Consider the following abstract coin tossing problem: Given a set of $n$ coins with unknown biases, find the most biased coin using a minimal number of coin tosses. This is a common abstraction of various exploration problems in theoretical computer science and machine learning and has been studied extensively over the years. In particular, algorithms with optimal sample complexity (number of coin tosses) have been known for this problem for quite some time. Motivated by applications to processing massive datasets, we study the space complexity of solving this problem with optimal number of coin tosses in the streaming model. In this model, the coins are arriving one by one and the algorithm is only allowed to store a limited number of coins at any point -- any coin not present in the memory is lost and can no longer be tossed or compared to arriving coins. Prior algorithms for the coin tossing problem with optimal sample complexity are based on iterative elimination of coins which inherently require storing all the coins, leading to memory-inefficient streaming algorithms. We remedy this state-of-affairs by presenting a series of improved streaming algorithms for this problem: we start with a simple algorithm which require storing only $O(\log{n})$ coins and then iteratively refine it further and further, leading to algorithms with $O(\log\log{(n)})$ memory, $O(\log^*{(n)})$ memory, and finally a one that only stores a single extra coin in memory -- the same exact space needed to just store the best coin throughout the stream. Furthermore, we extend our algorithms to the problem of finding the $k$ most biased coins as well as other exploration problems such as finding top-$k$ elements using noisy comparisons or finding an $\epsilon$-best arm in stochastic multi-armed bandits, and obtain efficient streaming algorithms for these problems.

We propose Spatio-temporal Crop Aggregation for video representation LEarning (SCALE), a novel method that enjoys high scalability at both training and inference time. Our model builds long-range video features by learning from sets of video clip-level features extracted with a pre-trained backbone. To train the model, we propose a self-supervised objective consisting of masked clip feature prediction. We apply sparsity to both the input, by extracting a random set of video clips, and to the loss function, by only reconstructing the sparse inputs. Moreover, we use dimensionality reduction by working in the latent space of a pre-trained backbone applied to single video clips. The video representation is then obtained by taking the ensemble of the concatenation of embeddings of separate video clips with a video clip set summarization token. These techniques make our method not only extremely efficient to train, but also highly effective in transfer learning. We demonstrate that our video representation yields state-of-the-art performance with linear, non-linear, and $k$-NN probing on common action classification datasets.

机器学习最近被出现为研究复杂现象的有希望的方法，其特征是丰富的数据集。特别地，以数据为中心的方法为手动检查可能错过的实验数据集中自动发现结构的可能性。在这里，我们介绍可解释的无监督监督的混合机学习方法，混合相关卷积神经网络（Hybrid-CCNN），并将其应用于使用基于Rydberg Atom阵列的可编程量子模拟器产生的实验数据。具体地，我们应用Hybrid-CCNN以通过可编程相互作用分析在方形格子上的新量子阶段。初始无监督的维度降低和聚类阶段首先揭示了五个不同的量子相位区域。在第二个监督阶段，我们通过培训完全解释的CCNN来细化这些相界并通过训练每个阶段提取相关的相关性。在条纹相中的每个相捕获量子波动中专门识别的特征空间加权和相关的相关性并鉴定两个先前未检测到的相，菱形和边界有序相位。这些观察结果表明，具有机器学习的可编程量子模拟器的组合可用作有关相关量子态的详细探索的强大工具。

在许多真实世界应用程序的组合匪徒如内容缓存，必须在满足最小服务要求的同时最大化奖励。此外，基本ARM可用性随着时间的推移而变化，并且采取的行动需要适应奖励最大化的情况。我们提出了一个名为Contexal Combinatial Volatile Birtits的新的强盗模型，具有组阈值来解决这些挑战。我们的模型通过考虑超级臂作为基础臂组的子集来归档组合匪徒。我们寻求最大化超级手臂奖励，同时满足构成超级臂的所有基座组的阈值。为此，我们定义了一个新的遗憾遗嘱，使超级臂奖励最大化与团体奖励满意度合并。为了便于学习，我们假设基臂的平均结果是由上下文索引的高斯过程的样本，并且预期的奖励是Lipschitz在预期的基础臂结果中连续。我们提出了一种算法，称为阈值组合高斯工艺的上置信度界限（TCGP-UCB），最大化累积奖励和满足组奖励阈值之间的余额，并证明它会导致$ \ tilde {o}（k \ sqrt {t \ overline { \ gamma} _ {t}}）$后悔具有高概率，其中$ \ overline {\ gamma} _ {t} $是与第一个$ t $轮中出现的基本arm上下文相关联的最大信息增益$ k $是所有在所有轮匝上任何可行行动的超级臂基数。我们在实验中展示了我们的算法累积了与最先进的组合强盗算法相当的奖励，同时采摘群体满足其阈值的动作。

Many applications of representation learning, such as privacy preservation, algorithmic fairness, and domain adaptation, desire explicit control over semantic information being discarded. This goal is formulated as satisfying two objectives: maximizing utility for predicting a target attribute while simultaneously being invariant (independent) to a known semantic attribute. Solutions to invariant representation learning (IRepL) problems lead to a trade-off between utility and invariance when they are competing. While existing works study bounds on this trade-off, two questions remain outstanding: 1) What is the exact trade-off between utility and invariance? and 2) What are the encoders (mapping the data to a representation) that achieve the trade-off, and how can we estimate it from training data? This paper addresses these questions for IRepLs in reproducing kernel Hilbert spaces (RKHS)s. Under the assumption that the distribution of a low-dimensional projection of high-dimensional data is approximately normal, we derive a closed-form solution for the global optima of the underlying optimization problem for encoders in RKHSs. This yields closed formulae for a near-optimal trade-off, corresponding optimal representation dimensionality, and the corresponding encoder(s). We also numerically quantify the trade-off on representative problems and compare them to those achieved by baseline IRepL algorithms.

优化通常是一个确定性问题，其中通过诸如梯度下降的一些迭代过程找到解决方案。然而，当培训神经网络时，由于样本的子集的随机选择，损耗函数会超过（迭代）时间。该随机化将优化问题转变为随机级别。我们建议将损失视为关于一些参考最优参考的嘈杂观察。这种对损失的解释使我们能够采用卡尔曼滤波作为优化器，因为其递归制剂旨在估计来自嘈杂测量的未知参数。此外，我们表明，用于未知参数的演进的卡尔曼滤波器动力学模型可用于捕获高级方法的梯度动态，如动量和亚当。我们称之为该随机优化方法考拉，对于Kalman优化算法而言，具有损失适应性的缺陷。考拉是一种易于实现，可扩展，高效的方法来训练神经网络。我们提供了通过实验的收敛分析和显示，它产生了与跨多个神经网络架构和机器学习任务的现有技术优化算法的现有状态的参数估计，例如计算机视觉和语言建模。

我们考虑优化从高斯过程（GP）采样的矢量值的目标函数$ \ boldsymbol {f} $ sampled的问题，其索引集是良好的，紧凑的度量空间$（{\ cal x}，d）$设计。我们假设$ \ boldsymbol {f} $之前未知，并且在Design $ x $的$ \ \ boldsymbol {f} $ x $导致$ \ boldsymbol {f}（x）$。由于当$ {\ cal x} $很大的基数时，识别通过详尽搜索的帕累托最优设计是不可行的，因此我们提出了一种称为Adaptive $ \ Boldsymbol {\ epsilon} $ - PAL的算法，从而利用GP的平滑度-Ampled函数和$（{\ cal x}，d）$的结构快速学习。从本质上讲，Adaptive $ \ Boldsymbol {\ epsilon} $ - PAL采用基于树的自适应离散化技术，以识别$ \ Boldsymbol {\ epsilon} $ - 尽可能少的评估中的准确帕累托一组设计。我们在$ \ boldsymbol {\ epsilon} $ - 准确的Pareto Set识别上提供信息类型和度量尺寸类型界限。我们还在实验表明我们的算法在多个基准数据集上优于其他Pareto Set识别方法。