Traffic congestion in metropolitan areas is a world-wide problem that can be ameliorated by traffic lights that respond dynamically to real-time conditions. Recent studies applying deep reinforcement learning (RL) to optimize single traffic lights have shown significant improvement over conventional control. However, optimization of global traffic condition over a large road network fundamentally is a cooperative multi-agent control problem, for which single-agent RL is not suitable due to environment non-stationarity and infeasibility of optimizing over an exponential joint-action space. Motivated by these challenges, we propose QCOMBO, a simple yet effective multi-agent reinforcement learning (MARL) algorithm that combines the advantages of independent and centralized learning. We ensure scalability by selecting actions from individually optimized utility functions, which are shaped to maximize global performance via a novel consistency regularization loss between individual utility and a global action-value function. Experiments on diverse road topologies and traffic flow conditions in the SUMO traffic simulator show competitive performance of QCOMBO versus recent state-of-the-art MARL algorithms. We further show that policies trained on small sub-networks can effectively generalize to larger networks under different traffic flow conditions, providing empirical evidence for the suitability of MARL for intelligent traffic control.

In the last decade, improvements in genomic, transcrip-tomic, and proteomic technologies have enabled personalized medicine (also called precision medicine) to become an essential part of contemporary medicine. Personalized medicine takes into account individual variability in genes, proteins, environment, and lifestyle to decide on optimal disease treatment and prevention [14]. The use of a patient's genetic and epigenetic information has already proven to be highly effective to tailor drug therapies or preventive care in a number of applications, such as breast [7], prostate [23], ovarian [17], and pancreatic cancers [24], cardiovascular disease [11], cystic fibrosis [36], and psychiatry [10]. The subfield of pharmacogenomics studies specifically how genes affect a person's response to particular drugs to develop more efficient and safer medications [37]. Genomic, epigenomic, and transcriptomic data used in precision medicine, such as gene expression, copy number variants, or methylation levels are typically high-dimensional with a number of variables that rivals or exceeds the number of observations.

An important linear algebra routine, GEneral Matrix Multiplication (GEMM), is a fundamental operator in deep learning. Compilers need to translate these routines into low-level code optimized for specific hardware. Compiler-level optimization of GEMM has significant performance impact on training and executing deep learning models. However, most deep learning frameworks rely on hardware-specific operator libraries in which GEMM optimization has been mostly achieved by manual tuning, which restricts the performance on different target hardware. In this paper, we propose two novel algorithms for GEMM optimization based on the TVM framework, a lightweight Greedy Best First Search (G-BFS) method based on heuristic search, and a Neighborhood Actor Advantage Critic (N-A2C) method based on reinforcement learning. Experimental results show significant performance improvement of the proposed methods, in both the optimality of the solution and the cost of search in terms of time and fraction of the search space explored. Specifically, the proposed methods achieve 24% and 40% savings in GEMM computation time over state-of-the-art XGBoost and RNN methods, respectively, while exploring only 0.1% of the search space. The proposed approaches have potential to be applied to other operator-level optimizations.

Gradient-based methods for optimisation of objectives in stochastic settings with unknown or intractable dynamics require estimators of derivatives. We derive an objective that, under automatic differentiation, produces low-variance unbiased estimators of derivatives at any order. Our objective is compatible with arbitrary advantage estimators, which allows the control of the bias and variance of any-order derivatives when using function approximation. Furthermore, we propose a method to trade off bias and variance of higher order derivatives by discounting the impact of more distant causal dependencies. We demonstrate the correctness and utility of our objective in analytically tractable MDPs and in meta-reinforcement-learning for continuous control.

We study the impact of the constraint set and gradient geometry on the convergence of online and stochastic methods for convex optimization, providing a characterization of the geometries for which stochastic gradient and adaptive gradient methods are (minimax) optimal. In particular, we show that when the constraint set is quadratically convex, diagonally pre-conditioned stochastic gradient methods are minimax optimal. We further provide a converse that shows that when the constraints are not quadratically convex---for example, any $\ell_p$-ball for $p < 2$---the methods are far from optimal. Based on this, we can provide concrete recommendations for when one should use adaptive, mirror or stochastic gradient methods.

In this paper, we focus on quantifying model stability as a function of random seed by investigating the effects of the induced randomness on model performance and the robustness of the model in general. We specifically perform a controlled study on the effect of random seeds on the behaviour of attention, gradient-based and surrogate model based (LIME) interpretations. Our analysis suggests that random seeds can adversely affect the consistency of models resulting in counterfactual interpretations. We propose a technique called Aggressive Stochastic Weight Averaging (ASWA)and an extension called Norm-filtered Aggressive Stochastic Weight Averaging (NASWA) which improves the stability of models over random seeds. With our ASWA and NASWA based optimization, we are able to improve the robustness of the original model, on average reducing the standard deviation of the model's performance by 72%.

For commonly used kernels such as Gaussian, the gradient computations mainly consist of matrix products and linear system solutions, thus they can be sped up significantly with GPU-accelerated linear system solvers. For instance, our imple - mentation took less than 80 miliseconds to compute DI/KDI gradients on an nVidia P100 GPU with feature dimensionalities up to 2000 and batch sizes up to 4000 using Gaussian kernels on the 3 datasets considered. In common learning methodologies, where a linear predictor is trained in conjunction with a parametric non-line ar mapping, the overall objective is to minimize a loss functio n averaged over the entire training sample, i.e., to minimize the expected loss over a single empirical distribution. Since D I directly measures the loss of the best linear predictor on a batch, however, stochastic gradient methods have a differe nt interpretation when utilizing this objective. Since each m ini-batch represents a different empirical distribution, DI ba sed training instead aims to find a feature mapping that adapts to various empirical distributions, which can reduce overfitt ing analogous to how bagging can improve generalization [ 27 ].

The majority of ML research concerns slow, statistical learning of i.i.d. samples from large, labelled datasets. Animals do not learn this way. An enviable characteristic of animal learning is 'episodic' learning - the ability to rapidly memorize a specific experience as a composition of existing concepts, without provided labels. The new knowledge can then be used to distinguish between similar experiences, to generalize between classes, and to selectively consolidate to long-term memory. The Hippocampus is known to be vital to these abilities. AHA is a biologically-plausible computational model of the Hippocampus. Unlike most machine learning models, AHA is trained without any external labels and uses only local and immediate credit assignment. We demonstrate AHA in a superset of the Omniglot classification benchmark. The extended benchmark covers a wider range of known Hippocampal functions by testing pattern separation, completion, and reconstruction of original input. These functions are all performed within a single configuration of the computational model. Despite these constraints, results are comparable to state-of-the-art deep convolutional ANNs. In addition to the demonstrated high degree of functional overlap with the Hippocampal region, AHA is remarkably aligned to current macro-scale biological models and uses biologically plausible micro-scale learning rules.

The Graph Convolutional Networks (GCN) has demonstrated superior performance in representing graph data, especially homogeneous graphs. However, the real-world graph data is usually heterogeneous and evolves with time, e.g., Facebook and DBLP, which has seldom been studied. To cope with this issue, we propose a novel approach named temporal heterogeneous graph convolutional network (THGCN). THGCN first embeds both spatial information and node attribute information together. Then, it captures short-term evolutionary patterns from the aggregations of embedded graph signals through compression network. Meanwhile, the long-term evolutionary patterns of heterogeneous graph data are also modeled via a TCN temporal convolutional network. To the best of our knowledge, this is the first attempt to model temporal heterogeneous graph data with a focus on community discovery task.

For dynamical systems that can be modelled as asymptotically stable linear systems forced by Gaussian noise, this paper develops methods to infer their modes from observations in real time. The modes can be real or complex. For a real mode, we infer its damping rate, mode shape and amplitude. For a complex mode, we infer its frequency, damping rate, (complex) mode shape and (complex) amplitude. The work is motivated and illustrated by the problem of detection of oscillations in power flow in AC electrical networks. Suggestions of other applications are given.