在启用语音的应用程序中，一个预定的热词在同时用来激活设备以便进行查询。 toavoid重复一个热词，我们提出了一个端到端的流（E2E）打算查询检测器，该查询检测器识别向设备指向的发音，并滤除针对设备的其他发出内容。提出的方法将预期的查询检测器置于E2E模型中，该模型将语音识别的不同组件折叠成一个神经网络。E2E对台面解码和预期的查询检测进行建模，也使我们可以基于早期的部分偏置检测结果， ，这对于减少潜伏期和使系统响应很重要。我们证明，与独立的预期检测器相比，检测准确性和600个MSLATENCE的相对相对改善的相对提高一级误差率（EER）的相对提高了22％。在我们的实验中，提出的模型检测用户正在用用户开始讲话后，用8.7％的Eerwithin与设备进行对话。

语言模型既展示了定量的改进，又展示了新的定性功能，随着规模的增加。尽管它们具有潜在的变革性影响，但这些新能力的特征却很差。为了为未来的研究提供信息，为破坏性的新模型能力做准备，并改善社会有害的效果，至关重要的是，我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战，我们介绍了超越模仿游戏基准（Big Bench）。 Big Bench目前由204个任务组成，由132家机构的442位作者贡献。任务主题是多样的，从语言学，儿童发展，数学，常识性推理，生物学，物理学，社会偏见，软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号，Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为，跨越了数百万到数十亿个参数。此外，一个人类专家评估者团队执行了所有任务，以提供强大的基准。研究结果包括：模型性能和校准都随规模改善，但绝对的术语（以及与评估者的性能相比）；在模型类中的性能非常相似，尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分，而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标；社交偏见通常会随着含糊不清的环境而随着规模而增加，但这可以通过提示来改善。

We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics. We give the first black-box reduction from privacy to robustness which can produce private estimators with optimal tradeoffs among sample complexity, accuracy, and privacy for a wide range of fundamental high-dimensional parameter estimation problems, including mean and covariance estimation. We show that this reduction can be implemented in polynomial time in some important special cases. In particular, using nearly-optimal polynomial-time robust estimators for the mean and covariance of high-dimensional Gaussians which are based on the Sum-of-Squares method, we design the first polynomial-time private estimators for these problems with nearly-optimal samples-accuracy-privacy tradeoffs. Our algorithms are also robust to a constant fraction of adversarially-corrupted samples.

Metric Elicitation (ME) is a framework for eliciting classification metrics that better align with implicit user preferences based on the task and context. The existing ME strategy so far is based on the assumption that users can most easily provide preference feedback over classifier statistics such as confusion matrices. This work examines ME, by providing a first ever implementation of the ME strategy. Specifically, we create a web-based ME interface and conduct a user study that elicits users' preferred metrics in a binary classification setting. We discuss the study findings and present guidelines for future research in this direction.

The first large-scale deployment of private federated learning uses differentially private counting in the continual release model as a subroutine (Google AI blog titled "Federated Learning with Formal Differential Privacy Guarantees"). In this case, a concrete bound on the error is very relevant to reduce the privacy parameter. The standard mechanism for continual counting is the binary mechanism. We present a novel mechanism and show that its mean squared error is both asymptotically optimal and a factor 10 smaller than the error of the binary mechanism. We also show that the constants in our analysis are almost tight by giving non-asymptotic lower and upper bounds that differ only in the constants of lower-order terms. Our algorithm is a matrix mechanism for the counting matrix and takes constant time per release. We also use our explicit factorization of the counting matrix to give an upper bound on the excess risk of the private learning algorithm of Denisov et al. (NeurIPS 2022). Our lower bound for any continual counting mechanism is the first tight lower bound on continual counting under approximate differential privacy. It is achieved using a new lower bound on a certain factorization norm, denoted by $\gamma_F(\cdot)$, in terms of the singular values of the matrix. In particular, we show that for any complex matrix, $A \in \mathbb{C}^{m \times n}$, \[ \gamma_F(A) \geq \frac{1}{\sqrt{m}}\|A\|_1, \] where $\|\cdot \|$ denotes the Schatten-1 norm. We believe this technique will be useful in proving lower bounds for a larger class of linear queries. To illustrate the power of this technique, we show the first lower bound on the mean squared error for answering parity queries.

Recent work shows that the expressive power of Graph Neural Networks (GNNs) in distinguishing non-isomorphic graphs is exactly the same as that of the Weisfeiler-Lehman (WL) graph test. In particular, they show that the WL test can be simulated by GNNs. However, those simulations involve neural networks for the 'combine' function of size polynomial or even exponential in the number of graph nodes $n$, as well as feature vectors of length linear in $n$. We present an improved simulation of the WL test on GNNs with \emph{exponentially} lower complexity. In particular, the neural network implementing the combine function in each node has only a polylogarithmic number of parameters in $n$, and the feature vectors exchanged by the nodes of GNN consists of only $O(\log n)$ bits. We also give logarithmic lower bounds for the feature vector length and the size of the neural networks, showing the (near)-optimality of our construction.

This work proposes Multi-task Meta Learning (MTML), integrating two learning paradigms Multi-Task Learning (MTL) and meta learning, to bring together the best of both worlds. In particular, it focuses simultaneous learning of multiple tasks, an element of MTL and promptly adapting to new tasks with fewer data, a quality of meta learning. It is important to highlight that we focus on heterogeneous tasks, which are of distinct kind, in contrast to typically considered homogeneous tasks (e.g., if all tasks are classification or if all tasks are regression tasks). The fundamental idea is to train a multi-task model, such that when an unseen task is introduced, it can learn in fewer steps whilst offering a performance at least as good as conventional single task learning on the new task or inclusion within the MTL. By conducting various experiments, we demonstrate this paradigm on two datasets and four tasks: NYU-v2 and the taskonomy dataset for which we perform semantic segmentation, depth estimation, surface normal estimation, and edge detection. MTML achieves state-of-the-art results for most of the tasks. Although semantic segmentation suffers quantitatively, our MTML method learns to identify segmentation classes absent in the pseudo labelled ground truth of the taskonomy dataset.

在本文中，我们提出了针对无人接地车辆（UGV）的新的控制屏障功能（CBF），该功能有助于避免与运动学（非零速度）障碍物发生冲突。尽管当前的CBF形式已经成功地保证了与静态障碍物的安全/碰撞避免安全性，但动态案例的扩展已获得有限的成功。此外，借助UGV模型，例如Unicycle或自行车，现有CBF的应用在控制方面是保守的，即在某些情况下不可能进行转向/推力控制。从经典的碰撞锥中汲取灵感来避免轨迹规划，我们介绍了其新颖的CBF配方，并具有对独轮车和自行车模型的安全性保证。主要思想是确保障碍物的速度W.R.T.车辆总是指向车辆。因此，我们构建了一个约束，该约束确保速度向量始终避开指向车辆的向量锥。这种新控制方法的功效在哥白尼移动机器人上进行了实验验证。我们将其进一步扩展到以自行车模型的形式扩展到自动驾驶汽车，并在Carla模拟器中的各种情况下证明了避免碰撞。

在过去的十年中，由于雷达目的的现场特异性，高保真射频（RF）建模和仿真工具的催化，在过去的十年中，经典方法的数据驱动公式迅速增长。尽管有这种激增，但有限的焦点已针对这些经典方法的理论基础。在这方面，作为我们正在进行的数据驱动的雷达时空自适应处理方法（Stap）的一部分，我们在雷达目标定位的背景下分析了精选子空间分离方法的渐近性能保证，并通过拟议目标位置估计的深度学习框架。在我们的方法中，我们通过使用RFView（由ISL Inc.开发的一个特定于站点的RF建模和模拟工具）将可变强度的目标随机放置在预定的约束区域中。在范围内，方位角和归一化自适应匹配过滤器（NAMF）测试统计量以及广义Sidelobe canceller（GSC）的输出功率的高度。使用我们的深度学习框架，我们从这些热图张量估算目标位置，以证明我们数据驱动方法在匹配和不匹配的设置中提供的可行性和显着改进。

前列腺活检和图像引导的治疗程序通常是在与磁共振图像（MRI）的超声指导下进行的。准确的图像融合依赖于超声图像上前列腺的准确分割。然而，超声图像中降低的信噪比和工件（例如，斑点和阴影）限制了自动前列腺分割技术的性能，并将这些方法推广到新的图像域是本质上很难的。在这项研究中，我们通过引入一种新型的2.5D深神经网络来解决这些挑战，用于超声图像上的前列腺分割。我们的方法通过组合有监督的域适应技术和知识蒸馏损失，解决了转移学习和填充方法的局限性（即，在更新模型权重时，在更新模型权重时的性能下降）。知识蒸馏损失允许保留先前学习的知识，并在新数据集上的模型填充后降低性能下降。此外，我们的方法依赖于注意模块，该模块认为模型特征定位信息以提高分割精度。我们对一个机构的764名受试者进行了培训，并仅使用后续机构中的十个受试者对我们的模型进行了审核。我们分析了方法在三个大型数据集上的性能，其中包括来自三个不同机构的2067名受试者。我们的方法达到了平均骰子相似性系数（骰子）为$ 94.0 \ pm0.03 $，而Hausdorff距离（HD95）为2.28 $ mm $，在第一机构的独立受试者中。此外，我们的模型在其他两个机构的研究中都很好地概括了（骰子：$ 91.0 \ pm0.03 $; hd95：3.7 $ mm $ and Dice：$ 82.0 \ pm0.03 $; hd95 $; hd95：7.1 $ mm $）。