A variety of different performance metrics are commonly used in the machine learning literature for the evaluation of classification systems. Some of the most common ones for measuring quality of hard decisions are standard and balanced accuracy, standard and balanced error rate, F-beta score, and Matthews correlation coefficient (MCC). In this document, we review the definition of these and other metrics and compare them with the expected cost (EC), a metric introduced in every statistical learning course but rarely used in the machine learning literature. We show that both the standard and balanced error rates are special cases of the EC. Further, we show its relation with F-score and MCC and argue that EC is superior to these traditional metrics, being more elegant, general, and intuitive, as well as being based on basic principles from statistics. The metrics above measure the quality of hard decisions. Yet, most modern classification systems output continuous scores for the classes which we may want to evaluate directly. Metrics for measuring the quality of system scores include the area under the ROC curve, equal error rate, cross-entropy, Brier score, and Bayes EC or Bayes risk, among others. The last three metrics are special cases of a family of metrics given by the expected value of proper scoring rules (PSRs). We review the theory behind these metrics and argue that they are the most principled way to measure the quality of the posterior probabilities produced by a system. Finally, we show how to use these metrics to compute the system's calibration loss and compare this metric with the standard expected calibration error (ECE), arguing that calibration loss based on PSRs is superior to the ECE for a variety of reasons.
相關內容
We consider a causal inference model in which individuals interact in a social network and they may not comply with the assigned treatments. In particular, we suppose that the form of network interference is unknown to researchers. To estimate meaningful causal parameters in this situation, we introduce a new concept of exposure mapping, which summarizes potentially complicated spillover effects into a fixed dimensional statistic of instrumental variables. We investigate identification conditions for the intention-to-treat effects and the average treatment effects for compliers, while explicitly considering the possibility of misspecification of exposure mapping. Based on our identification results, we develop nonparametric estimation procedures via inverse probability weighting. Their asymptotic properties, including consistency and asymptotic normality, are investigated using an approximate neighborhood interference framework. For an empirical illustration, we apply our method to experimental data on the anti-conflict intervention school program. The proposed methods are readily available with the companion R package latenetwork.
Many research explore how well computers are able to examine emotions displayed by humans and use that data to perform different tasks. However, there have been very few research which evaluate the computers ability to generate emotion classification information in an attempt to help the user make decisions or perform tasks. This is a crucial area to explore as it is paramount to the two way communication between humans and computers. This research conducted an experiment to investigate the impact of different uncertainty information displays of emotion classification on the human decision making process. Results show that displaying more uncertainty information can help users to be more confident when making decisions.
Semi-supervised learning (SSL) algorithm is a setup built upon a realistic assumption that access to a large amount of labeled data is tough. In this study, we present a generalized framework, named SCAR, standing for Selecting Clean samples with Adversarial Robustness, for improving the performance of recent SSL algorithms. By adversarially attacking pre-trained models with semi-supervision, our framework shows substantial advances in classifying images. We introduce how adversarial attacks successfully select high-confident unlabeled data to be labeled with current predictions. On CIFAR10, three recent SSL algorithms with SCAR result in significantly improved image classification.
Despite speculation that recent large language models (LLMs) are likely to be used maliciously to improve the quality or scale of influence operations, uncertainty persists regarding the economic value that LLMs offer propagandists. This research constructs a model of costs facing propagandists for content generation at scale and analyzes (1) the potential savings that LLMs could offer propagandists, (2) the potential deterrent effect of monitoring controls on API-accessible LLMs, and (3) the optimal strategy for propagandists choosing between multiple private and/or open source LLMs when conducting influence operations. Primary results suggest that LLMs need only produce usable outputs with relatively low reliability (roughly 25%) to offer cost savings to propagandists, that the potential reduction in content generation costs can be quite high (up to 70% for a highly reliable model), and that monitoring capabilities have sharply limited cost imposition effects when alternative open source models are available. In addition, these results suggest that nation-states -- even those conducting many large-scale influence operations per year -- are unlikely to benefit economically from training custom LLMs specifically for use in influence operations.
Removing information from a machine learning model is a non-trivial task that requires to partially revert the training process. This task is unavoidable when sensitive data, such as credit card numbers or passwords, accidentally enter the model and need to be removed afterwards. Recently, different concepts for machine unlearning have been proposed to address this problem. While these approaches are effective in removing individual data points, they do not scale to scenarios where larger groups of features and labels need to be reverted. In this paper, we propose the first method for unlearning features and labels. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters. It enables to adapt the influence of training data on a learning model retrospectively, thereby correcting data leaks and privacy issues. For learning models with strongly convex loss functions, our method provides certified unlearning with theoretical guarantees. For models with non-convex losses, we empirically show that unlearning features and labels is effective and significantly faster than other strategies.
Recoverable algorithms tolerate failures and recoveries of processes by using non-volatile memory. Of particular interest are self-implementations of key operations, in which a recoverable operation is implemented from its non-recoverable counterpart (in addition to reads and writes). This paper presents two self-implementations of the SWAP operation. One works in the system-wide failures model, where all processes fail and recover together, and the other in the independent failures model, where each process crashes and recovers independently of the other processes. Both algorithms are wait-free in crash-free executions, but their recovery code is blocking. We prove that this is inherent for the independent failures model. The impossibility result is proved for implementations of distinguishable operations using interfering functions, and in particular, it applies to a recoverable self-implementation of swap.
With the continuous increase in the size and complexity of machine learning models, the need for specialized hardware to efficiently run such models is rapidly growing. To address such a need, silicon-photonic-based neural network (SP-NN) accelerators have recently emerged as a promising alternative to electronic accelerators due to their lower latency and higher energy efficiency. Not only can SP-NNs alleviate the fan-in and fan-out problem with linear algebra processors, their operational bandwidth can match that of the photodetection rate (typically 100 GHz), which is at least over an order of magnitude faster than electronic counterparts that are restricted to a clock rate of a few GHz. Unfortunately, the underlying silicon photonic devices in SP-NNs suffer from inherent optical losses and crosstalk noise originating from fabrication imperfections and undesired optical couplings, the impact of which accumulates as the network scales up. Consequently, the inferencing accuracy in an SP-NN can be affected by such inefficiencies -- e.g., can drop to below 10% -- the impact of which is yet to be fully studied. In this paper, we comprehensively model the optical loss and crosstalk noise using a bottom-up approach, from the device to the system level, in coherent SP-NNs built using Mach-Zehnder interferometer (MZI) devices. The proposed models can be applied to any SP-NN architecture with different configurations to analyze the effect of loss and crosstalk. Such an analysis is important where there are inferencing accuracy and scalability requirements to meet when designing an SP-NN. Using the proposed analytical framework, we show a high power penalty and a catastrophic inferencing accuracy drop of up to 84% for SP-NNs of different scales with three known MZI mesh configurations (i.e., Reck, Clements, and Diamond) due to accumulated optical loss and crosstalk noise.
We introduce a new information-geometric structure associated with the dynamics on discrete objects such as graphs and hypergraphs. The presented setup consists of two dually flat structures built on the vertex and edge spaces, respectively. The former is the conventional duality between density and potential, e.g., the probability density and its logarithmic form induced by a convex thermodynamic function. The latter is the duality between flux and force induced by a convex and symmetric dissipation function, which drives the dynamics of the density. These two are connected topologically by the homological algebraic relation induced by the underlying discrete objects. The generalized gradient flow in this doubly dual flat structure is an extension of the gradient flows on Riemannian manifolds, which include Markov jump processes and nonlinear chemical reaction dynamics as well as the natural gradient and mirror descent. The information-geometric projections on this doubly dual flat structure lead to information-geometric extensions of the Helmholtz-Hodge decomposition and the Otto structure in $L^{2}$ Wasserstein geometry. The structure can be extended to non-gradient nonequilibrium flows, from which we also obtain the induced dually flat structure on cycle spaces. This abstract but general framework can extend the applicability of information geometry to various problems of linear and nonlinear dynamics.
Pre-trained Language Models (PLMs) which are trained on large text corpus via self-supervised learning method, have yielded promising performance on various tasks in Natural Language Processing (NLP). However, though PLMs with huge parameters can effectively possess rich knowledge learned from massive training text and benefit downstream tasks at the fine-tuning stage, they still have some limitations such as poor reasoning ability due to the lack of external knowledge. Research has been dedicated to incorporating knowledge into PLMs to tackle these issues. In this paper, we present a comprehensive review of Knowledge-Enhanced Pre-trained Language Models (KE-PLMs) to provide a clear insight into this thriving field. We introduce appropriate taxonomies respectively for Natural Language Understanding (NLU) and Natural Language Generation (NLG) to highlight these two main tasks of NLP. For NLU, we divide the types of knowledge into four categories: linguistic knowledge, text knowledge, knowledge graph (KG), and rule knowledge. The KE-PLMs for NLG are categorized into KG-based and retrieval-based methods. Finally, we point out some promising future directions of KE-PLMs.
The notion of uncertainty is of major importance in machine learning and constitutes a key element of machine learning methodology. In line with the statistical tradition, uncertainty has long been perceived as almost synonymous with standard probability and probabilistic predictions. Yet, due to the steadily increasing relevance of machine learning for practical applications and related issues such as safety requirements, new problems and challenges have recently been identified by machine learning scholars, and these problems may call for new methodological developments. In particular, this includes the importance of distinguishing between (at least) two different types of uncertainty, often refereed to as aleatoric and epistemic. In this paper, we provide an introduction to the topic of uncertainty in machine learning as well as an overview of hitherto attempts at handling uncertainty in general and formalizing this distinction in particular.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191