Non-linear state-space models, also known as general hidden Markov models, are ubiquitous in statistical machine learning, being the most classical generative models for serial data and sequences in general. The particle-based, rapid incremental smoother PaRIS is a sequential Monte Carlo (SMC) technique allowing for efficient online approximation of expectations of additive functionals under the smoothing distribution in these models. Such expectations appear naturally in several learning contexts, such as likelihood estimation (MLE) and Markov score climbing (MSC). PARIS has linear computational complexity, limited memory requirements and comes with non-asymptotic bounds, convergence results and stability guarantees. Still, being based on self-normalised importance sampling, the PaRIS estimator is biased. Our first contribution is to design a novel additive smoothing algorithm, the Parisian particle Gibbs PPG sampler, which can be viewed as a PaRIS algorithm driven by conditional SMC moves, resulting in bias-reduced estimates of the targeted quantities. We substantiate the PPG algorithm with theoretical results, including new bounds on bias and variance as well as deviation inequalities. Our second contribution is to apply PPG in a learning framework, covering MLE and MSC as special examples. In this context, we establish, under standard assumptions, non-asymptotic bounds highlighting the value of bias reduction and the implicit Rao--Blackwellization of PPG. These are the first non-asymptotic results of this kind in this setting. We illustrate our theoretical results with numerical experiments supporting our claims.

重要性采样（IS）是一种使用来自建议分布和相关重要性权重的独立样本在目标分布下近似期望的方法。在许多应用中，只有直到归一化常数才知道目标分布，在这种情况下，可以使用自称为（SNIS）。虽然自我正态化的使用可能会对估计量的分散产生积极影响，但它引入了偏见。在这项工作中，我们提出了一种新方法BR-SNIS，其复杂性与SNI的复杂性基本相同，并且显着降低了偏见而不增加差异。这种方法是一种包装器，从某种意义上说，它使用了与SNIS相同的建议样本和重要性权重，但巧妙地使用了迭代采样（ISIR）重新采样（ISIR）来形成估算器的偏置版本。我们为提出的算法提供了严格的理论结果，包括新的偏见，方差和高概率界限，这些算法由数值示例进行了说明。

我们提出了一种新的非参数混合物模型，用于多变量回归问题，灵感来自概率K-Nearthimest邻居算法。使用有条件指定的模型，对样本外输入的预测基于与每个观察到的数据点的相似性，从而产生高斯混合物表示的预测分布。在混合物组件的参数以及距离度量标准的参数上，使用平均场变化贝叶斯算法进行后推断，并具有基于随机梯度的优化过程。在与数据大小相比，输入 - 输出关系很复杂，预测分布可能偏向或多模式的情况下，输入相对较高的尺寸，该方法尤其有利。对五个数据集进行的计算研究，其中两个是合成生成的，这说明了我们的高维输入的专家混合物方法的明显优势，在验证指标和视觉检查方面都优于竞争者模型。

We introduce camouflaged data poisoning attacks, a new attack vector that arises in the context of machine unlearning and other settings when model retraining may be induced. An adversary first adds a few carefully crafted points to the training dataset such that the impact on the model's predictions is minimal. The adversary subsequently triggers a request to remove a subset of the introduced points at which point the attack is unleashed and the model's predictions are negatively affected. In particular, we consider clean-label targeted attacks (in which the goal is to cause the model to misclassify a specific test point) on datasets including CIFAR-10, Imagenette, and Imagewoof. This attack is realized by constructing camouflage datapoints that mask the effect of a poisoned dataset.

While dense retrieval has been shown effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance label is available. In this paper, we recognize the difficulty of zero-shot learning and encoding relevance. Instead, we propose to pivot through Hypothetical Document Embeddings~(HyDE). Given a query, HyDE first zero-shot instructs an instruction-following language model (e.g. InstructGPT) to generate a hypothetical document. The document captures relevance patterns but is unreal and may contain false details. Then, an unsupervised contrastively learned encoder~(e.g. Contriever) encodes the document into an embedding vector. This vector identifies a neighborhood in the corpus embedding space, where similar real documents are retrieved based on vector similarity. This second step ground the generated document to the actual corpus, with the encoder's dense bottleneck filtering out the incorrect details. Our experiments show that HyDE significantly outperforms the state-of-the-art unsupervised dense retriever Contriever and shows strong performance comparable to fine-tuned retrievers, across various tasks (e.g. web search, QA, fact verification) and languages~(e.g. sw, ko, ja).

Deep neural networks (DNNs) are often used for text classification tasks as they usually achieve high levels of accuracy. However, DNNs can be computationally intensive with billions of parameters and large amounts of labeled data, which can make them expensive to use, to optimize and to transfer to out-of-distribution (OOD) cases in practice. In this paper, we propose a non-parametric alternative to DNNs that's easy, light-weight and universal in text classification: a combination of a simple compressor like gzip with a $k$-nearest-neighbor classifier. Without any training, pre-training or fine-tuning, our method achieves results that are competitive with non-pretrained deep learning methods on six in-distributed datasets. It even outperforms BERT on all five OOD datasets, including four low-resource languages. Our method also performs particularly well in few-shot settings where labeled data are too scarce for DNNs to achieve a satisfying accuracy.

As language models (LMs) scale, they develop many novel behaviors, good and bad, exacerbating the need to evaluate how they behave. Prior work creates evaluations with crowdwork (which is time-consuming and expensive) or existing data sources (which are not always available). Here, we automatically generate evaluations with LMs. We explore approaches with varying amounts of human effort, from instructing LMs to write yes/no questions to making complex Winogender schemas with multiple stages of LM-based generation and filtering. Crowdworkers rate the examples as highly relevant and agree with 90-100% of labels, sometimes more so than corresponding human-written datasets. We generate 154 datasets and discover new cases of inverse scaling where LMs get worse with size. Larger LMs repeat back a dialog user's preferred answer ("sycophancy") and express greater desire to pursue concerning goals like resource acquisition and goal preservation. We also find some of the first examples of inverse scaling in RL from Human Feedback (RLHF), where more RLHF makes LMs worse. For example, RLHF makes LMs express stronger political views (on gun rights and immigration) and a greater desire to avoid shut down. Overall, LM-written evaluations are high-quality and let us quickly discover many novel LM behaviors.

An enhanced geothermal system is essential to provide sustainable and long-term geothermal energy supplies and reduce carbon emissions. Optimal well-control scheme for effective heat extraction and improved heat sweep efficiency plays a significant role in geothermal development. However, the optimization performance of most existing optimization algorithms deteriorates as dimension increases. To solve this issue, a novel surrogate-assisted level-based learning evolutionary search algorithm (SLLES) is proposed for heat extraction optimization of enhanced geothermal system. SLLES consists of classifier-assisted level-based learning pre-screen part and local evolutionary search part. The cooperation of the two parts has realized the balance between the exploration and exploitation during the optimization process. After iteratively sampling from the design space, the robustness and effectiveness of the algorithm are proven to be improved significantly. To the best of our knowledge, the proposed algorithm holds state-of-the-art simulation-involved optimization framework. Comparative experiments have been conducted on benchmark functions, a two-dimensional fractured reservoir and a three-dimensional enhanced geothermal system. The proposed algorithm outperforms other five state-of-the-art surrogate-assisted algorithms on all selected benchmark functions. The results on the two heat extraction cases also demonstrate that SLLES can achieve superior optimization performance compared with traditional evolutionary algorithm and other surrogate-assisted algorithms. This work lays a solid basis for efficient geothermal extraction of enhanced geothermal system and sheds light on the model management strategies of data-driven optimization in the areas of energy exploitation.

As AI systems become more capable, we would like to enlist their help to supervise other AIs. We experiment with methods for training a harmless AI assistant through self-improvement, without any human labels identifying harmful outputs. The only human oversight is provided through a list of rules or principles, and so we refer to the method as 'Constitutional AI'. The process involves both a supervised learning and a reinforcement learning phase. In the supervised phase we sample from an initial model, then generate self-critiques and revisions, and then finetune the original model on revised responses. In the RL phase, we sample from the finetuned model, use a model to evaluate which of the two samples is better, and then train a preference model from this dataset of AI preferences. We then train with RL using the preference model as the reward signal, i.e. we use 'RL from AI Feedback' (RLAIF). As a result we are able to train a harmless but non-evasive AI assistant that engages with harmful queries by explaining its objections to them. Both the SL and RL methods can leverage chain-of-thought style reasoning to improve the human-judged performance and transparency of AI decision making. These methods make it possible to control AI behavior more precisely and with far fewer human labels.

The application of natural language processing (NLP) to cancer pathology reports has been focused on detecting cancer cases, largely ignoring precancerous cases. Improving the characterization of precancerous adenomas assists in developing diagnostic tests for early cancer detection and prevention, especially for colorectal cancer (CRC). Here we developed transformer-based deep neural network NLP models to perform the CRC phenotyping, with the goal of extracting precancerous lesion attributes and distinguishing cancer and precancerous cases. We achieved 0.914 macro-F1 scores for classifying patients into negative, non-advanced adenoma, advanced adenoma and CRC. We further improved the performance to 0.923 using an ensemble of classifiers for cancer status classification and lesion size named entity recognition (NER). Our results demonstrated the potential of using NLP to leverage real-world health record data to facilitate the development of diagnostic tests for early cancer prevention.