从数据中学习的方法取决于各种类型的调整参数，例如惩罚强度或步长大小。由于性能可以在很大程度上取决于这些参数，因此重要的是要比较估算器的类别 - 考虑规定的有限调谐参数集，而不是特别调谐的方法。在这项工作中，我们通过同类中最佳方法的相对性能研究方法类。我们考虑了线性回归的中心问题，即随机的各向同性地面真理，并研究了两种基本方法的估计性能，即梯度下降和脊回归。我们公布以下现象。 （1）对于一般设计，当经验数据协方差矩阵衰减的特征值缓慢，作为指数较不小于统一的功率定律时，恒定的梯度下降优于山脊回归。相反，如果特征值迅速衰减，则作为指数大于统一或指数的权力定律，我们表明山脊回归优于梯度下降。 （2）对于正交设计，我们计算了确切的最小值最佳估计器类别（达到最低最大最大最佳），这表明它等同于具有衰减学习率的梯度下降。我们发现山脊回归和梯度下降的次数均具有恒定的步长。我们的结果表明，统计性能可以在很大程度上取决于调整参数。特别是，虽然最佳调谐脊回归是我们设置中的最佳估计器，但当仅在有限的许多正则化参数上调整两种方法时，它可以用任意/无界数量的梯度下降来表现优于梯度下降。

我们重新审视GD的平均算法稳定性，用于训练过度的浅色神经网络，并证明没有NTK或PL假设的新的泛化和过度的风险范围。特别是，我们显示Oracle类型的界限，揭示了GD的泛化和过度风险由具有最短GD路径的插值网络从初始化（从某种意义上是具有最小相对规范的内插网络）来控制。虽然这是封闭式嵌入式嵌入式的，但我们的证据直接适用于GD培训的网络，而无需中间结石。与此同时，通过在这里开发的放松Oracle不等式，我们以简单的方式恢复基于NTK的风险范围，这表明我们的分析更加紧张。最后，与大多数基于NTK的分析不同，我们专注于带标签噪声的回归，并显示早期停止的GD是一致的。

通过分布式机器学习设置（如联合学习），我们考虑拟合跨越异构数据集的分布式集合的统计模型的问题，其相似性结构由图形拓扑编码。精确地，我们分析每个节点与拟合稀疏线性模型相关联的情况，如果它们的解决方案的差异也稀疏，则边缘连接两个节点。我们提出了一种基于基础追踪的方法，具有总变化罚化，为子高斯设计矩阵提供有限的样本保证。将树根作为参考节点，我们表明，如果节点横跨节点的差异的稀疏性小于根目录处的稀疏性，则恢复成功，采样较少，而不是通过独立解决问题，或者使用方法依赖于信号支持的大重叠，例如组套索。我们考虑无噪声和嘈杂的设置，并在数值上研究了基于乘法器（ADMM）和超光谱的分布式交替方向方法的分布式方法的性能。

When testing conditions differ from those represented in training data, so-called out-of-distribution (OOD) inputs can mar the reliability of black-box learned components in the modern robot autonomy stack. Therefore, coping with OOD data is an important challenge on the path towards trustworthy learning-enabled open-world autonomy. In this paper, we aim to demystify the topic of OOD data and its associated challenges in the context of data-driven robotic systems, drawing connections to emerging paradigms in the ML community that study the effect of OOD data on learned models in isolation. We argue that as roboticists, we should reason about the overall system-level competence of a robot as it performs tasks in OOD conditions. We highlight key research questions around this system-level view of OOD problems to guide future research toward safe and reliable learning-enabled autonomy.

We present a machine-learning framework to accurately characterize morphologies of Active Galactic Nucleus (AGN) host galaxies within $z<1$. We first use PSFGAN to decouple host galaxy light from the central point source, then we invoke the Galaxy Morphology Network (GaMorNet) to estimate whether the host galaxy is disk-dominated, bulge-dominated, or indeterminate. Using optical images from five bands of the HSC Wide Survey, we build models independently in three redshift bins: low $(0<z<0.25)$, medium $(0.25<z<0.5)$, and high $(0.5<z<1.0)$. By first training on a large number of simulated galaxies, then fine-tuning using far fewer classified real galaxies, our framework predicts the actual morphology for $\sim$ $60\%-70\%$ host galaxies from test sets, with a classification precision of $\sim$ $80\%-95\%$, depending on redshift bin. Specifically, our models achieve disk precision of $96\%/82\%/79\%$ and bulge precision of $90\%/90\%/80\%$ (for the 3 redshift bins), at thresholds corresponding to indeterminate fractions of $30\%/43\%/42\%$. The classification precision of our models has a noticeable dependency on host galaxy radius and magnitude. No strong dependency is observed on contrast ratio. Comparing classifications of real AGNs, our models agree well with traditional 2D fitting with GALFIT. The PSFGAN+GaMorNet framework does not depend on the choice of fitting functions or galaxy-related input parameters, runs orders of magnitude faster than GALFIT, and is easily generalizable via transfer learning, making it an ideal tool for studying AGN host galaxy morphology in forthcoming large imaging survey.

Extreme wildfires continue to be a significant cause of human death and biodiversity destruction within countries that encompass the Mediterranean Basin. Recent worrying trends in wildfire activity (i.e., occurrence and spread) suggest that wildfires are likely to be highly impacted by climate change. In order to facilitate appropriate risk mitigation, it is imperative to identify the main drivers of extreme wildfires and assess their spatio-temporal trends, with a view to understanding the impacts of global warming on fire activity. To this end, we analyse the monthly burnt area due to wildfires over a region encompassing most of Europe and the Mediterranean Basin from 2001 to 2020, and identify high fire activity during this period in eastern Europe, Algeria, Italy and Portugal. We build an extreme quantile regression model with a high-dimensional predictor set describing meteorological conditions, land cover usage, and orography, for the domain. To model the complex relationships between the predictor variables and wildfires, we make use of a hybrid statistical deep-learning framework that allows us to disentangle the effects of vapour-pressure deficit (VPD), air temperature, and drought on wildfire activity. Our results highlight that whilst VPD, air temperature, and drought significantly affect wildfire occurrence, only VPD affects extreme wildfire spread. Furthermore, to gain insights into the effect of climate change on wildfire activity in the near future, we perturb VPD and temperature according to their observed trends and find evidence that global warming may lead to spatially non-uniform changes in wildfire activity.

We propose a learning-based robust predictive control algorithm that compensates for significant uncertainty in the dynamics for a class of discrete-time systems that are nominally linear with an additive nonlinear component. Such systems commonly model the nonlinear effects of an unknown environment on a nominal system. We optimize over a class of nonlinear feedback policies inspired by certainty equivalent "estimate-and-cancel" control laws pioneered in classical adaptive control to achieve significant performance improvements in the presence of uncertainties of large magnitude, a setting in which existing learning-based predictive control algorithms often struggle to guarantee safety. In contrast to previous work in robust adaptive MPC, our approach allows us to take advantage of structure (i.e., the numerical predictions) in the a priori unknown dynamics learned online through function approximation. Our approach also extends typical nonlinear adaptive control methods to systems with state and input constraints even when we cannot directly cancel the additive uncertain function from the dynamics. We apply contemporary statistical estimation techniques to certify the system's safety through persistent constraint satisfaction with high probability. Moreover, we propose using Bayesian meta-learning algorithms that learn calibrated model priors to help satisfy the assumptions of the control design in challenging settings. Finally, we show in simulation that our method can accommodate more significant unknown dynamics terms than existing methods and that the use of Bayesian meta-learning allows us to adapt to the test environments more rapidly.

Optimal transport (OT) is a framework that can guide the design of efficient resource allocation strategies in a network of multiple sources and targets. This paper applies discrete OT to a swarm of UAVs in a novel way to achieve appropriate task allocation and execution. Drone swarm deployments already operate in multiple domains where sensors are used to gain knowledge of an environment [1]. Use cases such as, chemical and radiation detection, and thermal and RGB imaging create a specific need for an algorithm that considers parameters on both the UAV and waypoint side and allows for updating the matching scheme as the swarm gains information from the environment. Additionally, the need for a centralized planner can be removed by using a distributed algorithm that can dynamically update based on changes in the swarm network or parameters. To this end, we develop a dynamic and distributed OT algorithm that matches a UAV to the optimal waypoint based on one parameter at the UAV and another parameter at the waypoint. We show the convergence and allocation of the algorithm through a case study and test the algorithm's effectiveness against a greedy assignment algorithm in simulation.

When presented with a data stream of two statistically dependent variables, predicting the future of one of the variables (the target stream) can benefit from information about both its history and the history of the other variable (the source stream). For example, fluctuations in temperature at a weather station can be predicted using both temperatures and barometric readings. However, a challenge when modelling such data is that it is easy for a neural network to rely on the greatest joint correlations within the target stream, which may ignore a crucial but small information transfer from the source to the target stream. As well, there are often situations where the target stream may have previously been modelled independently and it would be useful to use that model to inform a new joint model. Here, we develop an information bottleneck approach for conditional learning on two dependent streams of data. Our method, which we call Transfer Entropy Bottleneck (TEB), allows one to learn a model that bottlenecks the directed information transferred from the source variable to the target variable, while quantifying this information transfer within the model. As such, TEB provides a useful new information bottleneck approach for modelling two statistically dependent streams of data in order to make predictions about one of them.

This technical report presents GPS++, the first-place solution to the Open Graph Benchmark Large-Scale Challenge (OGB-LSC 2022) for the PCQM4Mv2 molecular property prediction task. Our approach implements several key principles from the prior literature. At its core our GPS++ method is a hybrid MPNN/Transformer model that incorporates 3D atom positions and an auxiliary denoising task. The effectiveness of GPS++ is demonstrated by achieving 0.0719 mean absolute error on the independent test-challenge PCQM4Mv2 split. Thanks to Graphcore IPU acceleration, GPS++ scales to deep architectures (16 layers), training at 3 minutes per epoch, and large ensemble (112 models), completing the final predictions in 1 hour 32 minutes, well under the 4 hour inference budget allocated. Our implementation is publicly available at: https://github.com/graphcore/ogb-lsc-pcqm4mv2.