Alternating direction method of multipliers (ADMM) is a popular optimization tool for the composite and constrained problems in machine learning. However, in many machine learning problems such as black-box attacks and bandit feedback, ADMM could fail because the explicit gradients of these problems are difficult or infeasible to obtain. Zeroth-order (gradient-free) methods can effectively solve these problems due to that the objective function values are only required in the optimization. Recently, though there exist a few zeroth-order ADMM methods, they build on the convexity of objective function. Clearly, these existing zeroth-order methods are limited in many applications. In the paper, thus, we propose a class of fast zeroth-order stochastic ADMM methods (i.e., ZO-SVRG-ADMM and ZO-SAGA-ADMM) for solving nonconvex problems with multiple nonsmooth penalties, based on the coordinate smoothing gradient estimator. Moreover, we prove that both the ZO-SVRG-ADMM and ZO-SAGA-ADMM have convergence rate of $O(1/T)$, where $T$ denotes the number of iterations. In particular, our methods not only reach the best convergence rate $O(1/T)$ for the nonconvex optimization, but also are able to effectively solve many complex machine learning problems with multiple regularized penalties and constraints. Finally, we conduct the experiments of black-box binary classification and structured adversarial attack on black-box deep neural network to validate the efficiency of our algorithms.

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show the possibility of these tracing (membership inference) attacks against complex models with a large number of parameters. However, the attack results are dependent on the specific training data, can be obtained only after the tedious process of training the model and performing the attack, and are missing any measure of the confidence and unused potential power of the attack. A model designer is interested in identifying which model structures leak more information, how adding new parameters to the model increases its privacy risk, and what is the gain of adding new data points to decrease the overall information leakage. The privacy analysis should also enable designing the most powerful inference attack. In this paper, we design a theoretical framework to analyze the maximum power of tracing attacks against high-dimensional models, with the focus on probabilistic graphical models. We provide a tight upper-bound on the power (true positive rate) of these attacks, with respect to their error (false positive rate). The bound, as it should be, is independent of the knowledge and algorithm of any specific attack, as well as the values of particular samples in the training set. It provides a measure of the potential leakage of a model given its structure, as a function of the structure complexity and the size of training set.

Insects play such a crucial role in ecosystems that a shift in demography of just a few species can have devastating consequences at environmental, social and economic levels. Despite this, evaluation of insect demography is strongly limited by the difficulty of collecting census data at sufficient scale. We propose a method to gather and leverage observations from bystanders, hikers, and entomology enthusiasts in order to provide researchers with data that could significantly help anticipate and identify environmental threats. Finally, we show that there is indeed interest on both sides for such collaboration.

Evolution Strategies (ES) are a powerful class of blackbox optimization techniques that recently became a competitive alternative to state-of-the-art policy gradient (PG) algorithms for reinforcement learning (RL). We propose a new method for improving accuracy of the ES algorithms, that as opposed to recent approaches utilizing only Monte Carlo structure of the gradient estimator, takes advantage of the underlying MDP structure to reduce the variance. We observe that the gradient estimator of the ES objective can be alternatively computed using reparametrization and PG estimators, which leads to new control variate techniques for gradient estimation in ES optimization. We provide theoretical insights and show through extensive experiments that this RL-specific variance reduction approach outperforms general purpose variance reduction methods.

Latent-state environments with long horizons, such as those faced by recommender systems, pose significant challenges for reinforcement learning (RL). In this work, we identify and analyze several key hurdles for RL in such environments, including belief state error and small action advantage. We develop a general principle of advantage amplification that can overcome these hurdles through the use of temporal abstraction. We propose several aggregation methods and prove they induce amplification in certain settings. We also bound the loss in optimality incurred by our methods in environments where latent state evolves slowly and demonstrate their performance empirically in a stylized user-modeling task.

A major challenge in cognitive science and AI has been to understand how autonomous agents might acquire and predict behavioral and mental states of other agents in the course of complex social interactions. How does such an agent model the goals, beliefs, and actions of other agents it interacts with? What are the computational principles to model a Theory of Mind (ToM)? Deep learning approaches to address these questions fall short of a better understanding of the problem. In part, this is due to the black-box nature of deep networks, wherein computational mechanisms of ToM are not readily revealed. Here, we consider alternative hypotheses seeking to model how the brain might realize a ToM. In particular, we propose embodied and situated agent models based on distributed adaptive control theory to predict actions of other agents in five different game theoretic tasks (Harmony Game, Hawk-Dove, Stag-Hunt, Prisoner's Dilemma and Battle of the Exes). Our multi-layer control models implement top-down predictions from adaptive to reactive layers of control and bottom-up error feedback from reactive to adaptive layers. We test cooperative and competitive strategies among seven different agent models (cooperative, greedy, tit-for-tat, reinforcement-based, rational, predictive and other's-model agents). We show that, compared to pure reinforcement-based strategies, probabilistic learning agents modeled on rational, predictive and other's-model phenotypes perform better in game-theoretic metrics across tasks. Our autonomous multi-agent models capture systems-level processes underlying a ToM and highlight architectural principles of ToM from a control-theoretic perspective.

In this paper, we study the prediction of a real-valued target, such as a risk score or recidivism rate, while guaranteeing a quantitative notion of fairness with respect to a protected attribute such as gender or race. We call this class of problems \emph{fair regression}. We propose general schemes for fair regression under two notions of fairness: (1) statistical parity, which asks that the prediction be statistically independent of the protected attribute, and (2) bounded group loss, which asks that the prediction error restricted to any protected group remain below some pre-determined level. While we only study these two notions of fairness, our schemes are applicable to arbitrary Lipschitz-continuous losses, and so they encompass least-squares regression, logistic regression, quantile regression, and many other tasks. Our schemes only require access to standard risk minimization algorithms (such as standard classification or least-squares regression) while providing theoretical guarantees on the optimality and fairness of the obtained solutions. In addition to analyzing theoretical properties of our schemes, we empirically demonstrate their ability to uncover fairness--accuracy frontiers on several standard datasets.

We study the sample complexity of approximate policy iteration (PI) for the Linear Quadratic Regulator (LQR), building on a recent line of work using LQR as a testbed to understand the limits of reinforcement learning (RL) algorithms on continuous control tasks. Our analysis quantifies the tension between policy improvement and policy evaluation, and suggests that policy evaluation is the dominant factor in terms of sample complexity. Specifically, we show that to obtain a controller that is within $\varepsilon$ of the optimal LQR controller, each step of policy evaluation requires at most $(n+d)^3/\varepsilon^2$ samples, where $n$ is the dimension of the state vector and $d$ is the dimension of the input vector. On the other hand, only $\log(1/\varepsilon)$ policy improvement steps suffice, resulting in an overall sample complexity of $(n+d)^3 \varepsilon^{-2} \log(1/\varepsilon)$. We furthermore build on our analysis and construct a simple adaptive procedure based on $\varepsilon$-greedy exploration which relies on approximate PI as a sub-routine and obtains $T^{2/3}$ regret, improving upon a recent result of Abbasi-Yadkori et al.

We propose Gaussian optimal transport for Image style transfer in an Encoder/Decoder framework . Optimal transport for Gaussian measures has closed forms Monge mappings from source to target distributions. Moreover interpolates between a content and a style image can be seen as geodesics in the Wasserstein Geometry. Using this insight, we show how to mix different target styles, using Wasserstein barycenter of Gaussian measures. Since Gaussians are closed under Wasserstein barycenter, this allows us a simple style transfer and style mixing and interpolation. Moreover we show how mixing different styles can be achieved using other geodesic metrics between gaussians such as the Fisher Rao metric, while the transport of the content to the new interpolate style is still performed with Gaussian OT maps. Our simple methodology allows to generate new stylized content interpolating between many artistic styles. The metric used in the interpolation results in different stylizations.

Ensemble learning use multiple algorithms to obtain better predictive performance than any single one of its constituent algorithms could. With growing popularity of deep learning, researchers have started to ensemble them for various purposes. Few if any, however, has used the deep learning approach as a means to ensemble algorithms. This paper presents a deep ensemble learning framework which aims to harness deep learning algorithms to integrate multisource data and tap the wisdom of experts. At the voting layer, a sparse autoencoder is trained for feature learning to reduce the correlation of attributes and diversify the base classifiers ultimately. At the stacking layer, a nonlinear feature-weighted method based on deep belief networks is proposed to rank the base classifiers which may violate the conditional independence. Neural network is used as meta classifier. At the optimizing layer, under-sampling and threshold-moving are used to cope with cost-sensitive problem. Optimized predictions are obtained based on ensemble of probabilistic predictions by similarity calculation. The proposed deep ensemble learning framework is used for Alzheimers disease classification. Experiments with the clinical dataset from national Alzheimers coordinating center demonstrate that the classification accuracy of our proposed framework is 4% better than 6 well-known ensemble approaches as well as the standard stacking algorithm. Adequate coverage of more accurate diagnostic services can be provided by utilizing the wisdom of averaged physicians. This paper points out a new way to boost the primary care of Alzheimers disease from the view of machine learning.