This paper presents a simulator-assisted training method (SimVAE) for variational autoencoders (VAE) that leads to a disentangled and interpretable latent space. Training SimVAE is a two-step process in which first a deep generator network(decoder) is trained to approximate the simulator. During this step, the simulator acts as the data source or as a teacher network. Then an inference network (encoder)is trained to invert the decoder. As such, upon complete training, the encoder represents an approximately inverted simulator. By decoupling the training of the encoder and decoder we bypass some of the difficulties that arise in training generative models such as VAEs and generative adversarial networks (GANs). We show applications of our approach in a variety of domains such as circuit design, graphics de-rendering and other natural science problems that involve inference via simulation.

The performance of deep neural networks is significantly affected by how well mini-batches are constructed. In this paper, we propose a novel adaptive batch selection algorithm called Recency Bias that exploits the uncertain samples predicted inconsistently in recent iterations. The historical label predictions of each sample are used to evaluate its predictive uncertainty within a sliding window. By taking advantage of this design, Recency Bias not only accelerates the training step but also achieves a more accurate network. We demonstrate the superiority of Recency Bias by extensive evaluation on two independent tasks. Compared with existing batch selection methods, the results showed that Recency Bias reduced the test error by up to 20.5% in a fixed wall-clock training time. At the same time, it improved the training time by up to 59.3% to reach the same test error.

Sparse principal component analysis (PCA) is an important technique for dimensionality reduction of high-dimensional data. However, most existing sparse PCA algorithms are based on non-convex optimization, which provide little guarantee on the global convergence. Sparse PCA algorithms based on a convex formulation, for example the Fantope projection and selection (FPS), overcome this difficulty, but are computationally expensive. In this work we study sparse PCA based on the convex FPS formulation, and propose a new algorithm that is computationally efficient and applicable to large and high-dimensional data sets. Nonasymptotic and explicit bounds are derived for both the optimization error and the statistical accuracy, which can be used for testing and inference problems. We also extend our algorithm to online learning problems, where data are obtained in a streaming fashion. The proposed algorithm is applied to high-dimensional gene expression data for the detection of functional gene groups.

Outlier based Robust Principal Component Analysis (RPCA) requires centering of the non-outliers. We show a "bias trick" that automatically centers these non-outliers. Using this bias trick we obtain the first RPCA algorithm that is optimal with respect to centering.

A BSTRACT We introduce and study the problem of Online Continual Compression, where one attempts to learn to compress and store a representative dataset from a non i.i.d data stream, while only observing each sample once. This problem is highly relevant for downstream online continual learning tasks, as well as standard learning methods under resource constrained data collection. To address this we propose a new architecture which Stacks Quantization Modules (SQM), consisting of a series of discrete autoencoders, each equipped with their own memory. Every added module is trained to reconstruct the latent space of the previous module using fewer bits, allowing the learned representation to become more compact as training progresses. This modularity has several advantages: 1) moderate compressions are quickly available early in training, which is crucial for remembering the early tasks, 2) as more data needs to be stored, earlier data becomes more compressed, freeing memory, 3) unlike previous methods, our approach does not require pretraining, even on challenging datasets. We show several potential applications of this method. We first replace the episodic memory used in Experience Replay with SQM, leading to significant gains on standard continual learning benchmarks using a fixed memory budget. We then apply our method to online compression of larger images like those from Imagenet, and show that it is also effective with other modalities, such as LiDAR data. 1 I NTRODUCTION Interest in machine learning in recent years has been fueled by the plethora of data being generated on a regular basis. Effectively storing and using this data is critical for many applications, especially those involving continual learning. In general, compression techniques can greatly improve data storage capacity, and, if done well, reduce the memory and compute usage in downstream machine learning tasks (Gueguen et al., 2018; Oyallon et al., 2018). Thus, learned compression has become a topic of great interest (Theis et al., 2017; Ball e et al., 2016; Johnston et al., 2018).

State-of-the-art adversarial attacks on neural networks use expensive iterative methods and numerous random restarts from different initial points. Iterative FGSM-based methods without restarts trade off performance for computational efficiency because they do not adequately explore the image space and are highly sensitive to the choice of step size. We propose a variant of Projected Gradient Descent (PGD) that uses a random step size to improve performance without resorting to expensive random restarts. Our method, Wide Iterative Stochastic crafting (WITCHcraft), achieves results superior to the classical PGD attack on the CIFAR-10 and MNIST data sets but without additional computational cost. This simple modification of PGD makes crafting attacks more economical, which is important in situations like adversarial training where attacks need to be crafted in real time.

Many real world tasks such as 3D object detection and high-resolution image classification involve learning from a set of instances. In these cases, only a group of instances, a set, collectively contains meaningful information and therefore only the sets have labels, and not individual data instances. In this work, we present a permutation invariant neural network called a \textbf{Memory-based Exchangeable Model (MEM)} for learning set functions. The model consists of memory units that embed an input sequence to high-level features (memories) enabling the model to learn inter-dependencies among instances of the set in the form of attention vectors. To demonstrate its learning ability, we evaluated our model on test datasets created using MNIST, point cloud classification, and population estimation. We also tested the model for classifying histopathology whole slide images to discriminate between two subtypes of Lung cancer---Lung Adenocarcinoma, and Lung Squamous Cell Carcinoma. We systematically extracted patches from lung cancer images from The Cancer Genome Atlas~(TCGA) dataset, the largest public repository of histopathology images. The proposed method achieved a competitive classification accuracy of 84.84\%. The results on other datasets are promising and demonstrate the efficacy of our model.

Unsupervised domain adaptation aims to address the problem of classifying unlabeled samples from the target domain whilst labeled samples are only available from the source domain and the data distributions are different in these two domains. As a result, classifiers trained from labeled samples in the source domain suffer from significant performance drop when directly applied to the samples from the target domain. To address this issue, different approaches have been proposed to learn domain-invariant features or domain-specific classifiers. In either case, the lack of labeled samples in the target domain can be an issue which is usually overcome by pseudo-labeling. Inaccurate pseudo-labeling, however, could result in catastrophic error accumulation during learning. In this paper, we propose a novel selective pseudo-labeling strategy based on structured prediction. The idea of structured prediction is inspired by the fact that samples in the target domain are well clustered within the deep feature space so that unsupervised clustering analysis can be used to facilitate accurate pseudo-labeling. Experimental results on four datasets (i.e. Office-Caltech, Office31, ImageCLEF-DA and Office-Home) validate our approach outperforms contemporary state-of-the-art methods.

Graph Neural Networks (GNN) have been shown to work effectively for modeling graph structured data to solve tasks such as node classification, link prediction and graph classification. There has been some recent progress in defining the notion of pooling in graphs whereby the model tries to generate a graph level representation by downsampling and summarizing the information present in the nodes. Existing pooling methods either fail to effectively capture the graph substructure or do not easily scale to large graphs. In this work, we propose ASAP (Adaptive Structure Aware Pooling), a sparse and differentiable pooling method that addresses the limitations of previous graph pooling architectures. ASAP utilizes a novel self-attention network along with a modified GNN formulation to capture the importance of each node in a given graph. It also learns a sparse soft cluster assignment for nodes at each layer to effectively pool the subgraphs to form the pooled graph. Through extensive experiments on multiple datasets and theoretical analysis, we motivate our choice of the components used in ASAP. Our experimental results show that combining existing GNN architectures with ASAP leads to state-of-the-art results on multiple graph classification benchmarks. ASAP has an average improvement of 4\%, compared to current sparse hierarchical state-of-the-art method.

For any c R d, and r 0, let B d(c, r) denote a d -dimensional null 2 ball of radius r centered at c . Let e i R d denote the i -th standard basis vector which has 1 in the i -th position and 0 everywhere else. Also, let 1 d and 0 d denote the all 1's vector and all 0's vector in R d respectively. By [n ] we denote the set { 1, 2,..., n } . For a discrete set of points C R d, let conv (C) denote the convex hull of points in C, i.e.,, conv(C): null null c C a cc a c 0, null c C a c 1 null . Suppose w R d be the parameters of a function to be learned (such as weights of a neural network). In each step of the SGD algorithm, the parameters are updated as w w η ˆ д, where η is a possibly time-varying learning rate and ˆ д is a stochastic unbiased estimate of д, the true gradient of some loss function with respect to w .