转移学习（TL）利用以前获得的知识有效地学习新任务，并且已被用于培训具有有限数量的数据的深度学习（DL）模型。当TL应用于DL时，佩带的预押（教师）模型是微调的，以构建特定域（学生）模型。这种微调依赖于DL模型可以分解到分类器和特征提取器，并且一系列研究表明，相同的特征提取器可用于培训多个任务上的分类器。此外，最近的研究提出了多种算法，可以进行微调教师模型的特征提取器，以更有效地培训学生模型。我们注意到，无论特征提取器的微调如何，学生模型的分类器都接受了特征提取器的最终输出（即倒数第二层的输出）。然而，最近的一项研究表明，跨层中的Resnet中的特征映射可能是在功能上等同的，提高要素提取器内的特征映射的可能性也可用于训练学生模型的分类器。灵感来自这项研究，我们测试了教师模型隐藏层中的特征映射，可用于提高学生模型的准确性（即，TL的效率）。具体而言，我们开发了“自适应传输学习（ATL）”，可以选择用于TL的最佳特征映射，并在几次拍摄的学习设置中测试。我们的实证评估表明，ATL可以帮助DL模型更有效地学习，特别是当可用示例有限时。

Modern statistical learning algorithms are capable of amazing flexibility, but struggle with interpretability. One possible solution is sparsity: making inference such that many of the parameters are estimated as being identically 0, which may be imposed through the use of nonsmooth penalties such as the $\ell_1$ penalty. However, the $\ell_1$ penalty introduces significant bias when high sparsity is desired. In this article, we retain the $\ell_1$ penalty, but define learnable penalty weights $\lambda_p$ endowed with hyperpriors. We start the article by investigating the optimization problem this poses, developing a proximal operator associated with the $\ell_1$ norm. We then study the theoretical properties of this variable-coefficient $\ell_1$ penalty in the context of penalized likelihood. Next, we investigate application of this penalty to Variational Bayes, developing a model we call the Sparse Bayesian Lasso which allows for behavior qualitatively like Lasso regression to be applied to arbitrary variational models. In simulation studies, this gives us the Uncertainty Quantification and low bias properties of simulation-based approaches with an order of magnitude less computation. Finally, we apply our methodology to a Bayesian lagged spatiotemporal regression model of internal displacement that occurred during the Iraqi Civil War of 2013-2017.

我们调查攻击者的效果如何，当它只从受害者的行为中学习时，没有受害者的奖励。在这项工作中，当受害者的动机未知时，我们被攻击者想要行事的情景。我们认为一个启发式方法可以使用攻击者是最大化受害者政策的熵。政策通常不会被滥用，这意味着它可以通过被动地观察受害者来提取。我们以奖励无源勘探算法的形式提供这样的策略，可以在勘探阶段最大化攻击者的熵，然后在规划阶段最大化受害者的经验熵。在我们的实验中，受害者代理商通过政策熵最大化而颠覆，暗示攻击者可能无法访问受害者的奖励成功。因此，仅基于观察行为的无奖励攻击表明，即使受害者的奖励信息受到保护，攻击者的可行性也在不了解受害者的动机。

Feature selection helps reduce data acquisition costs in ML, but the standard approach is to train models with static feature subsets. Here, we consider the dynamic feature selection (DFS) problem where a model sequentially queries features based on the presently available information. DFS is often addressed with reinforcement learning (RL), but we explore a simpler approach of greedily selecting features based on their conditional mutual information. This method is theoretically appealing but requires oracle access to the data distribution, so we develop a learning approach based on amortized optimization. The proposed method is shown to recover the greedy policy when trained to optimality and outperforms numerous existing feature selection methods in our experiments, thus validating it as a simple but powerful approach for this problem.

We derive a set of causal deep neural networks whose architectures are a consequence of tensor (multilinear) factor analysis. Forward causal questions are addressed with a neural network architecture composed of causal capsules and a tensor transformer. The former estimate a set of latent variables that represent the causal factors, and the latter governs their interaction. Causal capsules and tensor transformers may be implemented using shallow autoencoders, but for a scalable architecture we employ block algebra and derive a deep neural network composed of a hierarchy of autoencoders. An interleaved kernel hierarchy preprocesses the data resulting in a hierarchy of kernel tensor factor models. Inverse causal questions are addressed with a neural network that implements multilinear projection and estimates the causes of effects. As an alternative to aggressive bottleneck dimension reduction or regularized regression that may camouflage an inherently underdetermined inverse problem, we prescribe modeling different aspects of the mechanism of data formation with piecewise tensor models whose multilinear projections are well-defined and produce multiple candidate solutions. Our forward and inverse neural network architectures are suitable for asynchronous parallel computation.

We demonstrate how efficient autonomous drone swarms can be in detecting and tracking occluded targets in densely forested areas, such as lost people during search and rescue missions. Exploration and optimization of local viewing conditions, such as occlusion density and target view obliqueness, provide much faster and much more reliable results than previous, blind sampling strategies that are based on pre-defined waypoints. An adapted real-time particle swarm optimization and a new objective function are presented that are able to deal with dynamic and highly random through-foliage conditions. Synthetic aperture sensing is our fundamental sampling principle, and drone swarms are employed to approximate the optical signals of extremely wide and adaptable airborne lenses.

Sequential testing, always-valid $p$-values, and confidence sequences promise flexible statistical inference and on-the-fly decision making. However, unlike fixed-$n$ inference based on asymptotic normality, existing sequential tests either make parametric assumptions and end up under-covering/over-rejecting when these fail or use non-parametric but conservative concentration inequalities and end up over-covering/under-rejecting. To circumvent these issues, we sidestep exact at-least-$\alpha$ coverage and focus on asymptotically exact coverage and asymptotic optimality. That is, we seek sequential tests whose probability of ever rejecting a true hypothesis asymptotically approaches $\alpha$ and whose expected time to reject a false hypothesis approaches a lower bound on all tests with asymptotic coverage at least $\alpha$, both under an appropriate asymptotic regime. We permit observations to be both non-parametric and dependent and focus on testing whether the observations form a martingale difference sequence. We propose the universal sequential probability ratio test (uSPRT), a slight modification to the normal-mixture sequential probability ratio test, where we add a burn-in period and adjust thresholds accordingly. We show that even in this very general setting, the uSPRT is asymptotically optimal under mild generic conditions. We apply the results to stabilized estimating equations to test means, treatment effects, etc. Our results also provide corresponding guarantees for the implied confidence sequences. Numerical simulations verify our guarantees and the benefits of the uSPRT over alternatives.

User equipment is one of the main bottlenecks facing the gaming industry nowadays. The extremely realistic games which are currently available trigger high computational requirements of the user devices to run games. As a consequence, the game industry has proposed the concept of Cloud Gaming, a paradigm that improves gaming experience in reduced hardware devices. To this end, games are hosted on remote servers, relegating users' devices to play only the role of a peripheral for interacting with the game. However, this paradigm overloads the communication links connecting the users with the cloud. Therefore, service experience becomes highly dependent on network connectivity. To overcome this, Cloud Gaming will be boosted by the promised performance of 5G and future 6G networks, together with the flexibility provided by mobility in multi-RAT scenarios, such as WiFi. In this scope, the present work proposes a framework for measuring and estimating the main E2E metrics of the Cloud Gaming service, namely KQIs. In addition, different machine learning techniques are assessed for predicting KQIs related to Cloud Gaming user's experience. To this end, the main key quality indicators (KQIs) of the service such as input lag, freeze percent or perceived video frame rate are collected in a real environment. Based on these, results show that machine learning techniques provide a good estimation of these indicators solely from network-based metrics. This is considered a valuable asset to guide the delivery of Cloud Gaming services through cellular communications networks even without access to the user's device, as it is expected for telecom operators.

Large language models (LLMs) have demonstrated impressive capabilities in natural language understanding and generation, but the quality bar for medical and clinical applications is high. Today, attempts to assess models' clinical knowledge typically rely on automated evaluations on limited benchmarks. There is no standard to evaluate model predictions and reasoning across a breadth of tasks. To address this, we present MultiMedQA, a benchmark combining six existing open question answering datasets spanning professional medical exams, research, and consumer queries; and HealthSearchQA, a new free-response dataset of medical questions searched online. We propose a framework for human evaluation of model answers along multiple axes including factuality, precision, possible harm, and bias. In addition, we evaluate PaLM (a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM, on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA, MedMCQA, PubMedQA, MMLU clinical topics), including 67.6% accuracy on MedQA (US Medical License Exam questions), surpassing prior state-of-the-art by over 17%. However, human evaluation reveals key gaps in Flan-PaLM responses. To resolve this we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, recall of knowledge, and medical reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal important limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLM models for clinical applications.

Dataset scaling, also known as normalization, is an essential preprocessing step in a machine learning pipeline. It is aimed at adjusting attributes scales in a way that they all vary within the same range. This transformation is known to improve the performance of classification models, but there are several scaling techniques to choose from, and this choice is not generally done carefully. In this paper, we execute a broad experiment comparing the impact of 5 scaling techniques on the performances of 20 classification algorithms among monolithic and ensemble models, applying them to 82 publicly available datasets with varying imbalance ratios. Results show that the choice of scaling technique matters for classification performance, and the performance difference between the best and the worst scaling technique is relevant and statistically significant in most cases. They also indicate that choosing an inadequate technique can be more detrimental to classification performance than not scaling the data at all. We also show how the performance variation of an ensemble model, considering different scaling techniques, tends to be dictated by that of its base model. Finally, we discuss the relationship between a model's sensitivity to the choice of scaling technique and its performance and provide insights into its applicability on different model deployment scenarios. Full results and source code for the experiments in this paper are available in a GitHub repository.\footnote{https://github.com/amorimlb/scaling\_matters}