Fair division provides a rich computational and mathematical framework for the allocation of indivisible goods, which has given rise to numerous fairness concepts and their relaxations. In recent years, much attention has been given to theoretical and computational aspects of various fairness concepts. Nonetheless, the choice of which fairness concept is in practice perceived to be fairer by individuals is not well understood. We consider two conceptually different relaxations of envy-freeness and investigate how individuals perceive the induced allocations as fair. In particular, we examine a well-studied relaxation of envy-freeness up to one good (EF1) which is based on counterfactual thinking that any pairwise envy can be eliminated by the hypothetical removal of a single good from the envied agent's bundle. In contrast, a recently proposed epistemic notion, namely envy-freeness up to $k$ hidden goods (HEF-$k$), provides a relaxation by hiding information about a small subset of $k$ goods. Through various crowdsourcing experiments, we empirically demonstrate that allocations achieved by withholding information are perceived to be fairer compared to two variants of EF1.
相關內容
In this paper we are concerned with understanding the nature of program metrics for calculi with higher-order types, seen as natural generalizations of program equivalences. Some of the metrics we are interested in are well-known, such as those based on the interpretation of terms in metric spaces and those obtained by generalizing observational equivalence. We also introduce a new one, called the interactive metric, built by applying the well-known Int-Construction to the category of metric complete partial orders. Our aim is then to understand how these metrics relate to each other, i.e., whether and in which cases one such metric refines another, in analogy with corresponding well-studied problems about program equivalences. The results we obtain are twofold. We first show that the metrics of semantic origin, i.e., the denotational and interactive ones, lie \emph{in between} the observational and equational metrics and that in some cases, these inclusions are strict. Then, we give a result about the relationship between the denotational and interactive metrics, revealing that the former is less discriminating than the latter. All our results are given for a linear lambda-calculus, and some of them can be generalized to calculi with graded comonads, in the style of Fuzz.
We consider signal source localization from range-difference measurements. First, we give some readily-checked conditions on measurement noises and sensor deployment to guarantee the asymptotic identifiability of the model and show the consistency and asymptotic normality of the maximum likelihood (ML) estimator. Then, we devise an estimator that owns the same asymptotic property as the ML one. Specifically, we prove that the negative log-likelihood function converges to a function, which has a unique minimum and positive-definite Hessian at the true source's position. Hence, it is promising to execute local iterations, e.g., the Gauss-Newton (GN) algorithm, following a consistent estimate. The main issue involved is obtaining a preliminary consistent estimate. To this aim, we construct a linear least-squares problem via algebraic operation and constraint relaxation and obtain a closed-form solution. We then focus on deriving and eliminating the bias of the linear least-squares estimator, which yields an asymptotically unbiased (thus consistent) estimate. Noting that the bias is a function of the noise variance, we further devise a consistent noise variance estimator which involves $3$-order polynomial rooting. Based on the preliminary consistent location estimate, we prove that a one-step GN iteration suffices to achieve the same asymptotic property as the ML estimator. Simulation results demonstrate the superiority of our proposed algorithm in the large sample case.
The error of an estimator can be decomposed into a (statistical) bias term, a variance term, and an irreducible noise term. When we do bias analysis, formally we are asking the question: "how good are the predictions?" The role of bias in the error decomposition is clear: if we trust the labels/targets, then we would want the estimator to have as low bias as possible, in order to minimize error. Fair machine learning is concerned with the question: "Are the predictions equally good for different demographic/social groups?" This has naturally led to a variety of fairness metrics that compare some measure of statistical bias on subsets corresponding to socially privileged and socially disadvantaged groups. In this paper we propose a new family of performance measures based on group-wise parity in variance. We demonstrate when group-wise statistical bias analysis gives an incomplete picture, and what group-wise variance analysis can tell us in settings that differ in the magnitude of statistical bias. We develop and release an open-source library that reconciles uncertainty quantification techniques with fairness analysis, and use it to conduct an extensive empirical analysis of our variance-based fairness measures on standard benchmarks.
Class invariants -- consistency constraints preserved by every operation on objects of a given type -- are fundamental to building, understanding and verifying object-oriented programs. For verification, however, they raise difficulties, which have not yet received a generally accepted solution. The present work introduces a proof rule meant to address these issues and allow verification tools to benefit from invariants. It clarifies the notion of invariant and identifies the three associated problems: callbacks, furtive access and reference leak. As an example, the 2016 Ethereum DAO bug, in which $50 million were stolen, resulted from a callback invalidating an invariant. The discussion starts with a simplified model of computation and an associated proof rule, demonstrating its soundness. It then removes one by one the three simplifying assumptions, each removal raising one of the three issues, and leading to a corresponding adaptation to the proof rule. The final version of the rule can tackle tricky examples, including "challenge problems" listed in the literature.
The identification of choice models is crucial for understanding consumer behavior and informing marketing or operational strategies, policy design, and product development. The identification of parametric choice-based demand models is typically straightforward. However, nonparametric models, which are highly effective and flexible in explaining customer choice, may encounter the challenge of the dimensionality curse, hindering their identification. A prominent example of a nonparametric model is the ranking-based model, which mirrors the random utility maximization (RUM) class and is known to be nonidentifiable from the collection of choice probabilities alone. Our objective in this paper is to develop a new class of nonparametric models that is not subject to the problem of nonidentifiability. Our model assumes bounded rationality of consumers, which results in symmetric demand cannibalization and intriguingly enables full identification. Additionally, our choice model demonstrates competitive prediction accuracy compared to the state-of-the-art benchmarks in a real-world case study, despite incorporating the assumption of bounded rationality which could, in theory, limit the representation power of our model. In addition, we tackle the important problem of finding the optimal assortment under the proposed choice model. We demonstrate the NP-hardness of this problem and provide a fully polynomial-time approximation scheme through dynamic programming. Additionally, we propose an efficient estimation framework using a combination of column generation and expectation-maximization algorithms, which proves to be more tractable than the estimation algorithm of the aforementioned ranking-based model.
We study the problem of allocating many mobile robots for the execution of a pre-defined sweep schedule in a known two-dimensional environment, with applications toward search and rescue, coverage, surveillance, monitoring, pursuit-evasion, and so on. The mobile robots (or agents) are assumed to have one-dimensional sensing capability with probabilistic guarantees that deteriorate as the sensing distance increases. In solving such tasks, a time-parameterized distribution of robots along the sweep frontier must be computed, with the objective to minimize the number of robots used to achieve some desired coverage quality guarantee or to maximize the probabilistic guarantee for a given number of robots. We propose a max-flow based algorithm for solving the allocation task, which builds on a decomposition technique of the workspace as a generalization of the well-known boustrophedon decomposition. Our proposed algorithm has a very low polynomial running time and completes in under two seconds for polygonal environments with over $10^5$ vertices. Simulation experiments are carried out on three realistic use cases with randomly generated obstacles of varying shapes, sizes, and spatial distributions, which demonstrate the applicability and scalability our proposed method.
Probabilistic predictions can be evaluated through comparisons with observed label frequencies, that is, through the lens of calibration. Recent scholarship on algorithmic fairness has started to look at a growing variety of calibration-based objectives under the name of multi-calibration but has still remained fairly restricted. In this paper, we explore and analyse forms of evaluation through calibration by making explicit the choices involved in designing calibration scores. We organise these into three grouping choices and a choice concerning the agglomeration of group errors. This provides a framework for comparing previously proposed calibration scores and helps to formulate novel ones with desirable mathematical properties. In particular, we explore the possibility of grouping datapoints based on their input features rather than on predictions and formally demonstrate advantages of such approaches. We also characterise the space of suitable agglomeration functions for group errors, generalising previously proposed calibration scores. Complementary to such population-level scores, we explore calibration scores at the individual level and analyse their relationship to choices of grouping. We draw on these insights to introduce and axiomatise fairness deviation measures for population-level scores. We demonstrate that with appropriate choices of grouping, these novel global fairness scores can provide notions of (sub-)group or individual fairness.
While a large number of pre-trained models of source code have been successfully developed and applied to a variety of software engineering (SE) tasks in recent years, our understanding of these pre-trained models is arguably fairly limited. With the goal of advancing our understanding of these models, we perform the first systematic empirical comparison of 19 recently-developed pre-trained models of source code on 13 SE tasks. To gain additional insights into these models, we adopt a recently-developed 4-dimensional categorization of pre-trained models, and subsequently investigate whether there are correlations between different categories of pre-trained models and their performances on different SE tasks.
Text-to-image models, which can generate high-quality images based on textual input, have recently enabled various content-creation tools. Despite significantly affecting a wide range of downstream applications, the distributions of these generated images are still not fully understood, especially when it comes to the potential stereotypical attributes of different genders. In this work, we propose a paradigm (Gender Presentation Differences) that utilizes fine-grained self-presentation attributes to study how gender is presented differently in text-to-image models. By probing gender indicators in the input text (e.g., "a woman" or "a man"), we quantify the frequency differences of presentation-centric attributes (e.g., "a shirt" and "a dress") through human annotation and introduce a novel metric: GEP. Furthermore, we propose an automatic method to estimate such differences. The automatic GEP metric based on our approach yields a higher correlation with human annotations than that based on existing CLIP scores, consistently across three state-of-the-art text-to-image models. Finally, we demonstrate the generalization ability of our metrics in the context of gender stereotypes related to occupations.
The Q-learning algorithm is known to be affected by the maximization bias, i.e. the systematic overestimation of action values, an important issue that has recently received renewed attention. Double Q-learning has been proposed as an efficient algorithm to mitigate this bias. However, this comes at the price of an underestimation of action values, in addition to increased memory requirements and a slower convergence. In this paper, we introduce a new way to address the maximization bias in the form of a "self-correcting algorithm" for approximating the maximum of an expected value. Our method balances the overestimation of the single estimator used in conventional Q-learning and the underestimation of the double estimator used in Double Q-learning. Applying this strategy to Q-learning results in Self-correcting Q-learning. We show theoretically that this new algorithm enjoys the same convergence guarantees as Q-learning while being more accurate. Empirically, it performs better than Double Q-learning in domains with rewards of high variance, and it even attains faster convergence than Q-learning in domains with rewards of zero or low variance. These advantages transfer to a Deep Q Network implementation that we call Self-correcting DQN and which outperforms regular DQN and Double DQN on several tasks in the Atari 2600 domain.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191