亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

In deep learning, fine-grained N:M sparsity reduces the data footprint and bandwidth of a General Matrix multiply (GEMM) by x2, and doubles throughput by skipping computation of zero values. So far, it was only used to prune weights. We examine how this method can be used also for activations and their gradients (i.e., "neural gradients"). To this end, we first establish a tensor-level optimality criteria. Previous works aimed to minimize the mean-square-error (MSE) of each pruned block. We show that while minimization of the MSE works fine for pruning the activations, it catastrophically fails for the neural gradients. Instead, we show that optimal pruning of the neural gradients requires an unbiased minimum-variance pruning mask. We design such specialized masks, and find that in most cases, 1:2 sparsity is sufficient for training, and 2:4 sparsity is usually enough when this is not the case. Further, we suggest combining several such methods together in order to potentially speed up training even more. A reference implementation is supplied in //github.com/brianchmiel/Act-and-Grad-structured-sparsity.

The ability to accurately predict human behavior is central to the safety and efficiency of robot autonomy in interactive settings. Unfortunately, robots often lack access to key information on which these predictions may hinge, such as people's goals, attention, and willingness to cooperate. Dual control theory addresses this challenge by treating unknown parameters of a predictive model as stochastic hidden states and inferring their values at runtime using information gathered during system operation. While able to optimally and automatically trade off exploration and exploitation, dual control is computationally intractable for general interactive motion planning, mainly due to the fundamental coupling between robot trajectory optimization and human intent inference. In this paper, we present a novel algorithmic approach to enable active uncertainty reduction for interactive motion planning based on the implicit dual control paradigm. Our approach relies on sampling-based approximation of stochastic dynamic programming, leading to a model predictive control problem that can be readily solved by real-time gradient-based optimization methods. The resulting policy is shown to preserve the dual control effect for a broad class of predictive human models with both continuous and categorical uncertainty. The efficacy of our approach is demonstrated with simulated driving examples.

The utility of reinforcement learning is limited by the alignment of reward functions with the interests of human stakeholders. One promising method for alignment is to learn the reward function from human-generated preferences between pairs of trajectory segments. These human preferences are typically assumed to be informed solely by partial return, the sum of rewards along each segment. We find this assumption to be flawed and propose modeling preferences instead as arising from a different statistic: each segment's regret, a measure of a segment's deviation from optimal decision-making. Given infinitely many preferences generated according to regret, we prove that we can identify a reward function equivalent to the reward function that generated those preferences. We also prove that the previous partial return model lacks this identifiability property without preference noise that reveals rewards' relative proportions, and we empirically show that our proposed regret preference model outperforms it with finite training data in otherwise the same setting. Additionally, our proposed regret preference model better predicts real human preferences and also learns reward functions from these preferences that lead to policies that are better human-aligned. Overall, this work establishes that the choice of preference model is impactful, and our proposed regret preference model provides an improvement upon a core assumption of recent research.

The quintessential model-based reinforcement-learning agent iteratively refines its estimates or prior beliefs about the true underlying model of the environment. Recent empirical successes in model-based reinforcement learning with function approximation, however, eschew the true model in favor of a surrogate that, while ignoring various facets of the environment, still facilitates effective planning over behaviors. Recently formalized as the value equivalence principle, this algorithmic technique is perhaps unavoidable as real-world reinforcement learning demands consideration of a simple, computationally-bounded agent interacting with an overwhelmingly complex environment. In this work, we entertain an extreme scenario wherein some combination of immense environment complexity and limited agent capacity entirely precludes identifying an exactly value-equivalent model. In light of this, we embrace a notion of approximate value equivalence and introduce an algorithm for incrementally synthesizing simple and useful approximations of the environment from which an agent might still recover near-optimal behavior. Crucially, we recognize the information-theoretic nature of this lossy environment compression problem and use the appropriate tools of rate-distortion theory to make mathematically precise how value equivalence can lend tractability to otherwise intractable sequential decision-making problems.

From a model-building perspective, in this paper we propose a paradigm shift for fitting over-parameterized models. Philosophically, the mindset is to fit models to future observations rather than to the observed sample. Technically, choosing an imputation model for generating future observations, we fit over-parameterized models to future observations via optimizing an approximation to the desired expected loss-function based on its sample counterpart and an adaptive simplicity-preference function. This technique is discussed in detail to both creating bootstrap imputation and final estimation with bootstrap imputation. The method is illustrated with the many-normal-means problem, $n < p$ linear regression, and deep convolutional neural networks for image classification of MNIST digits. The numerical results demonstrate superior performance across these three different types of applications. For example, for the many-normal-means problem, our method uniformly dominates James-Stein and Efron's $g-$modeling, and for the MNIST image classification, it performs better than all existing methods and reaches arguably the best possible result. While this paper is largely expository because of the ambitious task of taking a look at over-parameterized models from the new perspective, fundamental theoretical properties are also investigated. We conclude the paper with a few remarks.

Bidirectional motion planning approaches decrease planning time, on average, compared to their unidirectional counterparts. In single-query feasible motion planning, using bidirectional search to find a continuous motion plan requires an edge connection between the forward and reverse search trees. Such a tree-tree connection requires solving a two-point Boundary Value Problem (BVP). However, a two-point BVP solution can be difficult or impossible to calculate for many systems. We present a novel bidirectional search strategy that does not require solving the two-point BVP. Instead of connecting the forward and reverse trees directly, the reverse tree's cost information is used as a guiding heuristic for the forward search. This enables the forward search to quickly converge to a feasible solution without solving the two-point BVP. We propose two new algorithms (GBRRT and GABRRT) that use this strategy and run multiple software simulations using multiple dynamical systems and real-world hardware experiments to show that our algorithms perform on-par or better than existing state-of-the-art methods in quickly finding an initial feasible solution.

We seek to provide an interpretable framework for segmenting users in a population for personalized decision-making. We propose a general methodology, Market Segmentation Trees (MSTs), for learning market segmentations explicitly driven by identifying differences in user response patterns. To demonstrate the versatility of our methodology, we design two new, specialized MST algorithms: (i) Choice Model Trees (CMTs), which can be used to predict a user's choice amongst multiple options and (ii) Isotonic Regression Trees (IRTs), which can be used to solve the bid landscape forecasting problem. We provide a theoretical analysis of the asymptotic running times of our algorithmic methods, which validates their computational tractability on large datasets. We also provide a customizable, open-source code base for training MSTs in Python which employs several strategies for scalability, including parallel processing and warm starts. Finally, we assess the practical performance of MSTs on several synthetic and real world datasets, showing that our method reliably finds market segmentations which accurately model response behavior. Moreover, MSTs are interpretable since the market segments can easily be described by a decision tree and often require only a fraction of the number of market segments generated by traditional approaches.

The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation. The encoder-decoder architecture utilizes an encoder to capture multilevel feature maps, which are incorporated into the final prediction by a decoder. As the context is crucial for precise segmentation, tremendous effort has been made to extract such information in an intelligent fashion, including employing dilated/atrous convolutions or inserting attention modules. However, these endeavors are all based on the FCN architecture with ResNet or other backbones, which cannot fully exploit the context from the theoretical concept. By contrast, we introduce the Swin Transformer as the backbone to extract the context information and design a novel decoder of densely connected feature aggregation module (DCFAM) to restore the resolution and produce the segmentation map. The experimental results on two remotely sensed semantic segmentation datasets demonstrate the effectiveness of the proposed scheme.Code is available at //github.com/WangLibo1995/GeoSeg

In this paper, we propose a novel multi-task learning architecture, which incorporates recent advances in attention mechanisms. Our approach, the Multi-Task Attention Network (MTAN), consists of a single shared network containing a global feature pool, together with task-specific soft-attention modules, which are trainable in an end-to-end manner. These attention modules allow for learning of task-specific features from the global pool, whilst simultaneously allowing for features to be shared across different tasks. The architecture can be built upon any feed-forward neural network, is simple to implement, and is parameter efficient. Experiments on the CityScapes dataset show that our method outperforms several baselines in both single-task and multi-task learning, and is also more robust to the various weighting schemes in the multi-task loss function. We further explore the effectiveness of our method through experiments over a range of task complexities, and show how our method scales well with task complexity compared to baselines.