Observations of traffic participants and their environment enable humans to drive road vehicles safely. However, when being driven, there is a notable difference between having a non-experienced vs. an experienced driver. One may get the feeling, that the latter one anticipates what may happen in the next few moments and considers these foresights in his driving behavior. To make the driving style of automated vehicles comparable to a human driver in the sense of comfort and perceived safety, the aforementioned anticipation skills need to become a built-in feature of self-driving vehicles. This article provides a systematic comparison of methods and strategies to generate this intention for self-driving cars using machine learning techniques. To implement and test these algorithms we use a large data set collected over more than 30000 km of highway driving and containing approximately 40000 real world driving situations. Moreover, we show that it is possible to certainly detect more than 47 % of all lane changes on German highways 3 or more seconds in advance with a false positive rate of less than 1 %. This enables us to predict the lateral position with a prediction horizon of 5 s with a median error of less than 0.21 m.

Clustering high-dimensional data, such as images or biological measurements, is a long-standing problem and has been studied extensively. Recently, Deep Clustering gained popularity due to the non-linearity of neural networks, which allows for flexibility in fitting the specific peculiarities of complex data. Here we introduce the Mixture-of-Experts Similarity Variational Autoencoder (MoE-Sim-VAE), a novel generative clustering model. The model can learn multi-modal distributions of high-dimensional data and use these to generate realistic data with high efficacy and efficiency. MoE-Sim-VAE is based on a Variational Autoencoder (VAE), where the decoder consists of a Mixture-of-Experts (MoE) architecture. This specific architecture allows for various modes of the data to be automatically learned by means of the experts. Additionally, we encourage the latent representation of our model to follow a Gaussian mixture distribution and to accurately represent the similarities between the data points. We assess the performance of our model on synthetic data, the MNIST benchmark data set, and a challenging real-world task of defining cell subpopulations from mass cytometry (CyTOF) measurements on hundreds of different datasets. MoE-Sim-VAE exhibits superior clustering performance on all these tasks in comparison to the baselines and we show that the MoE architecture in the decoder reduces the computational cost of sampling specific data modes with high fidelity.

Energy-Based Models (EBMs) outputs unmormalized log-probability values given data samples. Such an estimation is essential in a variety of applications such as sample generation, denoising, sample restoration, outlier detection, Bayesian reasoning, and many more. However, standard maximum likelihood training is computationally expensive due to the requirement of sampling the model distribution. Score matching potentially alleviates this problem, and denoising score matching is a particularly convenient version. However, previous works do not produce models capable of high quality sample synthesis in high dimensional datasets from random initialization. We believe that is because the score is only matched over a single noise scale, which corresponds to a small set in high-dimensional space. To overcome this limitation, here we instead learn an energy function using denoising score matching over all noise scales. When sampled from random initialization using Annealed Langevin Dynamics and single-step denoising jump, our model produced high-quality samples comparable to state-of-the-art techniques such as GANs. The learned model also provide density information and set a new sample quality baseline in energy-based models. We further demonstrate that the proposed method generalizes well with an image inpainting task.

In this brief, we improve the Broad Learning System (BLS) [7] by reducing the computational complexity of the incremental learning for added inputs. We utilize the inverse of a sum of matrices in [8] to improve a step in the pseudoinverse of a row-partitioned matrix. Accordingly we propose two fast algorithms for the cases of q > k and q < k, respectively, where q and k denote the number of additional training samples and the total number of nodes, respectively. Specifically, when q > k, the proposed algorithm computes only a k * k matrix inverse, instead of a q * q matrix inverse in the existing algorithm. Accordingly it can reduce the complexity dramatically. Our simulations, which follow those for Table V in [7], show that the proposed algorithm and the existing algorithm achieve the same testing accuracy, while the speedups in BLS training time of the proposed algorithm over the existing algorithm are 1.24 - 1.30.

Transfer and adaptation to new unknown environmental dynamics is a key challenge for reinforcement learning (RL). An even greater challenge is performing near-optimally in a single attempt at test time, possibly without access to dense rewards, which is not addressed by current methods that require multiple experience rollouts for adaptation. To achieve single episode transfer in a family of environments with related dynamics, we propose a general algorithm that optimizes a probe and an inference model to rapidly estimate underlying latent variables of test dynamics, which are then immediately used as input to a universal control policy. This modular approach enables integration of state-of-the-art algorithms for variational inference or RL. Moreover, our approach does not require access to rewards at test time, allowing it to perform in settings where existing adaptive approaches cannot. In diverse experimental domains with a single episode test constraint, our method significantly outperforms existing adaptive approaches and shows favorable performance against baselines for robust transfer.

Large-scale machine learning training suffers from two prior challenges, specifically for nuclear-norm constrained problems with distributed systems: the synchronization slowdown due to the straggling workers, and high communication costs. In this work, we propose an asynchronous Stochastic Frank Wolfe (SFW-asyn) method, which, for the first time, solves the two problems simultaneously, while successfully maintaining the same convergence rate as the vanilla SFW. We implement our algorithm in python (with MPI) to run on Amazon EC2, and demonstrate that SFW-asyn yields speed-ups almost linear to the number of machines compared to the vanilla SFW.

Deep Neural Networks (DNNs) are widely applied in a wide range of usecases. There is an increased demand for deploying DNNs on devices that do not have abundant resources such as memory and computation units. Recently, network compression through a variety of techniques such as pruning and quantization have been proposed to reduce the resource requirement. A key parameter that all existing compression techniques are sensitive to is the compression ratio (e.g., pruning sparsity, quantization bitwidth) of each layer. Traditional solutions treat the compression ratios of each layer as hyper-parameters, and tune them using human heuristic. Recent researchers start using black-box hyper-parameter optimizations, but they will introduce new hyper-parameters and have efficiency issue. In this paper, we propose a framework to jointly prune and quantize the DNNs automatically according to a target model size without using any hyper-parameters to manually set the compression ratio for each layer. In the experiments, we show that our framework can compress the weights data of ResNet-50 to be 836x smaller without accuracy loss on CIFAR-10, and compress AlexNet to be 205x smaller without accuracy loss on ImageNet classification.

This scenario is dir ectly analogous to longitudinal causal inference problems with multiple time-varying treatments that conta in time-varying confounders, variables that serve as confounders for some treatments and as mediators for othe r treatments. If there is an unmeasured con-founder for the R -Y relationship (represented by V and the dashed arrows in Figure 1 (a)), then conditioning on R fails to identify the direct effects of A on Y, because it opens a confounding pathway through V . See Hernan and Robins (2020) for an overview of these issues. The answer to the question posed in Appendix B of WB, "Can the c auses be causally dependent among themselves?" is therefore "no." If they are causally depend ent then the deconfounder, by dint of rendering the causes independent, breaks some of the structure among t he causes A, and as was originally established in the time-varying treatment setting, this undermines the identification of joint effects of A on Y by covariate adjustment. Analysis of Lemma 4. This simple argument also serves as a counterexample to Lemm a 4, which states that the deconfounder does not pick up any post-treatment va riables and can be treated as a pre-treatment covariate. This is necessarily false whenever the causes ar e causally dependent among themselves, but it need not hold even if the causes are not causally dependent, s ee below. The proof of Lemma 4 in Appendix I states that "Inferring the s ubstitute confounder Z

Among the six challenges of neural machine translation (NMT) coined by ( Koehn and Knowles, 2017), rare-word problem is considered the most severe one, especially in translation of low-resource languages. In this paper, we propose three solutions to address the rare words in neural machine translation systems. First, we enhance source context to predict the target words by connecting directly the source embeddings to the output of the attention component in NMT. Second, we propose an algorithm to learn morphology of unknown words for English in supervised way in order to minimize the adverse effect of rare-word problem. Finally, we exploit synonymous relation from the W ordNet to overcome out-of-vocabulary (OOV) problem of NMT. W e evaluate our approaches on two low-resource language pairs: English-Vietnamese and Japanese-Vietnamese. In our experiments, we have achieved significant improvements of up to roughly 1.0 BLEU points in both language pairs.

Within the context of empirical risk minimization, see Raginsky, Rakhlin, and Telgarsky (2017), we are concerned with a non-asymptotic analysis of sampling algorithms used in optimization. In particular, we obtain non-asymptotic error bounds for a popular class of algorithms called Stochastic Gradient Langevin Dynamics (SGLD). These results are derived in appropriate Wasserstein distances in the absence of the log-concavity of the target distribution. More precisely, the local Lipschitzness of the stochastic gradient $H(\theta, x)$ is assumed, and furthermore, the dissipativity and convexity at infinity condition are relaxed by removing the uniform dependence in $x$.