اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدEnforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretability
144
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
To date, there has been no formal study of the statistical cost of interpretability in machine learning. As such, the discourse around potential trade-offs is often informal and misconceptions abound. In this work, we aim to initiate a formal study of these trade-offs. A seemingly insurmountable roadblock is the lack of any agreed upon definition of interpretability. Instead, we propose a shift in perspective. Rather than attempt to define interpretability, we propose to model the emph{act} of emph{enforcing} interpretability. As a starting point, we focus on the setting of empirical risk minimization for binary classification, and view interpretability as a constraint placed on learning. That is, we assume we are given a subset of hypothesis that are deemed to be interpretable, possibly depending on the data distribution and other aspects of the context. We then model the act of enforcing interpretability as that of performing empirical risk minimization over the set of interpretable hypotheses. This model allows us to reason about the statistical implications of enforcing interpretability, using known results in statistical learning theory. Focusing on accuracy, we perform a case analysis, explaining why one may or may not observe a trade-off between accuracy and interpretability when the restriction to interpretable classifiers does or does not come at the cost of some excess statistical risk. We close with some worked examples and some open problems, which we hope will spur further theoretical development around the tradeoffs involved in interpretability.
قيم البحث
اقرأ أيضاً
We show that adding differential privacy to Explainable Boosting Machines (EBMs), a recent method for training interpretable ML models, yields state-of-the-art accuracy while protecting privacy. Our experiments on multiple classification and regressi
on datasets show that DP-EBM models suffer surprisingly little accuracy loss even with strong differential privacy guarantees. In addition to high accuracy, two other benefits of applying DP to EBMs are: a) trained models provide exact global and local interpretability, which is often important in settings where differential privacy is needed; and b) the models can be edited after training without loss of privacy to correct errors which DP noise may have introduced.
We identify a trade-off between robustness and accuracy that serves as a guiding principle in the design of defenses against adversarial examples. Although this problem has been widely studied empirically, much remains unknown concerning the theory u
nderlying this trade-off. In this work, we decompose the prediction error for adversarial examples (robust error) as the sum of the natural (classification) error and boundary error, and provide a differentiable upper bound using the theory of classification-calibrated loss, which is shown to be the tightest possible upper bound uniform over all probability distributions and measurable predictors. Inspired by our theoretical analysis, we also design a new defense method, TRADES, to trade adversarial robustness off against accuracy. Our proposed algorithm performs well experimentally in real-world datasets. The methodology is the foundation of our entry to the NeurIPS 2018 Adversarial Vision Challenge in which we won the 1st place out of ~2,000 submissions, surpassing the runner-up approach by $11.41%$ in terms of mean $ell_2$ perturbation distance.
It is well understood that classification algorithms, for example, for deciding on loan applications, cannot be evaluated for fairness without taking context into account. We examine what can be learned from a fairness oracle equipped with an underly
ing understanding of ``true fairness. The oracle takes as input a (context, classifier) pair satisfying an arbitrary fairness definition, and accepts or rejects the pair according to whether the classifier satisfies the underlying fairness truth. Our principal conceptual result is an extraction procedure that learns the underlying truth; moreover, the procedure can learn an approximation to this truth given access to a weak form of the oracle. Since every ``truly fair classifier induces a coarse metric, in which those receiving the same decision are at distance zero from one another and those receiving different decisions are at distance one, this extraction process provides the basis for ensuring a rough form of metric fairness, also known as individual fairness. Our principal technical result is a higher fidelity extractor under a mild technical constraint on the weak oracles conception of fairness. Our framework permits the scenario in which many classifiers, with differing outcomes, may all be considered fair. Our results have implications for interpretablity -- a highly desired but poorly defined property of classification systems that endeavors to permit a human arbiter to reject classifiers deemed to be ``unfair or illegitimately derived.
In the application of machine learning to real-life decision-making systems, e.g., credit scoring and criminal justice, the prediction outcomes might discriminate against people with sensitive attributes, leading to unfairness. The commonly used stra
tegy in fair machine learning is to include fairness as a constraint or a penalization term in the minimization of the prediction loss, which ultimately limits the information given to decision-makers. In this paper, we introduce a new approach to handle fairness by formulating a stochastic multi-objective optimization problem for which the corresponding Pareto fronts uniquely and comprehensively define the accuracy-fairness trade-offs. We have then applied a stochastic approximation-type method to efficiently obtain well-spread and accurate Pareto fronts, and by doing so we can handle training data arriving in a streaming way.
A common approach for feature selection is to examine the variable importance scores for a machine learning model, as a way to understand which features are the most relevant for making predictions. Given the significance of feature selection, it is
crucial for the calculated importance scores to reflect reality. Falsely overestimating the importance of irrelevant features can lead to false discoveries, while underestimating importance of relevant features may lead us to discard important features, resulting in poor model performance. Additionally, black-box models like XGBoost provide state-of-the art predictive performance, but cannot be easily understood by humans, and thus we rely on variable importance scores or methods for explainability like SHAP to offer insight into their behavior. In this paper, we investigate the performance of variable importance as a feature selection method across various black-box and interpretable machine learning methods. We compare the ability of CART, Optimal Trees, XGBoost and SHAP to correctly identify the relevant subset of variables across a number of experiments. The results show that regardless of whether we use the native variable importance method or SHAP, XGBoost fails to clearly distinguish between relevant and irrelevant features. On the other hand, the interpretable methods are able to correctly and efficiently identify irrelevant features, and thus offer significantly better performance for feature selection.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
