Time series forecasting, which aims to predict future values based on historical data, has garnered significant attention due to its broad range of applications.

ESG Rating Disagreement and Corporate Total Factor Productivity:Inference and Prediction Zhanli Li ESG rating disagreement can lead to a decline in corporate total factor productivity When faced with ESG rating disagreement, reactive green innovation by enterprises does not lead to improvements in total factor productivity. Abstract This paper explores the relationship between ESG rating disagreement and total factor productivity (TFP) based on data from Chinese domestic ESG rating agencies and financial data of A-share listed companies in China from 2015 to 2022. On one hand, the empirical results show that ESG rating disagreement reduces corporate TFP, a conclusion that is validated through multiple robustness tests. The mechanism analysis reveals an interaction effect between green innovation and ESG rating disagreement. Specifically, in firms without ESG rating disagreement, green innovation promotes the improvement of TFP; however, in firms with disagreement, although ESG rating disagreement may drive green innovation, this does not lead to an increase in TFP. The heterogeneity analysis indicates that this effect is more pronounced in non-state-owned, asset-intensive, and lowpollution enterprises.

Packing for Supervised Fine-Tuning (SFT) in autoregressive models involves concatenating data points of varying lengths until reaching the designed maximum length to facilitate GPU processing. However, randomly concatenating data points and feeding them into an autoregressive transformer can lead to cross-contamination of sequences due to the significant difference in their subject matter. The mainstream approaches in SFT ensure that each token in the attention calculation phase only focuses on tokens within its own short sequence, without providing additional learning signals for the preceding context. To address these challenges, we introduce Threshold Filtering Packing (TFP), a method that selects samples with related context while maintaining sufficient diversity within the same pack. Our experiments show that TFP offers a simple-to-implement and scalable approach that significantly enhances SFT performance, with observed improvements of up to 7\% on GSM8K, 4\% on HumanEval, and 15\% on the adult-census-income dataset.

Entity alignment (EA), a pivotal process in integrating multi-source Knowledge Graphs (KGs) have emerged as crucial tools in diverse Knowledge Graphs (KGs), seeks to identify equivalent entity pairs fields, including information retrieval [48], question answering across these graphs. Most existing approaches regard EA as a graph [1, 4], recommendation systems [6, 38], and natural language processing representation learning task, concentrating on enhancing graph [12]. Despite their growing relevance, KGs are hindered encoders. However, the decoding process in EA - essential for effective by coverage limitations, which diminish their utility in various operation and alignment accuracy - has received limited applications. A core challenge in leveraging heterogeneous KGs lies attention and remains tailored to specific datasets and model architectures, in Entity Alignment (EA) - the process of identifying analogous necessitating both entity and additional explicit relation entities across different KGs. EA typically unfolds in two phases: embeddings. This specificity limits its applicability, particularly encoding and decoding (Figure 1). Current EA methods heavily rely in GNN-based models. To address this gap, we introduce a novel, on seed alignments for supervised learning of entity representations, generalized, and efficient decoding approach for EA, relying solely thereby encoding KGs into a unified embedding space and on entity embeddings.

We are seeking to characterize the performance and potential bottlenecks of the latest fast MCMC samplers. I see that Stan is currently using Intel TBB to parallelize the no-U-turn sampler (NUTS) across multiple chains. Do you know of any research attempted to parallelize each sampler itself within one chain. Our group at Google has been very interested in using parallel compute in HMC variants (including NUTS), particularly on accelerators (e.g., GPUs). We've been working in the deep-learning-oriented autodiff accelerator software frameworks TensorFlow and JAX, both of which are supported by our TensorFlow Probability library.

Bayesian neural networks utilize probabilistic layers that capture uncertainty over weights and activations, and are trained using Bayesian inference. Since these probabilistic layers are designed to be drop-in replacement of their deterministic counter parts, Bayesian neural networks provide a direct and natural way to extend conventional deep neural networks to support probabilistic deep learning. However, it is nontrivial to understand, design and train Bayesian neural networks due to their complexities. We discuss the essentials of Bayesian neural networks including duality (deep neural networks, probabilistic models), approximate Bayesian inference, Bayesian priors, Bayesian posteriors, and deep variational learning. We use TensorFlow Probability APIs and code examples for illustration. The main problem with Bayesian neural networks is that the architecture of deep neural networks makes it quite redundant, and costly, to account for uncertainty for a large number of successive layers. Hybrid Bayesian neural networks, which use few probabilistic layers judicially positioned in the networks, provide a practical solution.

We present MCRapper, an algorithm for efficient computation of Monte-Carlo Empirical Rademacher Averages (MCERA) for families of functions exhibiting poset (e.g., lattice) structure, such as those that arise in many pattern mining tasks. The MCERA allows us to compute upper bounds to the maximum deviation of sample means from their expectations, thus it can be used to find both statistically-significant functions (i.e., patterns) when the available data is seen as a sample from an unknown distribution, and approximations of collections of high-expectation functions (e.g., frequent patterns) when the available data is a small sample from a large dataset. This feature is a strong improvement over previously proposed solutions that could only achieve one of the two. MCRapper uses upper bounds to the discrepancy of the functions to efficiently explore and prune the search space, a technique borrowed from pattern mining itself. To show the practical use of MCRapper, we employ it to develop an algorithm TFP-R for the task of True Frequent Pattern (TFP) mining. TFP-R gives guarantees on the probability of including any false positives (precision) and exhibits higher statistical power (recall) than existing methods offering the same guarantees. We evaluate MCRapper and TFP-R and show that they outperform the state-of-the-art for their respective tasks.

Markov chain Monte Carlo (MCMC) is widely regarded as one of the most important algorithms of the 20th century. Its guarantees of asymptotic convergence, stability, and estimator-variance bounds using only unnormalized probability functions make it indispensable to probabilistic programming. In this paper, we introduce the TensorFlow Probability MCMC toolkit, and discuss some of the considerations that motivated its design.

Since the Theano team announced that it would cease development and maintenance of Theano within a year, we, the PyMC developers, have been actively discussing what to do about this. We are very excited to announce that the new version of PyMC will use TensorFlow Probability (TFP) as its backend. TensorFlow already has a very broad user base and with TFP gained a powerful new library with elegant support for probability distributions and transformations (called bijections, see the TFP paper for a full description), as well as a layer for constructing probabilistic models, called Edward2. It is clear that TFP's focus is to provide a strong foundation upon which flexible statistical models for inference and prediction can be constructed from the ground up. Its focus is not, however, to provide a high-level API which makes construction and fitting of common classes of models easy for applied users.

The "Gaussian Copula" creates a few custom Bijectors and then shows how to easily build several different copulas. For more background on distributions, see "Understanding TensorFlow Distributions Shapes." It describes how to manage shapes for sampling, batch training, and modeling events. A variational autoencoder is a machine learning model which uses one learned system to represent data in some low-dimensional space and a second learned system to restore the low-dimensional representation to what would have otherwise been the input. Because TF supports automatic differentiation, black-box variational inference is a breeze!