Methods based on ordinary differential equations (ODEs) are widely used to build generative models of time-series. In addition to high computational overhead due to explicitly computing hidden states recurrence, existing ODE-based models fall short in learning sequence data with sharp transitions - common in many real-world systems - due to numerical challenges during optimization. In this work, we propose LS4, a generative model for sequences with latent variables evolving according to a state space ODE to increase modeling capacity. Inspired by recent deep state space models (S4), we achieve speedups by leveraging a convolutional representation of LS4 which bypasses the explicit evaluation of hidden states. We show that LS4 significantly outperforms previous continuous-time generative models in terms of marginal distribution, classification, and prediction scores on real-world datasets in the Monash Forecasting Repository, and is capable of modeling highly stochastic data with sharp temporal transitions. LS4 sets state-of-the-art for continuous-time latent generative models, with significant improvement of mean squared error and tighter variational lower bounds on irregularly-sampled datasets, while also being x100 faster than other baselines on long sequences.

During image editing, existing deep generative models tend to re-synthesize the entire output from scratch, including the unedited regions. This leads to a significant waste of computation, especially for minor editing operations. In this work, we present Spatially Sparse Inference (SSI), a general-purpose technique that selectively performs computation for edited regions and accelerates various generative models, including both conditional GANs and diffusion models. Our key observation is that users tend to make gradual changes to the input image. This motivates us to cache and reuse the feature maps of the original image. Given an edited image, we sparsely apply the convolutional filters to the edited regions while reusing the cached features for the unedited regions. Based on our algorithm, we further propose Sparse Incremental Generative Engine (SIGE) to convert the computation reduction to latency reduction on off-the-shelf hardware. With 1.2%-area edited regions, our method reduces the computation of DDIM by 7.5$\times$ and GauGAN by 18$\times$ while preserving the visual fidelity. With SIGE, we accelerate the speed of DDIM by 3.0x on RTX 3090 and 6.6$\times$ on Apple M1 Pro CPU, and GauGAN by 4.2$\times$ on RTX 3090 and 14$\times$ on Apple M1 Pro CPU.

Score-based generative models learn a family of noise-conditional score functions corresponding to the data density perturbed with increasingly large amounts of noise. These perturbed data densities are tied together by the Fokker-Planck equation (FPE), a PDE governing the spatial-temporal evolution of a density undergoing a diffusion process. In this work, we derive a corresponding equation characterizing the noise-conditional scores of the perturbed data densities (i.e., their gradients), termed the score FPE. Surprisingly, despite impressive empirical performance, we observe that scores learned via denoising score matching (DSM) do not satisfy the underlying score FPE. We mathematically analyze three implications of satisfying the score FPE and a potential explanation for why the score FPE is not satisfied in practice. At last, we propose to regularize the DSM objective to enforce satisfaction of the score FPE, and show its effectiveness on synthetic data and MNIST.

Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Diffusion and Imagen. However, a downside of classifier-free guided diffusion models is that they are computationally expensive at inference time since they require evaluating two diffusion models, a class-conditional model and an unconditional model, tens to hundreds of times. To deal with this limitation, we propose an approach to distilling classifier-free guided diffusion models into models that are fast to sample from: Given a pre-trained classifier-free guided model, we first learn a single model to match the output of the combined conditional and unconditional models, and then we progressively distill that model to a diffusion model that requires much fewer sampling steps. For standard diffusion models trained on the pixel-space, our approach is able to generate images visually comparable to that of the original model using as few as 4 sampling steps on ImageNet 64x64 and CIFAR-10, achieving FID/IS scores comparable to that of the original model while being up to 256 times faster to sample from. For diffusion models trained on the latent-space (e.g., Stable Diffusion), our approach is able to generate high-fidelity images using as few as 1 to 4 denoising steps, accelerating inference by at least 10-fold compared to existing methods on ImageNet 256x256 and LAION datasets. We further demonstrate the effectiveness of our approach on text-guided image editing and inpainting, where our distilled model is able to generate high-quality results using as few as 2-4 denoising steps.

使用通过组成可逆层获得的地图进行标准化模型复杂概率分布。特殊的线性层（例如蒙版和1x1卷积）在现有体系结构中起着关键作用，因为它们在具有可拖动的Jacobians和倒置的同时增加表达能力。我们提出了一个基于蝴蝶层的新的可逆线性层家族，理论上捕获复杂的线性结构，包括排列和周期性，但可以有效地倒置。这种代表力是我们方法的关键优势，因为这些结构在许多现实世界数据集中很常见。根据我们的可逆蝴蝶层，我们构建了一个新的称为蝴蝶流的归一化流量模型。从经验上讲，我们证明蝴蝶不仅可以在MNIST，CIFAR-10和Imagenet 32​​x32等自然图像上实现强密度估计结果，而且还可以在结构化数据集中获得明显更好的对数可能性，例如Galaxy图像和Mimic-III患者群体 - - 同时，在记忆和计算方面比相关基线更有效。

扩散模型可以用作解决各种反问题的学习先验。但是，大多数现有方法仅限于线性问题，从而将其适用性限制在更普遍的情况下。在本文中，我们建立在降级扩散恢复模型（DDRM）的基础上，并提出了一种解决某些非线性反问题的方法。我们利用DDRM中使用的伪内运算符并将此概念推广到其他测量操作员，这使我们能够使用预先训练的无条件扩散模型进行JPEG伪影校正等应用。我们从经验上证明了我们方法在各种质量因素中的有效性，从而达到与专门针对JPEG恢复任务训练的最先进方法相当的性能水平。

尽管自我监督学习（SSL）方法取得了经验成功，但尚不清楚其表示的哪些特征导致了高下游精度。在这项工作中，我们表征了SSL表示应该满足的属性。具体而言，我们证明了必要和充分的条件，因此，对于给出的数据增强的任何任务，在该表示形式上训练的所需探针（例如，线性或MLP）具有完美的准确性。这些要求导致一个统一的概念框架，用于改善现有的SSL方法并得出新方法。对于对比度学习，我们的框架规定了对以前的方法（例如使用不对称投影头）的简单但重大改进。对于非对比度学习，我们使用框架来得出一个简单新颖的目标。我们所得的SSL算法在标准基准测试上的表现优于基线，包括Imagenet线性探测的SHAV+多螺旋桨。

在处理多点测量时，即传统的黑盒优化方法效率低下，即，当控制域中的每个查询需要在次级域中的一组测量以计算目标时。在粒子加速器中，四极扫描的发射率调整是具有多点测量的优化示例。尽管发射率是高亮度机器（包括X射线激光器和线性碰撞者）的性能的关键参数，但综合优化通常受到调整所需的时间的限制。在这里，我们将最近提供的贝叶斯算法执行（BAX）扩展到具有多点测量的优化任务。 BAX通过在关节控制测量域中选择和建模各个点来实现样品效率。我们将BAX应用于Linac相干光源（LCLS）和晚期加速器实验测试II（Facet-II）粒子加速器的设施。在LCLS模拟环境中，我们表明BAX的效率提高了20倍，同时与传统优化方法相比，噪声也更强。此外，我们在LCLS和facet-II上运行了Bax，与Facet-II的手工调整发射率相匹配，并获得了比LCLS在LCLS上获得的最佳发射率低24％。我们预计我们的方法很容易适应其他类型的优化问题，这些优化问题涉及科学仪器中常见的多点测量。

大型视力模型的无监督预训练方法已显示出可以提高下游监督任务的性能。为卫星图像开发类似的技术带来了重要的机会，因为未标记的数据很丰富，并且固有的时间和多光谱结构提供了途径，以进一步改善现有的训练策略。在本文中，我们提出了Satmae，这是基于蒙面自动编码器（MAE）的时间或多光谱卫星图像的预训练框架。为了利用时间信息，我们包括一个时间嵌入以及跨时间独立掩盖图像贴片。此外，我们证明将多光谱数据编码为具有不同光谱位置编码的频段组是有益的。我们的方法在基准数据集（最高$ \ uparrow $ 7 \％）上的监督学习绩效方面都对先前最先前的技术产生了强大的改进，以及在下游遥感任务（包括土地）上的转移学习绩效封面分类（最多$ \ uparrow $ 14 \％）和语义细分。

采集函数是贝叶斯优化（BO）中的关键组成部分，通常可以写为在替代模型下对效用函数的期望。但是，为了确保采集功能是可以优化的，必须对替代模型和实用程序功能进行限制。为了将BO扩展到更广泛的模型和实用程序，我们提出了不含可能性的BO（LFBO），这是一种基于无似然推理的方法。 LFBO直接对采集函数进行建模，而无需单独使用概率替代模型进行推断。我们表明，可以将计算LFBO中的采集函数缩小为优化加权分类问题，而权重对应于所选择的实用程序。通过为预期改进选择实用程序功能，LFBO在几个现实世界优化问题上都优于各种最新的黑盒优化方法。 LFBO还可以有效利用目标函数的复合结构，从而进一步改善了其遗憾。