Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model and to the opposite "black box" setting. Black box attacks are particularly threatening as the adversary only needs access to the input and output of the model. Defending against black box adversarial example generation attacks is paramount as currently proposed defenses are not effective. Since these types of attacks rely on repeated queries to the model to estimate gradients over input dimensions, we investigate the use of randomization to thwart such adversaries from successfully creating adversarial examples. Randomization applied to the output of the deep neural network model has the potential to confuse potential attackers, however this introduces a tradeoff between accuracy and robustness. We show that for certain types of randomization, we can bound the probability of introducing errors by carefully setting distributional parameters. For the particular case of finite difference black box attacks, we quantify the error introduced by the defense in the finite difference estimate of the gradient. Lastly, we show empirically that the defense can thwart two adaptive black box adversarial attack algorithms.

Toward this goal, we propose a new class of challenges, and a class of architectures that can solve them. The challenges are meta-mappings, which involve systematically transforming task behaviors to adapt to new tasks zero-shot. We suggest that the key to achieving these challenges is representing the task being performed along with the computations used to perform it. We therefore draw inspiration from meta-learning and functional programming to propose a class of Embedded Meta-Learning (EML) architectures that represent both data and tasks in a shared latent space. EML architectures are applicable to any type of machine learning task, including supervised learning and reinforcement learning. We demonstrate the flexibility of these architectures by showing that they can perform meta-mappings, i.e. that they can exhibit zero-shot remapping of behavior to adapt to new tasks.

This paper introduces a cross adversarial source separation (CASS) framework via autoencoder, a new model that aims at separating an input signal consisting of a mixture of multiple components into individual components defined via adversarial learning and autoencoder fitting. CASS unifies popular generative networks like auto-encoders (AEs) and generative adversarial networks (GANs) in a single framework. The basic building block that filters the input signal and reconstructs the $i$-th target component is a pair of deep neural networks $\mathcal{EN}_i$ and $\mathcal{DE}_i$ as an encoder for dimension reduction and a decoder for component reconstruction, respectively. The decoder $\mathcal{DE}_i$ as a generator is enhanced by a discriminator network $\mathcal{D}_i$ that favors signal structures of the $i$-th component in the $i$-th given dataset as guidance through adversarial learning. In contrast with existing practices in AEs which trains each Auto-Encoder independently, or in GANs that share the same generator, we introduce cross adversarial training that emphasizes adversarial relation between any arbitrary network pairs $(\mathcal{DE}_i,\mathcal{D}_j)$, achieving state-of-the-art performance especially when target components share similar data structures.

Open access to high-quality education is limited by the difficulty of providing student feedback. In this paper, we present Generative Grading with Neural Approximate Parsing (GG-NAP): a novel approach for providing feedback at scale that is capable of both accurately grading student work while also providing verifiability--a property where the model is able to substantiate its claims with a provable certificate. Our approach uses generative descriptions of student cognition, written as probabilistic programs, to synthesise millions of labelled example solutions to a problem; it then trains inference networks to approximately parse real student solutions according to these generative models. We achieve feedback prediction accuracy comparable to professional human experts in a variety of settings: short-answer questions, programs with graphical output, block-based programming, and short Java programs. In a real classroom, we ran an experiment where humans used GG-NAP to grade, yielding doubled grading accuracy while halving grading time.

We introduce NAMSG, an adaptive first-order algorithm for training neural networks. The method is efficient in computation and memory, and is straightforward to implement. It computes the gradients at configurable remote observation points, in order to expedite the convergence by adjusting the step size for directions with different curvatures in the stochastic setting. It also scales the updating vector elementwise by a nonincreasing preconditioner to take the advantages of AMSGRAD. We analyze the convergence properties for both convex and nonconvex problems by modeling the training process as a dynamic system, and provide a guideline to select the observation distance without grid search. A data-dependent regret bound is proposed to guarantee the convergence in the convex setting. Experiments demonstrate that NAMSG works well in practical problems and compares favorably to popular adaptive methods, such as ADAM, NADAM, and AMSGRAD.

In this work, we propose new objective functions to train deep neural network based density ratio estimators and apply it to a change point detection problem. Existing methods use linear combinations of kernels to approximate the density ratio function by solving a convex constrained minimization problem. Approximating the density ratio function using a deep neural network requires defining a suitable objective function to optimize. We formulate and compare objective functions that can be minimized using gradient descent and show that the network can effectively learn to approximate the density ratio function. Using our deep density ratio estimation objective function results in better performance on a seizure detection task than other (kernel and neural network based) density ratio estimation methods and other window-based change point detection algorithms. We also show that the method can still support other neural network architectures, such as convolutional networks.

Supervised learning from training data with imbalanced class sizes, a commonly encountered scenario in real applications such as anomaly/fraud detection, has long been considered a significant challenge in machine learning. Motivated by recent progress in curriculum and self-paced learning, we propose to adopt a semi-supervised learning paradigm by training a deep neural network, referred to as SelectNet, to selectively add unlabelled data together with their predicted labels to the training dataset. Unlike existing techniques designed to tackle the difficulty in dealing with class imbalanced training data such as resampling, cost-sensitive learning, and margin-based learning, SelectNet provides an end-to-end approach for learning from important unlabelled data "in the wild" that most likely belong to the under-sampled classes in the training data, thus gradually mitigates the imbalance in the data used for training the classifier. We demonstrate the efficacy of SelectNet through extensive numerical experiments on standard datasets in computer vision.

Attention is an operation that selects some largest element from some set, where the notion of largest is defined elsewhere. Applying this operation to sequence to sequence mapping results in significant improvements to the task at hand. In this paper we provide the mathematical definition of attention and examine its application to sequence to sequence models. We highlight the exact correspondences between machine learning implementations of attention and our mathematical definition. We provide clear evidence of effectiveness of attention mechanisms evaluating models with varying degrees of attention on a very simple task: copying a sentence. We find that models that make greater use of attention perform much better on sequence to sequence mapping tasks, converge faster and are more stable.

Despite recent successes in Reinforcement Learning, value-based methods often suffer from high variance hindering performance. In this paper, we illustrate this in a continuous control setting where state of the art methods perform poorly whenever sensor noise is introduced. To overcome this issue, we introduce Recurrent Value Functions (RVFs) as an alternative to estimate the value function of a state. We propose to estimate the value function of the current state using the value function of past states visited along the trajectory. Due to the nature of their formulation, RVFs have a natural way of learning an emphasis function that selectively emphasizes important states. First, we establish RVF's asymptotic convergence properties in tabular settings. We then demonstrate their robustness on a partially observable domain and continuous control tasks. Finally, we provide a qualitative interpretation of the learned emphasis function.

The performance of deep neural networks (DNN) is very sensitive to the particular choice of hyper-parameters. To make it worse, the shape of the learning curve can be significantly affected when a technique like batchnorm is used. As a result, hyperparameter optimization of deep networks can be much more challenging than traditional machine learning models. In this work, we start from well known Bayesian Optimization solutions and provide enhancement strategies specifically designed for hyperparameter optimization of deep networks. The resulting algorithm is named as DEEP-BO (Diversified, Early-termination-Enabled, and Parallel Bayesian Optimization). When evaluated over six DNN benchmarks, DEEP-BO easily outperforms or shows comparable performance with some of the well-known solutions including GP-Hedge, Hyperband, BOHB, Median Stopping Rule, and Learning Curve Extrapolation.