受欢迎的LSPE（$ \ lambda $）策略评估算法被重新审视，以导出从一段时间内提供高概率性能保证的浓度。

使用Martingale浓度不平等，浓度界限为“从时间到$ n_0 $ on”是针对带有承包图的随机近似算法以及Martingale差异和Markov噪声的。这些应用于增强学习算法，尤其是异步Q学习和TD（0）。

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.

Of late, insurance fraud detection has assumed immense significance owing to the huge financial & reputational losses fraud entails and the phenomenal success of the fraud detection techniques. Insurance is majorly divided into two categories: (i) Life and (ii) Non-life. Non-life insurance in turn includes health insurance and auto insurance among other things. In either of the categories, the fraud detection techniques should be designed in such a way that they capture as many fraudulent transactions as possible. Owing to the rarity of fraudulent transactions, in this paper, we propose a chaotic variational autoencoder (C-VAE to perform one-class classification (OCC) on genuine transactions. Here, we employed the logistic chaotic map to generate random noise in the latent space. The effectiveness of C-VAE is demonstrated on the health insurance fraud and auto insurance datasets. We considered vanilla Variational Auto Encoder (VAE) as the baseline. It is observed that C-VAE outperformed VAE in both datasets. C-VAE achieved a classification rate of 77.9% and 87.25% in health and automobile insurance datasets respectively. Further, the t-test conducted at 1% level of significance and 18 degrees of freedom infers that C-VAE is statistically significant than the VAE.

语言模型既展示了定量的改进，又展示了新的定性功能，随着规模的增加。尽管它们具有潜在的变革性影响，但这些新能力的特征却很差。为了为未来的研究提供信息，为破坏性的新模型能力做准备，并改善社会有害的效果，至关重要的是，我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战，我们介绍了超越模仿游戏基准（Big Bench）。 Big Bench目前由204个任务组成，由132家机构的442位作者贡献。任务主题是多样的，从语言学，儿童发展，数学，常识性推理，生物学，物理学，社会偏见，软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号，Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为，跨越了数百万到数十亿个参数。此外，一个人类专家评估者团队执行了所有任务，以提供强大的基准。研究结果包括：模型性能和校准都随规模改善，但绝对的术语（以及与评估者的性能相比）；在模型类中的性能非常相似，尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分，而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标；社交偏见通常会随着含糊不清的环境而随着规模而增加，但这可以通过提示来改善。

低功率边缘-AI功能对于支持元视野的设备扩展现实（XR）应用至关重要。在这项工作中，我们研究了两个代表性的XR工作负载：（i）手动检测和（ii）眼睛分割，用于硬件设计空间探索。对于这两种应用，我们都会训练深层神经网络，并分析量化和硬件特定瓶颈的影响。通过模拟，我们评估了CPU和两个收缩推理加速器实现。接下来，我们将这些硬件解决方案与先进的技术节点进行比较。评估了将最新的新兴非易失性记忆技术（STT/SOT/VGSOT MRAM）集成到XR-AI推论管道中的影响。我们发现，可以通过在7nm节点的设计中引入非挥发性记忆来实现手部检测（IPS = 40）和眼部分割（IPS = 6）的显着能源益处（IPS = 40）（IPS = 6）。 （推断每秒）。此外，由于MRAM与传统的SRAM相比，由于MRAM的较小形式，我们可以大大减少面积（> = 30％）。

我们得出了基于等效路径问题的平均成本决策过程的Q学习算法的浓度，并将其与基于相对价值迭代的替代方案进行比较。

医疗人工智能（AI）的最新进展已提供了可以达到临床专家水平绩效的系统。但是，当在与训练环境不同的临床环境中评估时，这种系统往往会证明次优的“分布式”性能。一种常见的缓解策略是使用特定地点数据为每个临床环境开发单独的系统[1]。但是，这很快变得不切实际，因为医疗数据很耗时，可以注释且昂贵[2]。因此，“数据有效概括”的问题给医学AI开发带来了持续的困难。尽管代表性学习的进展显示出希望，但并未对其好处进行严格的研究，特别是用于分布的设置。为了应对这些挑战，我们提出了RESEDIS，这是一种统一的代表学习策略，以提高医学成像AI的鲁棒性和数据效率。雷雷迪斯使用大规模监督转移学习与自我监督学习的通用组合，几乎不需要特定于任务的自定义。我们研究各种医学成像任务，并使用回顾性数据模拟三个现实的应用程序场景。 RESEDIS表现出明显改善的分布性能，而在强有力的基线上，诊断准确性相对相对提高了11.5％。更重要的是，我们的策略会导致对医学成像AI的强大数据有效的概括，并使用跨任务的1％至33％的重新培训数据匹配强有力的监督基线。这些结果表明，Repedis可以显着加速医学成像AI开发的生命周期，从而为医学成像AI提供了重要的一步，以产生广泛的影响。

本文涉及由马尔可夫噪声驱动的随机近似的收敛和渐近统计：$$ \ theta_ {n + 1} = \ theta_n + \ alpha_ {n + 1} f（\ theta_n，\ phi_ {n + 1}）\， ，\ quad n \ ge 0，$$，其中每个$ \ theta_n \ in \ re ^ d $，$ \ {\ phi_n \} $是一般状态空间x上的马尔可夫链，静止分配$ \ pi $和$ f：\ re ^ d \ times \ text {x} \ to \ re ^ d $。除了在$ f $的标准lipschitz边界，以及消失的步骤大小序列$ \ {\ alpha_n \ \} $的条件外，假设相关ode是全局渐近稳定的静止点表示$ \ theta ^ * $ ，其中$ \ bar f（\ theta）= e [f（\ theta，\ phi）] $ with $ \ phi \ sim \ pi $。而且，ode @ $ \ infty $ virect with advoore字段，$$ \ bar f_ \ idty（\ theta）：= \ lim_ {r \ to \ infty} r ^ { - 1} \ bar f（r \ theta）\ ,, \ qquad \ theta \ in \ re ^ d，$$是渐近稳定的。主要贡献总结如下：（i）如果$ \ phi $是几何ergodic，则序列$ \ theta $是融合的，并且在$ f $兼容兼容的界限。剩余的结果是在马尔可夫链的更强大假设下建立：Donsker-varadhan Lyapunov漂移条件的稍微弱版本（DV3）。 （ii）为联合过程$ \ {\ theta_n，\ phi_n \} $构建Lyapunov函数，这意味着$ \ {\ theta_n \} $ in $ l_4 $的融合。 （iii）建立了功能性CLT，以及归一化误差$ z_n：=（\ theta_n- \ theta ^ *）/ \ sqrt {\ alpha_n} $的常规一维CLT。时刻界限结合了CLT暗示了归一化协方差的收敛，$$ \ lim_ {n \ to \ infty} e [z_n z_n ^ t] = \ sigma_ \ theta，$$在$ \ sigma_ \ theta $ where asbptotic协方差出现在CLT中。 （iv）提供了一个例子，其中马尔可夫链$ \ phi $是几何ergodic，但它不满足（dv3）。虽然算法收敛，但第二个时刻是无限的。

Designing experiments often requires balancing between learning about the true treatment effects and earning from allocating more samples to the superior treatment. While optimal algorithms for the Multi-Armed Bandit Problem (MABP) provide allocation policies that optimally balance learning and earning, they tend to be computationally expensive. The Gittins Index (GI) is a solution to the MABP that can simultaneously attain optimality and computationally efficiency goals, and it has been recently used in experiments with Bernoulli and Gaussian rewards. For the first time, we present a modification of the GI rule that can be used in experiments with exponentially-distributed rewards. We report its performance in simulated 2- armed and 3-armed experiments. Compared to traditional non-adaptive designs, our novel GI modified design shows operating characteristics comparable in learning (e.g. statistical power) but substantially better in earning (e.g. direct benefits). This illustrates the potential that designs using a GI approach to allocate participants have to improve participant benefits, increase efficiencies, and reduce experimental costs in adaptive multi-armed experiments with exponential rewards.