Intelligent agents should be able to learn useful representations by observing changes in their environment. We model such observations as pairs of non-i.i.d. images sharing at least one of the underlying factors of variation. First, we theoretically show that only knowing how many factors have changed, but not which ones, is sufficient to learn disentangled representations. Second, we provide practical algorithms that learn disentangled representations from pairs of images without requiring annotation of groups, individual factors, or the number of factors that have changed. Third, we perform a large-scale empirical study and show that such pairs of observations are sufficient to reliably learn disentangled representations on several benchmark data sets. Finally, we evaluate our learned representations and find that they are simultaneously useful on a diverse suite of tasks, including generalization under covariate shifts, fairness, and abstract reasoning. Overall, our results demonstrate that weak supervision enables learning of useful disentangled representations in realistic scenarios.

As neural networks are increasingly employed in machine learning practice, organizations will have to determine how to share limited training resources among a diverse set of model training tasks. This paper studies jointly training multiple neural network models on a single GPU. We presents an empirical study of this operation, called pack, and end-to-end experiments that suggest significant improvements for hyperparameter search systems. Our research prototype is in TensorFlow, and we evaluate performance across different models (ResNet, MobileNet, DenseNet, and MLP) and training scenarios. The results suggest: (1) packing two models can bring up to 40% performance improvement over unpacked setups for a single training step and the improvement increases when packing more models; (2) the benefit of a pack primitive largely depends on a number of factors including memory capacity, chip architecture, neural network structure, and batch size; (3) there exists a trade-off between packing and unpacking when training multiple neural network models on limited resources; (4) a pack-based Hyperband is up to 2.7x faster than the original Hyperband training method in our experiment setting, with this improvement growing as memory size increases and subsequently the density of models packed.

Programming-by-example (PBE) is a synthesis paradigm that allows users to generate functions by simply providing input-output examples. While a promising interaction paradigm, synthesis is still too slow for realtime interaction and more widespread adoption. Existing approaches to PBE synthesis have used automated reasoning tools, such as SMT solvers, as well as works applying machine learning techniques. At its core, the automated reasoning approach relies on highly domain specific knowledge of programming languages. On the other hand, the machine learning approaches utilize the fact that when working with program code, it is possible to generate arbitrarily large training datasets. In this work, we propose a system for using machine learning in tandem with automated reasoning techniques to solve Syntax Guided Synthesis (SyGuS) style PBE problems. By preprocessing SyGuS PBE problems with a neural network, we can use a data driven approach to reduce the size of the search space, then allow automated reasoning-based solvers to more quickly find a solution analytically. Our system is able to run atop existing SyGuS PBE synthesis tools, decreasing the runtime of the winner of the 2019 SyGuS Competition for the PBE Strings track by 47.65% to outperform all of the competing tools.

An average adult is exposed to hundreds of digital advertisements daily (https://www.mediadynamicsinc.com/uploads/files/PR092214-Note-only-150-Ads-2mk.pdf), making the digital advertisement industry a classic example of a big-data-driven platform. As such, the ad-tech industry relies on historical engagement logs (clicks or purchases) to identify potentially interested users for the advertisement campaign of a partner (a seller who wants to target users for its products). The number of advertisements that are shown for a partner, and hence the historical campaign data available for a partner depends upon the budget constraints of the partner. Thus, enough data can be collected for the high-budget partners to make accurate predictions, while this is not the case with the low-budget partners. This skewed distribution of the data leads to "preferential attachment" of the targeted display advertising platforms towards the high-budget partners. In this paper, we develop "domain-adaptation" approaches to address the challenge of predicting interested users for the partners with insufficient data, i.e., the tail partners. Specifically, we develop simple yet effective approaches that leverage the similarity among the partners to transfer information from the partners with sufficient data to cold-start partners, i.e., partners without any campaign data. Our approaches readily adapt to the new campaign data by incremental fine-tuning, and hence work at varying points of a campaign, and not just the cold-start. We present an experimental analysis on the historical logs of a major display advertising platform (https://www.criteo.com/). Specifically, we evaluate our approaches across 149 partners, at varying points of their campaigns. Experimental results show that the proposed approaches outperform the other "domain-adaptation" approaches at different time points of the campaigns.

Recently, several studies proposed methods to utilize some restricted classes of optimization problems as layers of deep neural networks. However, these methods are still in their infancy and require special treatments, i.e., analyzing the KKT condition, etc., for deriving the backpropagation formula. Instead, in this paper, we propose a method to utilize fixed-point iteration (FPI), a generalization of many types of numerical algorithms, as a network layer. We show that the derivative of an FPI layer depends only on the fixed point, and then we present a method to calculate it efficiently using another FPI which we call the backward FPI. The proposed method can be easily implemented based on the autograd functionalities in existing deep learning tools. Since FPI covers vast different types of numerical algorithms in machine learning and other fields, it has a lot of potential applications. In the experiments, the differentiable FPI layer is applied to two scenarios, i.e., gradient descent iterations for differentiable optimization problems and FPI with arbitrary neural network modules, of which the results demonstrate the simplicity and the effectiveness.

Recent research has shown that learning poli-cies parametrized by large neural networks can achieve significant success on challenging reinforcement learning problems. However, when memory is limited, it is not always possible to store such models exactly for inference, and com-pressing the policy into a compact representation might be necessary. We propose a general framework for policy representation, which reduces this problem to finding a low-dimensional embedding of a given density function in a separable inner product space. Our framework allows us to de-rive strong theoretical guarantees, controlling the error of the reconstructed policies. Such guaran-tees are typically lacking in black-box models, but are very desirable in risk-sensitive tasks. Our experimental results suggest that the reconstructed policies can use less than 10%of the number of parameters in the original networks, while incurring almost no decrease in rewards.

Kernel-based clustering algorithm can identify and capture the non-linear structure in datasets, and thereby it can achieve better performance than linear clustering. However, computing and storing the entire kernel matrix occupy so large memory that it is difficult for kernel-based clustering to deal with large-scale datasets. In this paper, we employ incomplete Cholesky factorization to accelerate kernel clustering and save memory space. The key idea of the proposed kernel $k$-means clustering using incomplete Cholesky factorization is that we approximate the entire kernel matrix by the product of a low-rank matrix and its transposition. Then linear $k$-means clustering is applied to columns of the transpose of the low-rank matrix. We show both analytically and empirically that the performance of the proposed algorithm is similar to that of the kernel $k$-means clustering algorithm, but our method can deal with large-scale datasets.

Sparse random projection (RP) is a popular tool for dimensionality reduction that shows promising performance with low computational complexity. However, in the existing sparse RP matrices, the positions of non-zero entries are usually randomly selected. Although they adopt uniform sampling with replacement, due to large sampling variance, the number of non-zeros is uneven among rows of the projection matrix which is generated in one trial, and more data information may be lost after dimension reduction. To break this bottleneck, based on random sampling without replacement in statistics, this paper builds a stable sparse subspace embedded matrix (S-SSE), in which non-zeros are uniformly distributed. It is proved that the S-SSE is stabler than the existing matrix, and it can maintain Euclidean distance between points well after dimension reduction. Our empirical studies corroborate our theoretical findings and demonstrate that our approach can indeed achieve satisfactory performance.

In this paper, we consider the problem of assessing the adversarial robustness of deep neural network models under both Markov chain Monte Carlo (MCMC) and Bayesian Dark Knowledge (BDK) inference approximations. We characterize the robustness of each method to two types of adversarial attacks: the fast gradient sign method (FGSM) and projected gradient descent (PGD). We show that full MCMC-based inference has excellent robustness, significantly outperforming standard point estimation-based learning. On the other hand, BDK provides marginal improvements. As an additional contribution, we present a storage-efficient approach to computing adversarial examples for large Monte Carlo ensembles using both the FGSM and PGD attacks.

We consider the problem of robust optimization within the well-established Bayesian optimization (BO) framework. While BO is intrinsically robust to noisy evaluations of the objective function, standard approaches do not consider the case of uncertainty about the input parameters. In this paper, we propose Noisy-Input Entropy Search (NES), a novel information-theoretic acquisition function that is designed to find robust optima for problems with both input and measurement noise. NES is based on the key insight that the robust objective in many cases can be modeled as a Gaussian process, however, it cannot be observed directly. We evaluate NES on several benchmark problems from the optimization literature and from engineering. The results show that NES reliably finds robust optima, outperforming existing methods from the literature on all benchmarks.