We present a novel intrinsically motivated agent that learns how to control the environment in the fastest possible manner by optimizing learning progress. It learns what can be controlled, how to allocate time and attention, and the relations between objects using surprise based motivation. The effectiveness of our method is demonstrated in a synthetic as well as a robotic manipulation environment yielding considerably improved performance and smaller sample complexity. In a nutshell, our work combines several task-level planning agent structures (backtracking search on task graph, probabilistic road-maps, allocation of search efforts) with intrinsic motivation to achieve learning from scratch.

Neural networks are vulnerable to adversarial examples, i.e. inputs that are imperceptibly perturbed from natural data and yet incorrectly classified by the network. Adversarial training, a heuristic form of robust optimization that alternates between minimization and maximization steps, has proven to be among the most successful methods to train networks that are robust against a pre-defined family of perturbations. This paper provides a partial answer to the success of adversarial training. When the inner maximization problem can be solved to optimality, we prove that adversarial training finds a network of small robust train loss. When the maximization problem is solved by a heuristic algorithm, we prove that adversarial training finds a network of small robust surrogate train loss. The analysis technique leverages recent work on the analysis of neural networks via Neural Tangent Kernel (NTK), combined with online-learning when the maximization is solved by a heuristic, and the expressiveness of the NTK kernel in the $\ell_\infty$-norm.

Generative modeling is a rapidly advancing area of machine learning research finding applications in multiple fields such as, generated art, on-demand video, image denoising [1], exploration in reinforcement learning [2], collaborative filtering [3], inpainting [4] and many more. In general, three approaches have been used in generative modeling tasks. First, graphical models based on a probabilistic framework with latent variables such as variational auto-encoders [5] and Restricted Boltzmann Machines (RBMs) [6, 7]. Then, more recently proposed models based on adversarial training such as Generative Adversarial Networks (GANs) [8] and its many variants. Furthermore, autoregressive models such as Pixel Recurrent Neural Networks (PixelRNNs) [9] that models the conditional distribution of every individual pixel given previous pixels and generation involves sequentially predicting the pixels in an image along the two spatial dimensions.

Accelerating magnetic resonance imaging (MRI) has been an ongoing research topic since its invention in the 1970s. Among a variety of acceleration techniques, compressed sensing (CS) has become an important strategy during the past decades. Although CS-based methods can achieve high performance with many theoretical guarantees, it is challenging to determine the numerical uncertainties in the reconstruction model such as the optimal sparse transformations, sparse regularizer in the transform do-main, regularization parameters and the parameters of the optimization algorithm. Recently, deep learning has been introduced in MR reconstruction to address these issues and shown potential to significantly improve image quality.In this paper, we propose a general framework combining the CS-MR model with deep learning to maximize the potential of deep learning and model-based reconstruction for fast MR imaging and attempt to provide a guideline on how to improve the image quality with deep learning based on the traditional reconstruction algorithms.

In this paper, we introduce two new directed graphical models from Gaussian data: the Gaussian graphical interaction model (GGIM) and the Gaussian graphical conditional expectation model (GGCEM). The development of these models comes from considering stationary Gaussian processes on graphs, and leveraging the equations between the resulting steady-state covariance matrix and the Laplacian matrix representing the interaction graph. Through the presentation of conceptually straightforward theory, we develop the new models and provide interpretations of the edges in each graphical model in terms of statistical measures. We show that when restricted to undirected graphs, the Laplacian matrix representing a GGIM is equivalent to the standard inverse covariance matrix that encodes conditional dependence relationships. We demonstrate that the problem of learning sparse GGIMs and GGCEMs for a given observation set can be framed as a LASSO problem. By comparison with the problem of inverse covariance estimation, we prove a bound on the difference between the covariance matrix corresponding to a sparse GGIM and the covariance matrix corresponding to the $l_1$-norm penalized maximum log-likelihood estimate. In all, the new models present a novel perspective on directed relationships between variables and significantly expand on the state of the art in Gaussian graphical modeling.

It has been shown that deep neural networks (DNNs) may be vulnerable to adversarial attacks, raising the concern on their robustness particularly for safety-critical applications. Recognizing the local nature and limitations of existing adversarial attacks, we present a new type of global adversarial attacks for assessing global DNN robustness. More specifically, we propose a novel concept of global adversarial example pairs in which each pair of two examples are close to each other but have different class labels predicted by the DNN. We further propose two families of global attack methods and show that our methods are able to generate diverse and intriguing adversarial example pairs at locations far from the training or testing data. Moreover, we demonstrate that DNNs hardened using the strong projected gradient descent (PGD) based (local) adversarial training are vulnerable to the proposed global adversarial example pairs, suggesting that global robustness must be considered while training robust deep learning networks.

This paper introduces PyRobot, an open-source robotics framework for research and benchmarking. PyRobot is a light-weight, high-level interface on top of ROS that provides a consistent set of hardware independent mid-level APIs to control different robots. PyRobot abstracts away details about low-level controllers and inter-process communication, and allows non-robotics researchers (ML, CV researchers) to focus on building high-level AI applications. PyRobot aims to provide a research ecosystem with convenient access to robotics datasets, algorithm implementations and models that can be used to quickly create a state-of-the-art baseline. We believe PyRobot, when paired up with low-cost robot platforms such as LoCoBot, will reduce the entry barrier into robotics, and democratize robotics. PyRobot is open-source, and can be accessed via https://pyrobot.org.

Deep generative models play an increasingly important role in machine learning and computer vision. However there are two fundamental issues hindering real-world applications of these techniques: the learning difficulty of variational inference in Variational AutoEncoder (VAE) and the functional absence of encoding samples in Generative Adversarial Network (GAN). In this paper, we manage to address these issues in one framework by proposing a novel algorithm named Latently Invertible Autoencoder (LIA). A deep invertible network and its inverse mapping are symmetrically embedded in the latent space of VAE. Thus the partial encoder first transforms inputs to be feature vectors and then the distribution of these feature vectors is reshaped to approach a prior by the invertible network. The decoder proceeds in reverse order of composite mappings of the complete encoder. The two-stage stochasticity-free training is devised to train LIA via adversarial learning, in the sense that we first train a standard GAN whose generator is the decoder of LIA and then an autoencoder in the adversarial manner by detaching the invertible network from LIA. Experiments conducted on the FFHQ dataset validate the effectiveness of LIA for inference and generation tasks.

We propose behavior-driven optimization via Wasserstein distances (WDs) to improve several classes of state-of-the-art reinforcement learning (RL) algorithms. We show that WD regularizers acting on appropriate policy embeddings efficiently incorporate behavioral characteristics into policy optimization. We demonstrate that they improve Evolution Strategy methods by encouraging more efficient exploration, can be applied in imitation learning and to speed up training of Trust Region Policy Optimization methods. Since the exact computation of WDs is expensive, we develop approximate algorithms based on the combination of different methods: dual formulation of the optimal transport problem, alternating optimization and random feature maps, to effectively replace exact WD computations in the RL tasks considered. We provide theoretical analysis of our algorithms and exhaustive empirical evaluation in a variety of RL settings.

Two distinct limits for deep learning as the net width $h\to\infty$ have been proposed, depending on how the weights of the last layer scale with $h$. In the "lazy-learning" regime, the dynamics becomes linear in the weights and is described by a Neural Tangent Kernel $\Theta$. By contrast, in the "feature-learning" regime, the dynamics can be expressed in terms of the density distribution of the weights. Understanding which regime describes accurately practical architectures and which one leads to better performance remains a challenge. We answer these questions and produce new characterizations of these regimes for the MNIST data set, by considering deep nets $f$ whose last layer of weights scales as $\frac{\alpha}{\sqrt{h}}$ at initialization, where $\alpha$ is a parameter we vary. We performed systematic experiments on two setups (A) fully-connected Softplus momentum full batch and (B) convolutional ReLU momentum stochastic. We find that (1) $\alpha^*=\frac{1}{\sqrt{h}}$ separates the two regimes. (2) for (A) and (B) feature learning outperforms lazy learning, a difference in performance that decreases with $h$ and becomes hardly detectable asymptotically for (A) but is very significant for (B). (3) In both regimes, the fluctuations $\delta f$ induced by initial conditions on the learned function follow $\delta f\sim1/\sqrt{h}$, leading to a performance that increases with $h$. This improvement can be instead obtained at intermediate $h$ values by ensemble averaging different networks. (4) In the feature regime there exists a time scale $t_1\sim\alpha\sqrt{h}$, such that for $t\ll t_1$ the dynamics is linear. At $t\sim t_1$, the output has grown by a magnitude $\sqrt{h}$ and the changes of the tangent kernel $\|\Delta\Theta\|$ become significant. Ultimately, it follows $\|\Delta\Theta\|\sim(\sqrt{h}\alpha)^{-a}$ for ReLU and Softplus activation, with $a<2$ & $a\to2$ when depth grows.