Black-box machine learning models are used in critical decision-making domains, giving rise to several calls for more algorithmic transparency. The drawback is that model explanations can leak information about the training data and the explanation data used to generate them, thus undermining data privacy. To address this issue, we propose differentially private algorithms to construct feature-based model explanations. We design an adaptive differentially private gradient descent algorithm, that finds the minimal privacy budget required to produce accurate explanations. It reduces the overall privacy loss on explanation data, by adaptively reusing past differentially private explanations. It also amplifies the privacy guarantees with respect to the training data. We evaluate the implications of differentially private models and our privacy mechanisms on the quality of model explanations.

Q-learning [Watkins and Dayan, 1992] is one of the most popular classes of methods for solving reinforcement learning (RL) problems. Q-learning tries to estimate the optimal state-action value function (Q-function). With a Q-function, at every state, one can greedily choose the action with the largest Q value to interact with the RL environment while achieving near optimal expected cumulative rewards in the long run. Compared to another popular classes of methods, e.g., modelbased RL, Q-learning algorithms (or more generally, model-free algorithms) often enjoy better memory and time efficiency

Many real-world vehicle routing problems involve rich sets of constraints with respect to the capacities of the vehicles, time windows for customers etc. While in recent years first machine learning models have been developed to solve basic vehicle routing problems faster than optimization heuristics, complex constraints rarely are taken into consideration. Due to their general procedure to construct solutions sequentially route by route, these methods generalize unfavorably to such problems. In this paper, we develop a policy model that is able to start and extend multiple routes concurrently by using attention on the joint action space of several tours. In that way the model is able to select routes and customers and thus learns to make difficult trade-offs between routes. In comprehensive experiments on three variants of the vehicle routing problem with time windows we show that our model called JAMPR works well for different problem sizes and outperforms the existing state-of-the-art constructive model. For two of the three variants it also creates significantly better solutions than a comparable meta-heuristic solver.

Hessian based measures of flatness, such as the trace, Frobenius and spectral norms, have been argued, used and shown to relate to generalisation. In this paper we demonstrate that for feed forward neural networks under the cross entropy loss, we would expect low loss solutions with large weights to have small Hessian based measures of flatness. This implies that solutions obtained using $L2$ regularisation should in principle be sharper than those without, despite generalising better. We show this to be true for logistic regression, multi-layer perceptrons, simple convolutional, pre-activated and wide residual networks on the MNIST and CIFAR-$100$ datasets. Furthermore, we show that for adaptive optimisation algorithms using iterate averaging, on the VGG-$16$ network and CIFAR-$100$ dataset, achieve superior generalisation to SGD but are $30 \times$ sharper. This theoretical finding, along with experimental results, raises serious questions about the validity of Hessian based sharpness measures in the discussion of generalisation. We further show that the Hessian rank can be bounded by the a constant times number of neurons multiplied by the number of classes, which in practice is often a small fraction of the network parameters. This explains the curious observation that many Hessian eigenvalues are either zero or very near zero which has been reported in the literature.

Compared to minimization problems, the min-max landscape in machine learning applications is considerably more convoluted because of the existence of cycles and similar phenomena. Such oscillatory behaviors are well-understood in the convex-concave regime, and many algorithms are known to overcome them. In this paper, we go beyond the convex-concave setting and we characterize the convergence properties of a wide class of zeroth-, first-, and (scalable) second-order methods in non-convex/non-concave problems. In particular, we show that these state-of-the-art min-max optimization algorithms may converge with arbitrarily high probability to attractors that are in no way min-max optimal or even stationary. Spurious convergence phenomena of this type can arise even in two-dimensional problems, a fact which corroborates the empirical evidence surrounding the formidable difficulty of training GANs.

A common approach, called transductive In this paper we develop a principled, probabilistic, semi-supervised learning (Zhu & Goldberg, 2009; Triguero unified approach to nonstandard classification et al., 2015), is to attempt to predict labels on the unlabelled tasks, such as semi-supervised, positiveunlabelled, dataset and then use the combined dataset to train final multi-positive-unlabelled and noisylabel models. One transductive method is self-training in which learning. We train a classifier on the given a model switches between training and relabelling its labels to predict the label-distribution.

Ensemble of models is well known to improve single model performance. We present a novel ensembling technique coined MAC that is designed to find the optimal function for combining models while remaining invariant to the number of sub-models involved in the combination. Being agnostic to the number of sub-models enables addition and replacement of sub-models to the combination even after deployment, unlike many of the current methods for ensembling such as stacking, boosting, mixture of experts and super learners that lock the models used for combination during training and therefore need retraining whenever a new model is introduced into the ensemble. We show that on the Kaggle RSNA Intracranial Hemorrhage Detection challenge, MAC outperforms classical average methods, demonstrates competitive results to boosting via XGBoost for a fixed number of sub-models, and outperforms it when adding sub-models to the combination without retraining.

This paper is concerned with functional learning by utilizing two-stage sampled distribution regression. We study a multi-penalty regularization algorithm for distribution regression under the framework of learning theory. The algorithm aims at regressing to real valued outputs from probability measures. The theoretical analysis on distribution regression is far from maturity and quite challenging, since only second stage samples are observable in practical setting. In the algorithm, to transform information from samples, we embed the distributions to a reproducing kernel Hilbert space $\mathcal{H}_K$ associated with Mercer kernel $K$ via mean embedding technique. The main contribution of the paper is to present a novel multi-penalty regularization algorithm to capture more features of distribution regression and derive optimal learning rates for the algorithm. The work also derives learning rates for distribution regression in the nonstandard setting $f_{\rho}\notin\mathcal{H}_K$, which is not explored in existing literature. Moreover, we propose a distribution regression-based distributed learning algorithm to face large-scale data or information challenge. The optimal learning rates are derived for the distributed learning algorithm. By providing new algorithms and showing their learning rates, we improve the existing work in different aspects in the literature.

Model noise is known to have detrimental effects on neural networks, such as training instability and predictive distributions with non-calibrated uncertainty properties. These factors set bottlenecks on the expressive potential of Neural Stochastic Differential Equations (NSDEs), a model family that employs neural nets on both drift and diffusion functions. We introduce a novel algorithm that solves a generic NSDE using only deterministic approximation methods. Given a discretization, we estimate the marginal distribution of the It\^{o} process implied by the NSDE using a recursive scheme to propagate deterministic approximations of the statistical moments across time steps. The proposed algorithm comes with theoretical guarantees on numerical stability and convergence to the true solution, enabling its computational use for robust, accurate, and efficient prediction of long sequences. We observe our novel algorithm to behave interpretably on synthetic setups and to improve the state of the art on two challenging real-world tasks.

Complex black-box machine learning models are regularly used in critical decision-making domains. This has given rise to several calls for algorithmic explainability. Many explanation algorithms proposed in literature assign importance to each feature individually. However, such explanations fail to capture the joint effects of sets of features. Indeed, few works so far formally analyze \coloremph{high dimensional model explanations}. In this paper, we propose a novel high dimension model explanation method that captures the joint effect of feature subsets. We propose a new axiomatization for a generalization of the Banzhaf index; our method can also be thought of as an approximation of a black-box model by a higher-order polynomial. In other words, this work justifies the use of the generalized Banzhaf index as a model explanation by showing that it uniquely satisfies a set of natural desiderata and that it is the optimal local approximation of a black-box model. Our empirical evaluation of our measure highlights how it manages to capture desirable behavior, whereas other measures that do not satisfy our axioms behave in an unpredictable manner.