在这项工作中，我们提出了一种深度自适应采样（DAS）方法，用于求解部分微分方程（PDE），其中利用深神经网络近似PDE和深生成模型的解决方案，用于生成改进训练集的新的搭配点。 DAS的整体过程由两个组件组成：通过最小化训练集中的搭配点上的剩余损失来解决PDE，并生成新的训练集，以进一步提高电流近似解的准确性。特别地，我们将残差作为概率密度函数进行处理，并用一个被称为Krnet的深生成模型近似它。来自Krnet的新样品与残留物诱导的分布一致，即，更多样品位于大残留的区域中，并且较少的样品位于小残余区域中。类似于经典的自适应方法，例如自适应有限元，Krnet作为引导训练集的改进的错误指示器。与用均匀分布的搭配点获得的神经网络近似相比，发达的算法可以显着提高精度，特别是对于低规律性和高维问题。我们展示了一个理论分析，表明所提出的DAS方法可以减少误差并展示其与数值实验的有效性。

本文介绍了一种基于Krnet（ADDA-KR）的自适应深度近似策略，用于求解稳态Fokker-Planck（F-P）方程。 F-P方程通常是高维度和在无限域上定义的，这限制了基于传统网格的数值方法的应用。通过Knothe-Rosenblatt重新排列，我们的新提出的基于流的生成模型称为KrNet，提供了一种概率密度函数的家族，以作为Fokker-Planck方程的有效解决方案候选者，这与传统的计算方法较弱的维度依赖性较弱并且可以有效地估计一般的高维密度函数。为了获得用于F-P方程的近似的有效随机搭配点，我们开发了一种自适应采样过程，其中使用每次迭代的近似密度函数来迭代地生成样本。我们介绍了ADDA-KR的一般框架，验证了其准确性并通过数值实验展示了其效率。

在这项工作中，我们已经提出了一种称为VAE-Krnet的生成模型，用于密度估计或近似，其将规范变形Autiachoder（VAE）与我们最近开发的基于流的生成模型相结合，称为Krnet。 VAE用作尺寸减少技术以捕获潜伏空间，并且Krnet用于模拟潜在变量的分布。在数据和潜在变量之间使用线性模型，我们表明VAE-Krnet可以比规范VAE更有效且鲁棒。 VAE-KRNET可以用作密度模型，以近似数据分布或任意概率密度函数（PDF）已知到常数。 VAE-KRNET在维度方面灵活。当尺寸的数量相对较小时，Krnet可以有效地近似于原始随机变量的分布。对于高维病例，我们可以使用VAE-Krnet合并尺寸减少。 VAE-Krnet的一个重要应用是用于后部分布的近似的变分贝叶。变分贝叶斯方法通常基于模型和后部之间的Kullback-Leibler（KL）发散的最小化。对于高尺寸分布，由于维度的诅咒构建精确的密度模型是非常具有挑战性的，其中通常引入额外的假设以效率。例如，经典平均场方法假设尺寸之间的相互独立性，这通常会导致由于过度简化而产生低估的方差。为了减轻这个问题，我们包括丢失潜在随机变量和原始随机变量之间的相互信息的最大化，这有助于从低密度的区域保持更多信息，使得方差估计得到改善。

In this paper we explore the task of modeling (semi) structured object sequences; in particular we focus our attention on the problem of developing a structure-aware input representation for such sequences. In such sequences, we assume that each structured object is represented by a set of key-value pairs which encode the attributes of the structured object. Given a universe of keys, a sequence of structured objects can then be viewed as an evolution of the values for each key, over time. We encode and construct a sequential representation using the values for a particular key (Temporal Value Modeling - TVM) and then self-attend over the set of key-conditioned value sequences to a create a representation of the structured object sequence (Key Aggregation - KA). We pre-train and fine-tune the two components independently and present an innovative training schedule that interleaves the training of both modules with shared attention heads. We find that this iterative two part-training results in better performance than a unified network with hierarchical encoding as well as over, other methods that use a {\em record-view} representation of the sequence \cite{de2021transformers4rec} or a simple {\em flattened} representation of the sequence. We conduct experiments using real-world data to demonstrate the advantage of interleaving TVM-KA on multiple tasks and detailed ablation studies motivating our modeling choices. We find that our approach performs better than flattening sequence objects and also allows us to operate on significantly larger sequences than existing methods.

Face Anti-spoofing (FAS) is essential to secure face recognition systems from various physical attacks. However, recent research generally focuses on short-distance applications (i.e., phone unlocking) while lacking consideration of long-distance scenes (i.e., surveillance security checks). In order to promote relevant research and fill this gap in the community, we collect a large-scale Surveillance High-Fidelity Mask (SuHiFiMask) dataset captured under 40 surveillance scenes, which has 101 subjects from different age groups with 232 3D attacks (high-fidelity masks), 200 2D attacks (posters, portraits, and screens), and 2 adversarial attacks. In this scene, low image resolution and noise interference are new challenges faced in surveillance FAS. Together with the SuHiFiMask dataset, we propose a Contrastive Quality-Invariance Learning (CQIL) network to alleviate the performance degradation caused by image quality from three aspects: (1) An Image Quality Variable module (IQV) is introduced to recover image information associated with discrimination by combining the super-resolution network. (2) Using generated sample pairs to simulate quality variance distributions to help contrastive learning strategies obtain robust feature representation under quality variation. (3) A Separate Quality Network (SQN) is designed to learn discriminative features independent of image quality. Finally, a large number of experiments verify the quality of the SuHiFiMask dataset and the superiority of the proposed CQIL.

Temporal sentence grounding (TSG) aims to identify the temporal boundary of a specific segment from an untrimmed video by a sentence query. All existing works first utilize a sparse sampling strategy to extract a fixed number of video frames and then conduct multi-modal interactions with query sentence for reasoning. However, we argue that these methods have overlooked two indispensable issues: 1) Boundary-bias: The annotated target segment generally refers to two specific frames as corresponding start and end timestamps. The video downsampling process may lose these two frames and take the adjacent irrelevant frames as new boundaries. 2) Reasoning-bias: Such incorrect new boundary frames also lead to the reasoning bias during frame-query interaction, reducing the generalization ability of model. To alleviate above limitations, in this paper, we propose a novel Siamese Sampling and Reasoning Network (SSRN) for TSG, which introduces a siamese sampling mechanism to generate additional contextual frames to enrich and refine the new boundaries. Specifically, a reasoning strategy is developed to learn the inter-relationship among these frames and generate soft labels on boundaries for more accurate frame-query reasoning. Such mechanism is also able to supplement the absent consecutive visual semantics to the sampled sparse frames for fine-grained activity understanding. Extensive experiments demonstrate the effectiveness of SSRN on three challenging datasets.

Unlike traditional distributed machine learning, federated learning stores data locally for training and then aggregates the models on the server, which solves the data security problem that may arise in traditional distributed machine learning. However, during the training process, the transmission of model parameters can impose a significant load on the network bandwidth. It has been pointed out that the vast majority of model parameters are redundant during model parameter transmission. In this paper, we explore the data distribution law of selected partial model parameters on this basis, and propose a deep hierarchical quantization compression algorithm, which further compresses the model and reduces the network load brought by data transmission through the hierarchical quantization of model parameters. And we adopt a dynamic sampling strategy for the selection of clients to accelerate the convergence of the model. Experimental results on different public datasets demonstrate the effectiveness of our algorithm.

In the new era of personalization, learning the heterogeneous treatment effect (HTE) becomes an inevitable trend with numerous applications. Yet, most existing HTE estimation methods focus on independently and identically distributed observations and cannot handle the non-stationarity and temporal dependency in the common panel data setting. The treatment evaluators developed for panel data, on the other hand, typically ignore the individualized information. To fill the gap, in this paper, we initialize the study of HTE estimation in panel data. Under different assumptions for HTE identifiability, we propose the corresponding heterogeneous one-side and two-side synthetic learner, namely H1SL and H2SL, by leveraging the state-of-the-art HTE estimator for non-panel data and generalizing the synthetic control method that allows flexible data generating process. We establish the convergence rates of the proposed estimators. The superior performance of the proposed methods over existing ones is demonstrated by extensive numerical studies.

Latent factor model estimation typically relies on either using domain knowledge to manually pick several observed covariates as factor proxies, or purely conducting multivariate analysis such as principal component analysis. However, the former approach may suffer from the bias while the latter can not incorporate additional information. We propose to bridge these two approaches while allowing the number of factor proxies to diverge, and hence make the latent factor model estimation robust, flexible, and statistically more accurate. As a bonus, the number of factors is also allowed to grow. At the heart of our method is a penalized reduced rank regression to combine information. To further deal with heavy-tailed data, a computationally attractive penalized robust reduced rank regression method is proposed. We establish faster rates of convergence compared with the benchmark. Extensive simulations and real examples are used to illustrate the advantages.

Our situated environment is full of uncertainty and highly dynamic, thus hindering the widespread adoption of machine-led Intelligent Decision-Making (IDM) in real world scenarios. This means IDM should have the capability of continuously learning new skills and efficiently generalizing across wider applications. IDM benefits from any new approaches and theoretical breakthroughs that exhibit Artificial General Intelligence (AGI) breaking the barriers between tasks and applications. Recent research has well-examined neural architecture, Transformer, as a backbone foundation model and its generalization to various tasks, including computer vision, natural language processing, and reinforcement learning. We therefore argue that a foundation decision model (FDM) can be established by formulating various decision-making tasks as a sequence decoding task using the Transformer architecture; this would be a promising solution to advance the applications of IDM in more complex real world tasks. In this paper, we elaborate on how a foundation decision model improves the efficiency and generalization of IDM. We also discuss potential applications of a FDM in multi-agent game AI, production scheduling, and robotics tasks. Finally, through a case study, we demonstrate our realization of the FDM, DigitalBrain (DB1) with 1.2 billion parameters, which achieves human-level performance over 453 tasks, including text generation, images caption, video games playing, robotic control, and traveling salesman problems. As a foundation decision model, DB1 would be a baby step towards more autonomous and efficient real world IDM applications.