We show how to take a regression function $\hat{f}$ that is appropriately ``multicalibrated'' and efficiently post-process it into an approximately error minimizing classifier satisfying a large variety of fairness constraints. The post-processing requires no labeled data, and only a modest amount of unlabeled data and computation. The computational and sample complexity requirements of computing $\hat f$ are comparable to the requirements for solving a single fair learning task optimally, but it can in fact be used to solve many different downstream fairness-constrained learning problems efficiently. Our post-processing method easily handles intersecting groups, generalizing prior work on post-processing regression functions to satisfy fairness constraints that only applied to disjoint groups. Our work extends recent work showing that multicalibrated regression functions are ``omnipredictors'' (i.e. can be post-processed to optimally solve unconstrained ERM problems) to constrained optimization.
相關內容
The interplay between Machine Learning (ML) and Constrained Optimization (CO) has recently been the subject of increasing interest, leading to a new and prolific research area covering (e.g.) Decision Focused Learning and Constrained Reinforcement Learning. Such approaches strive to tackle complex decision problems under uncertainty over multiple stages, involving both explicit (cost function, constraints) and implicit knowledge (from data), and possibly subject to execution time restrictions. While a good degree of success has been achieved, the existing methods still have limitations in terms of both applicability and effectiveness. For problems in this class, we propose UNIFY, a unified framework to design a solution policy for complex decision-making problems. Our approach relies on a clever decomposition of the policy in two stages, namely an unconstrained ML model and a CO problem, to take advantage of the strength of each approach while compensating for its weaknesses. With a little design effort, UNIFY can generalize several existing approaches, thus extending their applicability. We demonstrate the method effectiveness on two practical problems, namely an Energy Management System and the Set Multi-cover with stochastic coverage requirements. Finally, we highlight some current challenges of our method and future research directions that can benefit from the cross-fertilization of the two fields.
Compared with multi-class classification, multi-label classification that contains more than one class is more suitable in real life scenarios. Obtaining fully labeled high-quality datasets for multi-label classification problems, however, is extremely expensive, and sometimes even infeasible, with respect to annotation efforts, especially when the label spaces are too large. This motivates the research on partial-label classification, where only a limited number of labels are annotated and the others are missing. To address this problem, we first propose a pseudo-label based approach to reduce the cost of annotation without bringing additional complexity to the existing classification networks. Then we quantitatively study the impact of missing labels on the performance of classifier. Furthermore, by designing a novel loss function, we are able to relax the requirement that each instance must contain at least one positive label, which is commonly used in most existing approaches. Through comprehensive experiments on three large-scale multi-label image datasets, i.e. MS-COCO, NUS-WIDE, and Pascal VOC12, we show that our method can handle the imbalance between positive labels and negative labels, while still outperforming existing missing-label learning approaches in most cases, and in some cases even approaches with fully labeled datasets.
We propose a supervised principal component regression method for relating functional responses with high dimensional predictors. Unlike the conventional principal component analysis, the proposed method builds on a newly defined expected integrated residual sum of squares, which directly makes use of the association between the functional response and the predictors. Minimizing the integrated residual sum of squares gives the supervised principal components, which is equivalent to solving a sequence of nonconvex generalized Rayleigh quotient optimization problems. We reformulate the nonconvex optimization problems into a simultaneous linear regression with a sparse penalty to deal with high dimensional predictors. Theoretically, we show that the reformulated regression problem can recover the same supervised principal subspace under certain conditions. Statistically, we establish non-asymptotic error bounds for the proposed estimators when the covariate covariance is bandable. We demonstrate the advantages of the proposed method through numerical experiments and an application to the Human Connectome Project fMRI data.
Distributed statistical learning problems arise commonly when dealing with large datasets. In this setup, datasets are partitioned over machines, which compute locally, and communicate short messages. Communication is often the bottleneck. In this paper, we study one-step and iterative weighted parameter averaging in statistical linear models under data parallelism. We do linear regression on each machine, send the results to a central server, and take a weighted average of the parameters. Optionally, we iterate, sending back the weighted average and doing local ridge regressions centered at it. How does this work compared to doing linear regression on the full data? Here we study the performance loss in estimation, test error, and confidence interval length in high dimensions, where the number of parameters is comparable to the training data size. We find the performance loss in one-step weighted averaging, and also give results for iterative averaging. We also find that different problems are affected differently by the distributed framework. Estimation error and confidence interval length increase a lot, while prediction error increases much less. We rely on recent results from random matrix theory, where we develop a new calculus of deterministic equivalents as a tool of broader interest.
In domains where sample sizes are limited, efficient learning algorithms are critical. Learning using privileged information (LuPI) offers increased sample efficiency by allowing prediction models access to auxiliary information at training time which is unavailable when the models are used. In recent work, it was shown that for prediction in linear-Gaussian dynamical systems, a LuPI learner with access to intermediate time series data is never worse and often better in expectation than any unbiased classical learner. We provide new insights into this analysis and generalize it to nonlinear prediction tasks in latent dynamical systems, extending theoretical guarantees to the case where the map connecting latent variables and observations is known up to a linear transform. In addition, we propose algorithms based on random features and representation learning for the case when this map is unknown. A suite of empirical results confirm theoretical findings and show the potential of using privileged time-series information in nonlinear prediction.
Feature selection plays a vital role in promoting the classifier's performance. However, current methods ineffectively distinguish the complex interaction in the selected features. To further remove these hidden negative interactions, we propose a GA-like dynamic probability (GADP) method with mutual information which has a two-layer structure. The first layer applies the mutual information method to obtain a primary feature subset. The GA-like dynamic probability algorithm, as the second layer, mines more supportive features based on the former candidate features. Essentially, the GA-like method is one of the population-based algorithms so its work mechanism is similar to the GA. Different from the popular works which frequently focus on improving GA's operators for enhancing the search ability and lowering the converge time, we boldly abandon GA's operators and employ the dynamic probability that relies on the performance of each chromosome to determine feature selection in the new generation. The dynamic probability mechanism significantly reduces the parameter number in GA that making it easy to use. As each gene's probability is independent, the chromosome variety in GADP is more notable than in traditional GA, which ensures GADP has a wider search space and selects relevant features more effectively and accurately. To verify our method's superiority, we evaluate our method under multiple conditions on 15 datasets. The results demonstrate the outperformance of the proposed method. Generally, it has the best accuracy. Further, we also compare the proposed model to the popular heuristic methods like POS, FPA, and WOA. Our model still owns advantages over them.
This article introduces the 50stateSimulations, a collection of simulated congressional districting plans and underlying code developed by the Algorithm-Assisted Redistricting Methodology (ALARM) Project. The 50stateSimulations allow for the evaluation of enacted and other congressional redistricting plans in the United States. While the use of redistricting simulation algorithms has become standard in academic research and court cases, any simulation analysis requires non-trivial efforts to combine multiple data sets, identify state-specific redistricting criteria, implement complex simulation algorithms, and summarize and visualize simulation outputs. We have developed a complete workflow that facilitates this entire process of simulation-based redistricting analysis for the congressional districts of all 50 states. The resulting 50stateSimulations include ensembles of simulated 2020 congressional redistricting plans and necessary replication data. We also provide the underlying code, which serves as a template for customized analyses. All data and code are free and publicly available. This article details the design, creation, and validation of the data.
In this paper, we propose to use the concept of local fairness for auditing and ranking redistricting plans. Given a redistricting plan, a deviating group is a population-balanced contiguous region in which a majority of individuals are of the same interest and in the minority of their respective districts; such a set of individuals have a justified complaint with how the redistricting plan was drawn. A redistricting plan with no deviating groups is called locally fair. We show that the problem of auditing a given plan for local fairness is NP-complete. We present an MCMC approach for auditing as well as ranking redistricting plans. We also present a dynamic programming based algorithm for the auditing problem that we use to demonstrate the efficacy of our MCMC approach. Using these tools, we test local fairness on real-world election data, showing that it is indeed possible to find plans that are almost or exactly locally fair. Further, we show that such plans can be generated while sacrificing very little in terms of compactness and existing fairness measures such as competitiveness of the districts or seat shares of the plans.
Model diagnostics and forecast evaluation are two sides of the same coin. A common principle is that fitted or predicted distributions ought to be calibrated or reliable, ideally in the sense of auto-calibration, where the outcome is a random draw from the posited distribution. For binary responses, this is the universal concept of reliability. For real-valued outcomes, a general theory of calibration has been elusive, despite a recent surge of interest in distributional regression and machine learning. We develop a framework rooted in probability theory, which gives rise to hierarchies of calibration, and applies to both predictive distributions and stand-alone point forecasts. In a nutshell, a prediction - distributional or single-valued - is conditionally T-calibrated if it can be taken at face value in terms of the functional T. Whenever T is defined via an identification function - as in the cases of threshold (non) exceedance probabilities, quantiles, expectiles, and moments - auto-calibration implies T-calibration. We introduce population versions of T-reliability diagrams and revisit a score decomposition into measures of miscalibration (MCB), discrimination (DSC), and uncertainty (UNC). In empirical settings, stable and efficient estimators of T-reliability diagrams and score components arise via nonparametric isotonic regression and the pool-adjacent-violators algorithm. For in-sample model diagnostics, we propose a universal coefficient of determination, $$\text{R}^\ast = \frac{\text{DSC}-\text{MCB}}{\text{UNC}},$$ that nests and reinterprets the classical $\text{R}^2$ in least squares (mean) regression and its natural analogue $\text{R}^1$ in quantile regression, yet applies to T-regression in general, with MCB $\geq 0$, DSC $\geq 0$, and $\text{R}^\ast \in [0,1]$ under modest conditions.
Modern neural network training relies heavily on data augmentation for improved generalization. After the initial success of label-preserving augmentations, there has been a recent surge of interest in label-perturbing approaches, which combine features and labels across training samples to smooth the learned decision surface. In this paper, we propose a new augmentation method that leverages the first and second moments extracted and re-injected by feature normalization. We replace the moments of the learned features of one training image by those of another, and also interpolate the target labels. As our approach is fast, operates entirely in feature space, and mixes different signals than prior methods, one can effectively combine it with existing augmentation methods. We demonstrate its efficacy across benchmark data sets in computer vision, speech, and natural language processing, where it consistently improves the generalization performance of highly competitive baseline networks.
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