Posted Content•
Neural Architecture Search with Reinforcement Learning
TL;DR: This paper uses a recurrent network to generate the model descriptions of neural networks and trains this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set.
Abstract: Neural networks are powerful and flexible models that work well for many difficult learning tasks in image, speech and natural language understanding. Despite their success, neural networks are still hard to design. In this paper, we use a recurrent network to generate the model descriptions of neural networks and train this RNN with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation set. On the CIFAR-10 dataset, our method, starting from scratch, can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy. Our CIFAR-10 model achieves a test error rate of 3.65, which is 0.09 percent better and 1.05x faster than the previous state-of-the-art model that used a similar architectural scheme. On the Penn Treebank dataset, our model can compose a novel recurrent cell that outperforms the widely-used LSTM cell, and other state-of-the-art baselines. Our cell achieves a test set perplexity of 62.4 on the Penn Treebank, which is 3.6 perplexity better than the previous state-of-the-art model. The cell can also be transferred to the character language modeling task on PTB and achieves a state-of-the-art perplexity of 1.214.
Citations
More filters
Proceedings Article•
18 May 2021TL;DR: In this paper, a dynamic one-shot search space for multi-branch neural architectures of GNNs is proposed, which maintains a subset of the large search space along with a set of importance weights for operation candidates in the subset as the architecture parameters.
Abstract: Relying on the diverse graph convolution operations that have emerged in recent years, graph neural networks (GNNs) are shown to be powerful to deal with high-dimensional non-Euclidean domains, such as social networks or citation networks. Despite the tremendous human efforts been taken to explore new graph convolution operations, there are a few attempts to automatically search operations in GNNs. The search space of GNNs is significantly larger than that of CNNs, because of diverse components in the message-passing of GNNs. This, therefore, prevents the straightforward application of classical NAS methods for GNNs. In this work, we propose a novel dynamic one-shot search space for multi-branch neural architectures of GNNs. The dynamic search space maintains a subset of the large search space along with a set of importance weights for operation candidates in the subset as the architecture parameters. After each iteration, the subset is pruned by removing candidates with low importance weights and is expanded with new operations. The dynamic subsets of operation candidates are not uniform but is individual for each edge in the computation graph of the neural architecture, which can ensure the diversity of operations in the final architecture is as competitive as direct search in the large search space. Our experiments of semi-supervised and supervised node classification on citation networks, including Cora, Citeseer, and Pubmed, demonstrate that our method outperforms the current state-of-the-art manually designed architectures and reaches competitive performance to existing GNN NAS approaches with up to 10 times of speedup.
9 citations
TL;DR: A theoretical and conceptual framework to design neural architectures for Bayesian compressive sensing of simplex-constrained sparse stochastic vectors and shows that the proposed architecture yields superior approximations with less parameters when compared to a standard ReLU architecture in a supervised learning setting.
Abstract: This paper presents a theoretical and conceptual framework to design neural architectures for Bayesian compressive sensing of simplex-constrained sparse stochastic vectors. First, we recast the problem of MMSE estimation (w.r.t. a pre-defined uniform input distribution over the simplex) as the problem of computing the centroid of a polytope that is equal to the intersection of the simplex and an affine subspace determined by compressive measurements. Then, we use multidimensional Laplace techniques to obtain a closed-form solution to this computation problem, and we show how to map this solution to a neural architecture comprising threshold functions, rectified linear (ReLU) and rectified polynomial activation functions. In the proposed architecture, the number of layers is equal to the number of measurements that allows for faster solutions in the low-measurement regime when compared to the integration by domain decomposition or Monte Carlo approximation. We also show by simulation that the proposed solution is robust to small model mismatches; furthermore, the proposed architecture yields superior approximations with less parameters when compared to a standard ReLU architecture in a supervised learning setting.
9 citations
Cites background from "Neural Architecture Search with Rei..."
...Obtaining neural architectures ‘from scratch’ using excessive computational resources via so-called architecture search has been applied for the problem of image classification in [21], [22] but the efficacy for sparse signal recovery is unclear....
[...]
Posted Content•
TL;DR: This work proposes a sampling method adaptive to the distribution entropy, drawing more samples to encourage explorations at the beginning, and reducing samples as learning proceeds to search fast in the multivariate space, and calls this method Fast Probabilistic NAS.
Abstract: Differential Neural Architecture Search (NAS) requires all layer choices to be held in memory simultaneously; this limits the size of both search space and final architecture. In contrast, Probabilistic NAS, such as PARSEC, learns a distribution over high-performing architectures, and uses only as much memory as needed to train a single model. Nevertheless, it needs to sample many architectures, making it computationally expensive for searching in an extensive space. To solve these problems, we propose a sampling method adaptive to the distribution entropy, drawing more samples to encourage explorations at the beginning, and reducing samples as learning proceeds. Furthermore, to search fast in the multi-variate space, we propose a coarse-to-fine strategy by using a factorized distribution at the beginning which can reduce the number of architecture parameters by over an order of magnitude. We call this method Fast Probabilistic NAS (FP-NAS). Compared with PARSEC, it can sample 64% fewer architectures and search 2.1x faster. Compared with FBNetV2, FP-NAS is 1.9x - 3.5x faster, and the searched models outperform FBNetV2 models on ImageNet. FP-NAS allows us to expand the giant FBNetV2 space to be wider (i.e. larger channel choices) and deeper (i.e. more blocks), while adding Split-Attention block and enabling the search over the number of splits. When searching a model of size 0.4G FLOPS, FP-NAS is 132x faster than EfficientNet, and the searched FP-NAS-L0 model outperforms EfficientNet-B0 by 0.7% accuracy. Without using any architecture surrogate or scaling tricks, we directly search large models up to 1.0G FLOPS. Our FP-NAS-L2 model with simple distillation outperforms BigNAS-XL with advanced in-place distillation by 0.7% accuracy using similar FLOPS.
9 citations
Cites background or methods from "Neural Architecture Search with Rei..."
...However, early approaches based on evolution or reinforcement learning take hundreds or thousands of GPU days just for CIFAR10 or Imagenet target datasets [42, 43, 31, 25]....
[...]
...In the pioneering work [42], a RNN controller is adopted to sample architectures, which are trained to obtain accuracy as the reward signal for updating the controller....
[...]
Posted Content•
TL;DR: The subjective human factor in comparisons of state of the art results and scientific reproducibility in deep learning is investigated and a strong positive correlation between the participant's experience and the final performance is shown.
Abstract: How does a user's prior experience with deep learning impact accuracy? We present an initial study based on 31 participants with different levels of experience. Their task is to perform hyperparameter optimization for a given deep learning architecture. The results show a strong positive correlation between the participant's experience and the final performance. They additionally indicate that an experienced participant finds better solutions using fewer resources on average. The data suggests furthermore that participants with no prior experience follow random strategies in their pursuit of optimal hyperparameters. Our study investigates the subjective human factor in comparisons of state of the art results and scientific reproducibility in deep learning.
9 citations
Additional excerpts
...Finding the best hyperparameters is something that can be done automatically by autoML [2, 7, 15, 17] or Neural Architecture Search [8, 22, 27, 36]....
[...]
Posted Content•
TL;DR: In this article, the authors present and motivate the problem of efficiency in deep learning, followed by a thorough survey of the five core areas of model efficiency (spanning modeling techniques, infrastructure, and hardware) and the seminal work there.
Abstract: Deep Learning has revolutionized the fields of computer vision, natural language understanding, speech recognition, information retrieval and more. However, with the progressive improvements in deep learning models, their number of parameters, latency, resources required to train, etc. have all have increased significantly. Consequently, it has become important to pay attention to these footprint metrics of a model as well, not just its quality. We present and motivate the problem of efficiency in deep learning, followed by a thorough survey of the five core areas of model efficiency (spanning modeling techniques, infrastructure, and hardware) and the seminal work there. We also present an experiment-based guide along with code, for practitioners to optimize their model training and deployment. We believe this is the first comprehensive survey in the efficient deep learning space that covers the landscape of model efficiency from modeling techniques to hardware support. Our hope is that this survey would provide the reader with the mental model and the necessary understanding of the field to apply generic efficiency techniques to immediately get significant improvements, and also equip them with ideas for further research and experimentation to achieve additional gains.
9 citations
References
More filters
27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
123,388 citations
Proceedings Article•
01 Jan 2015TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Abstract: We introduce Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. The method is straightforward to implement, is computationally efficient, has little memory requirements, is invariant to diagonal rescaling of the gradients, and is well suited for problems that are large in terms of data and/or parameters. The method is also appropriate for non-stationary objectives and problems with very noisy and/or sparse gradients. The hyper-parameters have intuitive interpretations and typically require little tuning. Some connections to related algorithms, on which Adam was inspired, are discussed. We also analyze the theoretical convergence properties of the algorithm and provide a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Empirical results demonstrate that Adam works well in practice and compares favorably to other stochastic optimization methods. Finally, we discuss AdaMax, a variant of Adam based on the infinity norm.
111,197 citations
Proceedings Article•
04 Sep 2014TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
55,235 citations
"Neural Architecture Search with Rei..." refers methods in this paper
...Along with this success is a paradigm shift from feature designing to architecture designing, i.e., from SIFT (Lowe, 1999), and HOG (Dalal & Triggs, 2005), to AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al., 2015), and ResNet (He et al., 2016a)....
[...]
01 Jan 1998
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.
42,067 citations
20 Jun 2005
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Abstract: We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection. We study the influence of each stage of the computation on performance, concluding that fine-scale gradients, fine orientation binning, relatively coarse spatial binning, and high-quality local contrast normalization in overlapping descriptor blocks are all important for good results. The new approach gives near-perfect separation on the original MIT pedestrian database, so we introduce a more challenging dataset containing over 1800 annotated human images with a large range of pose variations and backgrounds.
31,952 citations
"Neural Architecture Search with Rei..." refers methods in this paper
...Along with this success is a paradigm shift from feature designing to architecture designing, i.e., from SIFT (Lowe, 1999), and HOG (Dalal & Triggs, 2005), to AlexNet (Krizhevsky et al., 2012), VGGNet (Simonyan & Zisserman, 2014), GoogleNet (Szegedy et al., 2015), and ResNet (He et al., 2016a)....
[...]