通过提供前所未有的计算资源访问，云计算能够在机器学习等技术中快速增长，其计算需求产生了高能源成本和相应的碳足迹。结果，最近的奖学金呼吁更好地估计AI的温室气体影响：当今的数据科学家无法轻松或可靠地访问该信息的测量，从而排除了可行策略的发展。向用户提供有关软件碳强度的信息的云提供商是一种基本的垫脚石，以最大程度地减少排放。在本文中，我们提供了一个测量软件碳强度的框架，并建议通过使用每个能量单元使用基于位置和特定时间的边际排放数据来测量运行碳排放。我们为一组自然语言处理和计算机视觉的现代模型提供了操作软件强度的测量，以及各种模型尺寸，包括预处理61亿个参数语言模型。然后，我们评估了一套用于减少Microsoft Azure Cloud Compute平台排放的方法套件：使用不同地理区域中的云实例，在一天中的不同时间使用云实例，并在边际碳强度高于某个阈值时动态暂停云实例。我们证实了先前的结果，即数据中心的地理区域在给定云实例的碳强度中起着重要作用，并发现选择合适的区域可能具有最大的运营排放减少影响。我们还表明，一天中的时间对操作软件碳强度有显着影响。最后，我们最终提出了有关机器学习从业人员如何使用软件碳强度信息来减少环境影响的建议。

A Digital Twin (DT) is a simulation of a physical system that provides information to make decisions that add economic, social or commercial value. The behaviour of a physical system changes over time, a DT must therefore be continually updated with data from the physical systems to reflect its changing behaviour. For resource-constrained systems, updating a DT is non-trivial because of challenges such as on-board learning and the off-board data transfer. This paper presents a framework for updating data-driven DTs of resource-constrained systems geared towards system health monitoring. The proposed solution consists of: (1) an on-board system running a light-weight DT allowing the prioritisation and parsimonious transfer of data generated by the physical system; and (2) off-board robust updating of the DT and detection of anomalous behaviours. Two case studies are considered using a production gas turbine engine system to demonstrate the digital representation accuracy for real-world, time-varying physical systems.

Rankings are widely collected in various real-life scenarios, leading to the leakage of personal information such as users' preferences on videos or news. To protect rankings, existing works mainly develop privacy protection on a single ranking within a set of ranking or pairwise comparisons of a ranking under the $\epsilon$-differential privacy. This paper proposes a novel notion called $\epsilon$-ranking differential privacy for protecting ranks. We establish the connection between the Mallows model (Mallows, 1957) and the proposed $\epsilon$-ranking differential privacy. This allows us to develop a multistage ranking algorithm to generate synthetic rankings while satisfying the developed $\epsilon$-ranking differential privacy. Theoretical results regarding the utility of synthetic rankings in the downstream tasks, including the inference attack and the personalized ranking tasks, are established. For the inference attack, we quantify how $\epsilon$ affects the estimation of the true ranking based on synthetic rankings. For the personalized ranking task, we consider varying privacy preferences among users and quantify how their privacy preferences affect the consistency in estimating the optimal ranking function. Extensive numerical experiments are carried out to verify the theoretical results and demonstrate the effectiveness of the proposed synthetic ranking algorithm.

Contextual bandit has been widely used for sequential decision-making based on the current contextual information and historical feedback data. In modern applications, such context format can be rich and can often be formulated as a matrix. Moreover, while existing bandit algorithms mainly focused on reward-maximization, less attention has been paid to the statistical inference. To fill in these gaps, in this work we consider a matrix contextual bandit framework where the true model parameter is a low-rank matrix, and propose a fully online procedure to simultaneously make sequential decision-making and conduct statistical inference. The low-rank structure of the model parameter and the adaptivity nature of the data collection process makes this difficult: standard low-rank estimators are not fully online and are biased, while existing inference approaches in bandit algorithms fail to account for the low-rankness and are also biased. To address these, we introduce a new online doubly-debiasing inference procedure to simultaneously handle both sources of bias. In theory, we establish the asymptotic normality of the proposed online doubly-debiased estimator and prove the validity of the constructed confidence interval. Our inference results are built upon a newly developed low-rank stochastic gradient descent estimator and its non-asymptotic convergence result, which is also of independent interest.

The reward hypothesis posits that, "all of what we mean by goals and purposes can be well thought of as maximization of the expected value of the cumulative sum of a received scalar signal (reward)." We aim to fully settle this hypothesis. This will not conclude with a simple affirmation or refutation, but rather specify completely the implicit requirements on goals and purposes under which the hypothesis holds.

The coverage of different stakeholders mentioned in the news articles significantly impacts the slant or polarity detection of the concerned news publishers. For instance, the pro-government media outlets would give more coverage to the government stakeholders to increase their accessibility to the news audiences. In contrast, the anti-government news agencies would focus more on the views of the opponent stakeholders to inform the readers about the shortcomings of government policies. In this paper, we address the problem of stakeholder extraction from news articles and thereby determine the inherent bias present in news reporting. Identifying potential stakeholders in multi-topic news scenarios is challenging because each news topic has different stakeholders. The research presented in this paper utilizes both contextual information and external knowledge to identify the topic-specific stakeholders from news articles. We also apply a sequential incremental clustering algorithm to group the entities with similar stakeholder types. We carried out all our experiments on news articles on four Indian government policies published by numerous national and international news agencies. We also further generalize our system, and the experimental results show that the proposed model can be extended to other news topics.

The primary aim of this research was to find a model that best predicts which fallen angel bonds would either potentially rise up back to investment grade bonds and which ones would fall into bankruptcy. To implement the solution, we thought that the ideal method would be to create an optimal machine learning model that could predict bankruptcies. Among the many machine learning models out there we decided to pick four classification methods: logistic regression, KNN, SVM, and NN. We also utilized an automated methods of Google Cloud's machine learning. The results of our model comparisons showed that the models did not predict bankruptcies very well on the original data set with the exception of Google Cloud's machine learning having a high precision score. However, our over-sampled and feature selection data set did perform very well. This could likely be due to the model being over-fitted to match the narrative of the over-sampled data (as in, it does not accurately predict data outside of this data set quite well). Therefore, we were not able to create a model that we are confident that would predict bankruptcies. However, we were able to find value out of this project in two key ways. The first is that Google Cloud's machine learning model in every metric and in every data set either outperformed or performed on par with the other models. The second is that we found that utilizing feature selection did not reduce predictive power that much. This means that we can reduce the amount of data to collect for future experimentation regarding predicting bankruptcies.

We study the learning dynamics of self-predictive learning for reinforcement learning, a family of algorithms that learn representations by minimizing the prediction error of their own future latent representations. Despite its recent empirical success, such algorithms have an apparent defect: trivial representations (such as constants) minimize the prediction error, yet it is obviously undesirable to converge to such solutions. Our central insight is that careful designs of the optimization dynamics are critical to learning meaningful representations. We identify that a faster paced optimization of the predictor and semi-gradient updates on the representation, are crucial to preventing the representation collapse. Then in an idealized setup, we show self-predictive learning dynamics carries out spectral decomposition on the state transition matrix, effectively capturing information of the transition dynamics. Building on the theoretical insights, we propose bidirectional self-predictive learning, a novel self-predictive algorithm that learns two representations simultaneously. We examine the robustness of our theoretical insights with a number of small-scale experiments and showcase the promise of the novel representation learning algorithm with large-scale experiments.

As an autonomous system performs a task, it should maintain a calibrated estimate of the probability that it will achieve the user's goal. If that probability falls below some desired level, it should alert the user so that appropriate interventions can be made. This paper considers settings where the user's goal is specified as a target interval for a real-valued performance summary, such as the cumulative reward, measured at a fixed horizon $H$. At each time $t \in \{0, \ldots, H-1\}$, our method produces a calibrated estimate of the probability that the final cumulative reward will fall within a user-specified target interval $[y^-,y^+].$ Using this estimate, the autonomous system can raise an alarm if the probability drops below a specified threshold. We compute the probability estimates by inverting conformal prediction. Our starting point is the Conformalized Quantile Regression (CQR) method of Romano et al., which applies split-conformal prediction to the results of quantile regression. CQR is not invertible, but by using the conditional cumulative distribution function (CDF) as the non-conformity measure, we show how to obtain an invertible modification that we call \textbf{P}robability-space \textbf{C}onformalized \textbf{Q}uantile \textbf{R}egression (PCQR). Like CQR, PCQR produces well-calibrated conditional prediction intervals with finite-sample marginal guarantees. By inverting PCQR, we obtain marginal guarantees for the probability that the cumulative reward of an autonomous system will fall within an arbitrary user-specified target intervals. Experiments on two domains confirm that these probabilities are well-calibrated.

Diffusion models have quickly become the go-to paradigm for generative modelling of perceptual signals (such as images and sound) through iterative refinement. Their success hinges on the fact that the underlying physical phenomena are continuous. For inherently discrete and categorical data such as language, various diffusion-inspired alternatives have been proposed. However, the continuous nature of diffusion models conveys many benefits, and in this work we endeavour to preserve it. We propose CDCD, a framework for modelling categorical data with diffusion models that are continuous both in time and input space. We demonstrate its efficacy on several language modelling tasks.