machine learning techniques in a supervised way, such solutions have the limitations that they require large amount of labeled data for training and are unlikely to detect zero-day attacks. Existing anomaly detection solutions also do not provide an easy way to explain or identify attacks in the anomalous traffic. To address these limitations, we develop and present GEE, a framework for detecting and explaining anomalies in network traffic. GEE comprises of two components: (i) Variational Autoencoder (VAE) - an unsupervised deep-learning technique for detecting anomalies, and (ii) a gradient-based fingerprinting technique for explaining anomalies. Evaluation of GEE on the recent UGR dataset demonstrates that our approach is effective in detecting different anomalies as well as identifying fingerprints that are good representations of these various attacks.
Rectified deep neural networks overcome the curse of dimensionality for nonsmooth value functions in zero-sum games of nonlinear stiff systems (1903.06652v1)
Christoph Reisinger, Yufei Zhang
2019-03-15
In this paper, we establish that for a wide class of controlled stochastic differential equations (SDEs) with stiff coefficients, the value functions of corresponding zero-sum games can be represented by a deep artificial neural network (DNN), whose complexity grows at most polynomially in both the dimension of the state equation and the reciprocal of the required accuracy. Such nonlinear stiff systems may arise, for example, from Galerkin approximations of controlled stochastic partial differential equations (SPDEs), or controlled PDEs with uncertain initial conditions and source terms. This implies that DNNs can break the curse of dimensionality in numerical approximations and optimal control of PDEs and SPDEs. The main ingredient of our proof is to construct a suitable discrete-time system to effectively approximate the evolution of the underlying stochastic dynamics. Similar ideas can also be applied to obtain expression rates of DNNs for value functions induced by stiff systems with regime switching coefficients and driven by general L'{e}vy noise.
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length (1807.05031v4)
Stanisław Jastrzębski, Zachary Kenton, Nicolas Ballas, Asja Fischer, Yoshua Bengio, Amos Storkey
2018-07-13
Stochastic Gradient Descent (SGD) based training of neural networks with a large learning rate or a small batch-size typically ends in well-generalizing, flat regions of the weight space, as indicated by small eigenvalues of the Hessian of the training loss. However, the curvature along the SGD trajectory is poorly understood. An empirical investigation shows that initially SGD visits increasingly sharp regions, reaching a maximum sharpness determined by both the learning rate and the batch-size of SGD. When studying the SGD dynamics in relation to the sharpest directions in this initial phase, we find that the SGD step is large compared to the curvature and commonly fails to minimize the loss along the sharpest directions. Furthermore, using a reduced learning rate along these directions can improve training speed while leading to both sharper and better generalizing solutions compared to vanilla SGD. In summary, our analysis of the dynamics of SGD in the subspace of the sharpest directions shows that they influence the regions that SGD steers to (where larger learning rate or smaller batch size result in wider regions visited), the overall training speed, and the generalization ability of the final model.
Sentiment Analysis of Czech Texts: An Algorithmic Survey (1901.02780v2)
Erion Çano, Ondřej Bojar
2019-01-09
In the area of online communication, commerce and transactions, analyzing sentiment polarity of texts written in various natural languages has become crucial. While there have been a lot of contributions in resources and studies for the English language, "smaller" languages like Czech have not received much attention. In this survey, we explore the effectiveness of many existing machine learning algorithms for sentiment analysis of Czech Facebook posts and product reviews. We report the sets of optimal parameter values for each algorithm and the scores in both datasets. We finally observe that support vector machines are the best classifier and efforts to increase performance even more with bagging, boosting or voting ensemble schemes fail to do so.