Variational autoencoders model high-dimensional data by positing low-dimensional latent variables that are mapped through a flexible distribution parametrized by a neural network. Unfortunately, variational autoencoders often suffer from posterior collapse: the posterior of the latent variables is equal to its prior, rendering the variational autoencoder useless as a means to produce meaningful representations. Existing approaches to posterior collapse often attribute it to the use of neural networks or optimization issues due to variational approximation. In this paper, we consider posterior collapse as a problem of latent variable non-identifiability. We prove that the posterior collapses if and only if the latent variables are non-identifiable in the generative model. This fact implies that posterior collapse is not a phenomenon specific to the use of flexible distributions or approximate inference. Rather, it can occur in classical probabilistic models even with exact inference, which we also demonstrate. Based on these results, we propose a class of latent-identifiable variational autoencoders, deep generative models which enforce identifiability without sacrificing flexibility. This model class resolves the problem of latent variable non-identifiability by leveraging bijective Brenier maps and parameterizing them with input convex neural networks, without special variational inference objectives or optimization tricks. Across synthetic and real datasets, latent-identifiable variational autoencoders outperform existing methods in mitigating posterior collapse and providing meaningful representations of the data.

Likelihood-based deep generative models have recently been shown to exhibit pathological behaviour under the manifold hypothesis as a consequence of using high-dimensional densities to model data with low-dimensional structure. In this paper we propose two methodologies aimed at addressing this problem. Both are based on adding Gaussian noise to the data to remove the dimensionality mismatch during training, and both provide a denoising mechanism whose goal is to sample from the model as though no noise had been added to the data. Our first approach is based on Tweedie's formula, and the second on models which take the variance of added noise as a conditional input. We show that surprisingly, while well motivated, these approaches only sporadically improve performance over not adding noise, and that other methods of addressing the dimensionality mismatch are more empirically adequate.

Gaussian processes scale prohibitively with the size of the dataset. In response, many approximation methods have been developed, which inevitably introduce approximation error. This additional source of uncertainty, due to limited computation, is entirely ignored when using the approximate posterior. Therefore in practice, GP models are often as much about the approximation method as they are about the data. Here, we develop a new class of methods that provides consistent estimation of the combined uncertainty arising from both the finite number of data observed and the finite amount of computation expended. The most common GP approximations map to an instance in this class, such as methods based on the Cholesky factorization, conjugate gradients, and inducing points. For any method in this class, we prove (i) convergence of its posterior mean in the associated RKHS, (ii) decomposability of its combined posterior covariance into mathematical and computational covariances, and (iii) that the combined variance is a tight worst-case bound for the squared error between the method's posterior mean and the latent function. Finally, we empirically demonstrate the consequences of ignoring computational uncertainty and show how implicitly modeling it improves generalization performance on benchmark datasets.

与高斯过程（GPS）的变异近似通常使用一组诱导点来形成与协方差矩阵的低级别近似值。在这项工作中，我们相反利用了精度矩阵的稀疏近似。我们提出了差异最近的邻居高斯工艺（VNNGP），该过程引入了先验，该过程仅保留在k最近的邻居观测中的相关性，从而诱导稀疏精度结构。使用变分框架，可以将VNNGP的目标分解在观测值和诱导点上，从而以O（$ k^3 $）的时间复杂性实现随机优化。因此，我们可以任意扩展诱导点大小，甚至可以在每个观察到的位置放置诱导点。我们通过各种实验将VNNGP与其他可扩展的GP进行比较，并证明VNNGP（1）可以极大地超过低级别方法，而（2）比其他最近的邻居方法较不适合过度拟合。

高斯工艺高参数优化需要大核矩阵的线性溶解和对数确定因子。迭代数值技术依赖于线性溶液的共轭梯度方法（CG）和对数数据的随机痕迹估计的迭代数值技术变得越来越流行。这项工作介绍了用于预处理这些计算的新算法和理论见解。虽然在CG的背景下对预处理有充分的理解，但我们证明了它也可以加速收敛并减少对数数据及其衍生物的估计值的方差。我们证明了对数确定性，对数 - 界限可能性及其衍生物的预处理计算的一般概率误差界限。此外，我们得出了一系列内核 - 前提组合的特定速率，这表明可以达到指数收敛。我们的理论结果可以证明对内核超参数的有效优化，我们在大规模的基准问题上进行经验验证。我们的方法可以加速训练，最多可以达到数量级。

宽度限制最近是深度学习研究的焦点：模数计算实用，做更广泛的网络优于较窄的网络？当传统网络增益具有宽度的代表性，潜在掩盖任何负面影响，回答这个问题一直在具有挑战性。我们在本文中的分析通过神经网络的概括到深层高斯过程（深GP），一类非参数分层模型，占据了神经网络的非参数分层模型。在这样做时，我们的目标是了解一旦对给定建模任务的容量足够的容量，才能了解宽度（标准）神经网络。我们深入GP的理论和经验结果表明，大宽度可能对等级模型有害。令人惊讶的是，我们证明了甚至非参数的深GP融合到高斯过程，实际上变得浅薄而没有任何代表性的力量。对应于数据适应性基本函数的混合的后后，与宽度变得较小。我们的尾部分析表明，宽度和深度具有相反的影响：深度突出了模型的非高斯，而宽度使模型越来越高斯。我们发现有一个“甜蜜点”，可以在限制GP行为防止适应性之前最大化测试性能，以宽度= 1或宽度= 2用于非参数深GP。这些结果对具有L2正规化训练的传统神经网络中的相同现象（类似于参数的高斯），使得这种神经网络可能需要多达500至1000个隐藏单元的现象，以获得足够的容量 - 取决于数据集 - 但进一步的宽度降低了性能。

归一化流量是具有易于易变量的神经网络的可逆性网络，其允许通过最大可能性优化它们的参数来有效地执行。然而，通常假设感兴趣的数据生活在嵌入在高维环境空间中的一些（通常未知）的低维歧管中。结果是自建设中以来的建模不匹配 - 可逆性要求意味着学习分布的高维支持。注射流量，从低到高维空间的映射，旨在通过学习歧管的分布来解决这种差异，但是由此产生的体积变化术语变得更具挑战性。目前方法避免完全使用各种启发式计算该术语，或者假设歧管预先已知，因此不广泛适用。相反，我们提出了两种方法来对模型的参数来促进该术语的梯度，依赖于仔细使用来自数值线性代数的自动分化和技术。两种方法都对将其投射到这种歧管上的数据执行端到端非线性歧管学习和密度估计。我们研究了我们所提出的方法之间的权衡，经验验证我们优于更准确地学习歧管和对应的相应分布忽略音量变化术语的优先级，并显示出对分布外检测的有希望的结果。我们的代码可在https://github.com/layer6ai-labs/rectangular-flows中找到。

Gumbel-Softmax是对单纯形的连续分布，通常用作离散分布的放松。因为它可以轻松解释和容易重新聚集，所以它可以广泛使用。我们提出了一个模块化，更灵活的可重新聚集分布家族，其中高斯噪声通过可逆函数转化为单热近似。这种可逆函数由修改后的软磁性组成，可以结合具有不同特定目的的各种转换。例如，破坏过程使我们能够将重新聚集技巧扩展到具有无数支持的分布，从而使我们沿非参数模型的分布使用或归一化流量使我们提高了分布的灵活性。我们的构造具有比Gumbel-Softmax（例如封闭形式KL）的理论优势，并且在各种实验中都显着优于它。我们的代码可在https://github.com/cunningham-lab/igr上获得。

We demonstrate a proof-of-concept of a large language model conducting corporate lobbying related activities. We use an autoregressive large language model (OpenAI's text-davinci-003) to determine if proposed U.S. Congressional bills are relevant to specific public companies and provide explanations and confidence levels. For the bills the model deems as relevant, the model drafts a letter to the sponsor of the bill in an attempt to persuade the congressperson to make changes to the proposed legislation. We use hundreds of ground-truth labels of the relevance of a bill to a company to benchmark the performance of the model, which outperforms the baseline of predicting the most common outcome of irrelevance. However, we test the ability to determine the relevance of a bill with the previous OpenAI GPT-3 model (text-davinci-002), which was state-of-the-art on many language tasks until text-davinci-003 was released on November 28, 2022. The performance of text-davinci-002 is worse than simply always predicting that a bill is irrelevant to a company. These results suggest that, as large language models continue to improve core natural language understanding capabilities, performance on corporate lobbying related tasks will continue to improve. We then discuss why this could be problematic for societal-AI alignment.

We introduce Argoverse 2 (AV2) - a collection of three datasets for perception and forecasting research in the self-driving domain. The annotated Sensor Dataset contains 1,000 sequences of multimodal data, encompassing high-resolution imagery from seven ring cameras, and two stereo cameras in addition to lidar point clouds, and 6-DOF map-aligned pose. Sequences contain 3D cuboid annotations for 26 object categories, all of which are sufficiently-sampled to support training and evaluation of 3D perception models. The Lidar Dataset contains 20,000 sequences of unlabeled lidar point clouds and map-aligned pose. This dataset is the largest ever collection of lidar sensor data and supports self-supervised learning and the emerging task of point cloud forecasting. Finally, the Motion Forecasting Dataset contains 250,000 scenarios mined for interesting and challenging interactions between the autonomous vehicle and other actors in each local scene. Models are tasked with the prediction of future motion for "scored actors" in each scenario and are provided with track histories that capture object location, heading, velocity, and category. In all three datasets, each scenario contains its own HD Map with 3D lane and crosswalk geometry - sourced from data captured in six distinct cities. We believe these datasets will support new and existing machine learning research problems in ways that existing datasets do not. All datasets are released under the CC BY-NC-SA 4.0 license.