We consider the problem of a neural network being requested to classify images (or other inputs) without making implicit use of a "protected concept", that is a concept that should not play any role in the decision of the network. Typically these concepts include information such as gender or race, or other contextual information such as image backgrounds that might be implicitly reflected in unknown correlations with other variables, making it insufficient to simply remove them from the input features. In other words, making accurate predictions is not good enough if those predictions rely on information that should not be used: predictive performance is not the only important metric for learning systems. We apply a method developed in the context of domain adaptation to address this problem of "being right for the right reason", where we request a classifier to make a decision in a way that is entirely 'agnostic' to a given protected concept (e.g. gender, race, background etc.), even if this could be implicitly reflected in other attributes via unknown correlations. After defining the concept of an 'agnostic model', we demonstrate how the Domain-Adversarial Neural Network can remove unwanted information from a model using a gradient reversal layer.
Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity
Institute for Advanced Study（高等研究院）；Princeton University（普林斯顿大学）；University of California, San Diego（加利福尼亚大学圣地亚哥分校）；Carnegie Mellon University（卡内基梅隆大学）
本文研究确定性系统中具有函数逼近的不可知$Q$学习问题，其中最优$Q$函数可由类$\mathcal{F}$中的函数逼近，逼近误差为$δ\ge 0$ .我们提出了一种新的基于递归的算法，并表明，如果$δ= O\left(ρ/\sqrt{\dim_E}\right)$，那么可以找到最佳的政策使用$O\left(\dim_E\right)$轨迹，其中$ρ$是最佳的$Q$ -值的最佳行动和第二最佳行动和$\dim_E$之间的差距是$\mathcal{F}$的Eluder维。我们的结果有两个含义：1）结合[Du et al.，ICLR 2020]，我们的上界表明条件$δ= \widetildeΘ\left(ρ/\sqrt{\mathrm{dim}_E}\right)$对于多项式样本复杂度的算法是必要和充分的. 2)结合[Wen and Van Roy，NIPS 2013]中的下限，我们的上限表明，即使在不可知论的设置中，样本复杂度$\widetildeΘ\left(\mathrm{dim}_E\right)$也是紧密的。因此，我们解决了[Wen and Van Roy，NIPS 2013]中提出的不可知$Q$学习的开放问题。我们进一步扩展我们的算法的随机奖励设置，并获得类似的结果。
Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation
Cornell Tech（康奈尔科技）；Cornell University（康奈尔大学）；Department of Radiology, Stanford University（斯坦福大学放射科）；Oxford University（牛津大学）；Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey（视觉、语音和信号处理中心（CVSSP）、塞维利亚大学）
Sharp Structure-Agnostic Minimax Risk for Partial Linear Models
Center for Computational Science and Engineering, MIT（麻省理工学院计算科学与工程中心）；Department of Civil and Environmental Engineering, MIT（麻省理工学院土木与环境工程系）；Institute for Data, Systems, and Society, MIT（麻省理工学院数据、系统与社会研究所）
MACE: Model Agnostic Concept Extractor for Explaining Image Classification Networks
IIT Ropar（印度理工学院罗帕尔分校）
深度卷积网络在各种图像分类任务中非常成功。目前解释预训练模型预测的方法依赖于梯度信息，通常会导致突出图集中在整个前景对象上。然而，人类通常通过解剖图像并指出较小概念的存在来进行推理。最终的输出通常是这些较小概念的存在或不存在的集合。在这项工作中，我们提出了MACE：一个模型不可知的概念提取器，它可以通过更小的概念来解释卷积网络的工作。MACE框架剖析了由卷积网络为图像生成的特征图，以提取基于概念的原型解释。此外，它估计提取的概念与预训练模型预测的相关性，这是解释单个类预测所需的关键方面，在现有方法中缺失。我们使用VGG16和ResNet50 CNN架构以及Animals With Attributes 2（AWA2）和Places365等数据集验证了我们的框架。我们的实验表明，由MACE框架提取的概念增加了人类对解释的可解释性，并且忠实于底层的预训练黑盒模型。
Making informed decisions in cutting tool maintenance in milling: A KNN-based model agnostic approach
Modern Education Society’s Wadia College of Engineering（现代教育协会瓦迪亚工程学院）；COEP Technological University（COEP理工大学）；Institute of Fluid Flow Machinery, Polish Academy of Sciences（波兰科学院流体机械研究所）；Cummins College of Engineering for Women（康明斯女子工程学院）
From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?
TMLR Group, Department of Computer Science, Hong Kong Baptist University；Stanford University；Mila - Qu\'ebec AI Institute；Cooperative Medianet Innovation Center, Shanghai Jiao Tong University
