Author name cluster

Dennis Wei

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

28 papers

2 author rows

AAAI Conference 2026 Conference Paper

Parameterized Abstract Interpretation for Transformer Verification

Pei Huang
Dennis Wei
Omri Isac
Haoze Wu
Min Wu
Clark Barrett

Transformers based on the self-attention mechanism have become foundational models across a wide range of domains, thereby creating an urgent need for effective formal verification techniques to better understand their behavior and ensure safety guarantees. In this paper, we propose two parameterized linear abstract domains for the inner products in the self-attention module, aiming to improve verification precision. The first one constructs symbolic quadratic upper and lower bounds for the product of two scalars, and then derives parameterized affine bounds using tangents. The other one constructs parameterized bounds by interpolating affine bounds proposed in prior work. We evaluate these two parameterization methods and demonstrate that both of them outperform the state-of-the-art approach which is regarded as optimal with respect to a certain mean gap. Experimental results show that, in the context of robustness verification, our approach is able to verify many instances that cannot be verified by existing methods. In the interval analysis, our method achieves tighter results compared to the SOTA, with the strength becoming more pronounced as the network depth increases.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Fair Continuous Resource Allocation with Equality of Impact

Blossom Metevier
Dennis Wei
Karthikeyan Natesan Ramamurthy
Philip Thomas

Recent works have studied fair resource allocation in social settings, where fairness is judged by the impact of allocation decisions rather than more traditional minimum or maximum thresholds on the allocations themselves. Our work significantly adds to this literature by developing continuous resource allocation strategies that adhere to equality of impact, a generalization of equality of opportunity. We derive methods to maximize total welfare across groups subject to minimal violation of equality of impact, in settings where the outcomes of allocations are unknown but have a diminishing marginal effect. While focused on a two-group setting, our study addresses a broader class of welfare dynamics than explored in prior work. Our contributions are threefold. First, we introduce Equality of Impact (EoI), a fairness criterion defined via group-level impact functions. Second, we design an online algorithm for non-noisy settings that leverages the problem’s geometric structure and achieves constant cumulative fairness regret. Third, we extend this approach to noisy environments with a meta-algorithm and empirically demonstrate that our methods find fair allocations and perform competitively relative to representative baselines.

PDF Details

NeurIPS Conference 2025 Conference Paper

Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods

Dennis Wei
Inkit Padhi
Soumya Ghosh
Amit Dhurandhar
Karthikeyan Natesan Ramamurthy
Maria Chang

Training data attribution (TDA) is concerned with understanding model behavior in terms of the training data. This paper draws attention to the common setting where one has access only to the final trained model, and not the training algorithm or intermediate information from training. We reframe the problem in this "final-model-only" setting as one of measuring sensitivity of the model to training instances. To operationalize this reframing, we propose further training, with appropriate adjustment and averaging, as a gold standard method to measure sensitivity. We then unify existing gradient-based methods for TDA by showing that they all approximate the further training gold standard in different ways. We investigate empirically the quality of these gradient-based approximations to further training, for tabular, image, and text datasets and models. We find that the approximation quality of first-order methods is sometimes high but decays with the amount of further training. In contrast, the approximations given by influence function methods are more stable but surprisingly lower in quality.

PDF Details

ICML Conference 2025 Conference Paper

Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning

Changsheng Wang
Yihua Zhang
Jinghan Jia
Parikshit Ram
Dennis Wei
Yuguang Yao
Soumyadeep Pal
Nathalie Baracaldo

Machine unlearning presents a promising approach to mitigating privacy and safety concerns in large language models (LLMs) by enabling the selective removal of targeted data or knowledge while preserving model utility. However, existing unlearning methods remain over-sensitive to downstream fine-tuning, which can rapidly recover what is supposed to be unlearned information even when the fine-tuning task is entirely unrelated to the unlearning objective. To enhance robustness, we introduce the concept of ‘invariance’ into unlearning for the first time from the perspective of invariant risk minimization (IRM), a principle for environment-agnostic training. By leveraging IRM, we develop a new invariance-regularized LLM unlearning framework, termed invariant LLM unlearning (ILU). We show that the proposed invariance regularization, even using only a single fine-tuning dataset during ILU training, can enable unlearning robustness to generalize effectively across diverse and new fine-tuning tasks at test time. A task vector analysis is also provided to further elucidate the rationale behind ILU’s effectiveness. Extensive experiments on the WMDP benchmark, which focuses on removing an LLM’s hazardous knowledge generation capabilities, reveal that ILU significantly outperforms state-of-the-art unlearning methods, including negative preference optimization (NPO) and representation misdirection for unlearning (RMU). Notably, ILU achieves superior unlearning robustness across diverse downstream fine-tuning scenarios (e. g. , math, paraphrase detection, and sentiment analysis) while preserving the fine-tuning performance.

Details

TMLR Journal 2025 Journal Article

The RealHumanEval: Evaluating Large Language Models’ Abilities to Support Programmers

Hussein Mozannar
Valerie Chen
Mohammed Alsobay
Subhro Das
Sebastian Zhao
Dennis Wei
Manish Nagireddy
Prasanna Sattigeri

Evaluation of large language models for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), or more recently using human preferences of LLM responses. As LLMs are increasingly used as programmer assistants, we study whether gains on existing benchmarks or more preferred LLM responses translate to programmer productivity when coding with LLMs, including time spent coding. We introduce RealHumanEval, a web interface to measure the ability of LLMs to assist programmers, through either autocomplete or chat support. We conducted a user study (N=243) using RealHumanEval in which users interacted with seven LLMs of varying base model performance. Despite static benchmarks not incorporating humans-in-the-loop, we find that improvements in benchmark performance lead to increased programmer productivity; however gaps in benchmark versus human performance are not proportional---a trend that holds across both forms of LLM support. In contrast, we find that programmer preferences do not correlate with their actual performance, motivating the need for better proxy signals. We open-source RealHumanEval to enable human-centric evaluation of new models and the study data to facilitate efforts to improve code models.

PDF Details

NeurIPS Conference 2024 Conference Paper

Interventional Causal Discovery in a Mixture of DAGs

Burak Varıcı
Dmitriy A. Katz
Dennis Wei
Prasanna Sattigeri
Ali Tajer

Causal interactions among a group of variables are often modeled by a single causal graph. In some domains, however, these interactions are best described by multiple co-existing causal graphs, e. g. , in dynamical systems or genomics. This paper addresses the hitherto unknown role of interventions in learning causal interactions among variables governed by a mixture of causal systems, each modeled by one directed acyclic graph (DAG). Causal discovery from mixtures is fundamentally more challenging than single-DAG causal discovery. Two major difficulties stem from (i) an inherent uncertainty about the skeletons of the component DAGs that constitute the mixture and (ii) possibly cyclic relationships across these component DAGs. This paper addresses these challenges and aims to identify edges that exist in at least one component DAG of the mixture, referred to as the *true* edges. First, it establishes matching necessary and sufficient conditions on the size of interventions required to identify the true edges. Next, guided by the necessity results, an adaptive algorithm is designed that learns all true edges using ${\cal O}(n^2)$ interventions, where $n$ is the number of nodes. Remarkably, the size of the interventions is optimal if the underlying mixture model does not contain cycles across its components. More generally, the gap between the intervention size used by the algorithm and the optimal size is quantified. It is shown to be bounded by the *cyclic complexity number* of the mixture model, defined as the size of the minimal intervention that can break the cycles in the mixture, which is upper bounded by the number of cycles among the ancestors of a node.

PDF Details DOI

ICLR Conference 2024 Conference Paper

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Chongyu Fan
Jiancheng Liu
Yihua Zhang
Eric Wong 0001
Dennis Wei
Sijia Liu 0001

With evolving data regulations, machine unlearning (MU) has become an important tool for fostering trust and safety in today's AI models. However, existing MU methods focusing on data and/or weight perspectives often suffer limitations in unlearning accuracy, stability, and cross-domain applicability. To address these challenges, we introduce the concept of 'weight saliency' for MU, drawing parallels with input saliency in model explanation. This innovation directs MU's attention toward specific model weights rather than the entire model, improving effectiveness and efficiency. The resultant method that we call saliency unlearning (SalUn) narrows the performance gap with 'exact' unlearning (model retraining from scratch after removing the forgetting data points). To the best of our knowledge, SalUn is the first principled MU approach that can effectively erase the influence of forgetting data, classes, or concepts in both image classification and generation tasks. As highlighted below, For example, SalUn yields a stability advantage in high-variance random data forgetting, e.g., with a 0.2% gap compared to exact unlearning on the CIFAR-10 dataset. Moreover, in preventing conditional diffusion models from generating harmful images, SalUn achieves nearly 100% unlearning accuracy, outperforming current state-of-the-art baselines like Erased Stable Diffusion and Forget-Me-Not. Codes are available at https://github.com/OPTML-Group/Unlearn-Saliency. **WARNING**: This paper contains model outputs that may be offensive in nature.

Details

NeurIPS Conference 2024 Conference Paper

Selective Explanations

Lucas M. Paes
Dennis Wei
Flavio P. Calmon

Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, there have been increasing efforts to develop amortized explainers, where a ML model is trained to efficiently approximate computationally expensive feature attribution scores. Despite their efficiency, amortized explainers can produce misleading explanations. In this paper, we propose selective explanations to (i) detect when amortized explainers generate inaccurate explanations and (ii) improve the approximation of the explanation using a technique we call explanations with initial guess. Selective explanations allow practitioners to specify the fraction of samples that receive explanations with initial guess, offering a principled way to bridge the gap between amortized explainers (one inference) and more computationally costly approximations (multiple inferences). Our experiments on various models and datasets demonstrate that feature attributions via selective explanations strike a favorable balance between explanation quality and computational efficiency.

PDF Details DOI

TMLR Journal 2024 Journal Article

Separability Analysis for Causal Discovery in Mixture of DAGs

Burak Varici
Dmitriy Katz
Dennis Wei
Prasanna Sattigeri
Ali Tajer

Directed acyclic graphs (DAGs) are effective for compactly representing causal systems and specifying the causal relationships among the system's constituents. Specifying such causal relationships in some systems requires a mixture of multiple DAGs -- a single DAG is insufficient. Some examples include time-varying causal systems or aggregated subgroups of a population. Recovering the causal structure of the systems represented by single DAGs is investigated extensively, but it remains mainly open for the systems represented by a mixture of DAGs. A major difference between single- versus mixture-DAG recovery is the existence of node pairs that are separable in the individual DAGs but become inseparable in their mixture. This paper provides the theoretical foundations for analyzing such inseparable node pairs. Specifically, the notion of \emph{emergent edges} is introduced to represent such inseparable pairs that do not exist in the single DAGs but emerge in their mixtures. Necessary conditions for identifying the emergent edges are established. Operationally, these conditions serve as sufficient conditions for separating a pair of nodes in the mixture of DAGs. These results are further extended, and matching necessary and sufficient conditions for identifying the emergent edges in tree-structured DAGs are established. Finally, a novel graphical representation is formalized to specify these conditions, and an algorithm is provided for inferring the learnable causal relations.

PDF Details

ICML Conference 2024 Conference Paper

Trust Regions for Explanations via Black-Box Probabilistic Certification

Amit Dhurandhar
Swagatam Haldar
Dennis Wei
Karthikeyan Natesan Ramamurthy

Given the black box nature of machine learning models, a plethora of explainability methods have been developed to decipher the factors behind individual decisions. In this paper, we introduce a novel problem of black box (probabilistic) explanation certification. We ask the question: Given a black box model with only query access, an explanation for an example and a quality metric (viz. fidelity, stability), can we find the largest hypercube (i. e. , $\ell_{\infty}$ ball) centered at the example such that when the explanation is applied to all examples within the hypercube, (with high probability) a quality criterion is met (viz. fidelity greater than some value)? Being able to efficiently find such a trust region has multiple benefits: i) insight into model behavior in a region, with a guarantee; ii) ascertained stability of the explanation; iii) explanation reuse, which can save time, energy and money by not having to find explanations for every example; and iv) a possible meta-metric to compare explanation methods. Our contributions include formalizing this problem, proposing solutions, providing theoretical guarantees for these solutions that are computable, and experimentally showing their efficacy on synthetic and real data.

Details

IJCAI Conference 2024 Conference Paper

Using Causal Inference to Investigate Contraceptive Discontinuation in Sub-Saharan Africa

Victor Akinwande
Megan MacGregor
Celia Cintas
Ehud Karavani
Dennis Wei
Kush R. Varshney
Pablo Nepomnaschy

Discontinuation rates vary by family planning method and across socio-economic contexts. Understanding these variations and their causes is paramount for developing and implementing policies aimed at curbing discontinuation rates. Randomized controlled trials (RCTs) are ideal for obtaining this information, but this design can be extremely expensive and logistically complex. The ongoing collection of comprehensive data sets, such as Demographic and Health Surveys (DHS data), when combined with machine learning methods, present an alternative and relatively cost-effective means of evidence gathering for policy development. Here, we use causal inference to estimate the effect of injectable contraceptive use on discontinuation over the 12-month period that follows its adoption. To that aim, we use retrospective observational data from seven sub-Saharan African countries captured by the DHS’ Contraceptive Calendar. We use machine learning methods to characterize data regions that share common covariate support. We find that the use of injectables increased the risk of discontinuation in four of the seven countries analyzed. Consistent with existing literature, we find that concerns with the side-effects of injectables appear to be the most frequent reason for discontinuation. However, these risks decreased after adjusting for socio-economic factors. As risk estimates may not apply uniformly within populations, we characterized the sub-populations for robust estimations by their geographical region, level of unmet needs, marital status, level of education, and age of first sex.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Effective Human-AI Teams via Learned Natural Language Rules and Onboarding

Hussein Mozannar
Jimin Lee
Dennis Wei
Prasanna Sattigeri
Subhro Das
David Sontag

People are relying on AI agents to assist them with various tasks. The human must know when to rely on the agent, collaborate with the agent, or ignore its suggestions. In this work, we propose to learn rules grounded in data regions and described in natural language that illustrate how the human should collaborate with the AI. Our novel region discovery algorithm finds local regions in the data as neighborhoods in an embedding space that corrects the human prior. Each region is then described using an iterative and contrastive procedure where a large language model describes the region. We then teach these rules to the human via an onboarding stage. Through user studies on object detection and question-answering tasks, we show that our method can lead to more accurate human-AI teams. We also evaluate our region discovery and description algorithms separately.

PDF Details

JMLR Journal 2023 Journal Article

Interpretable and Fair Boolean Rule Sets via Column Generation

Connor Lawless
Sanjeeb Dash
Oktay Gunluk
Dennis Wei

This paper considers the learning of Boolean rules in disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) as an interpretable model for classification. An integer program is formulated to optimally trade classification accuracy for rule simplicity. We also consider the fairness setting and extend the formulation to include explicit constraints on two different measures of classification parity: equality of opportunity and equalized odds. Column generation (CG) is used to efficiently search over an exponential number of candidate rules without the need for heuristic rule mining. To handle large data sets, we propose an approximate CG algorithm using randomization. Compared to three recently proposed alternatives, the CG algorithm dominates the accuracy-simplicity trade-off in 8 out of 16 data sets. When maximized for accuracy, CG is competitive with rule learners designed for this purpose, sometimes finding significantly simpler solutions that are no less accurate. Compared to other fair and interpretable classifiers, our method is able to find rule sets that meet stricter notions of fairness with a modest trade-off in accuracy. [abs] [ pdf ][ bib ] &copy JMLR 2023. ( edit, beta )

PDF Details

UAI Conference 2023 Conference Paper

Interpretable differencing of machine learning models

Swagatam Haldar
Diptikalyan Saha
Dennis Wei
Rahul Nair 0004
Elizabeth M. Daly

Understanding the differences between machine learning (ML) models is of interest in scenarios ranging from choosing amongst a set of competing models, to updating a deployed model with new training data. In these cases, we wish to go beyond differences in overall metrics such as accuracy to identify where in the feature space do the differences occur. We formalize this problem of model differencing as one of predicting a dissimilarity function of two ML models’ outputs, subject to the representation of the differences being human-interpretable. Our solution is to learn a Joint Surrogate Tree (JST), which is composed of two conjoined decision tree surrogates for the two models. A JST provides an intuitive representation of differences and places the changes in the context of the models’ decision logic. Context is important as it helps users to map differences to an underlying mental model of an AI system. We also propose a refinement procedure to increase the precision of a JST. We demonstrate, through an empirical evaluation, that such contextual differencing is concise and can be achieved with no loss in fidelity over naive approaches.

Details

NeurIPS Conference 2022 Conference Paper

On the Safety of Interpretable Machine Learning: A Maximum Deviation Approach

Dennis Wei
Rahul Nair
Amit Dhurandhar
Kush R. Varshney
Elizabeth Daly
Moninder Singh

Interpretable and explainable machine learning has seen a recent surge of interest. We focus on safety as a key motivation behind the surge and make the relationship between interpretability and safety more quantitative. Toward assessing safety, we introduce the concept of maximum deviation via an optimization problem to find the largest deviation of a supervised learning model from a reference model regarded as safe. We then show how interpretability facilitates this safety assessment. For models including decision trees, generalized linear and additive models, the maximum deviation can be computed exactly and efficiently. For tree ensembles, which are not regarded as interpretable, discrete optimization techniques can still provide informative bounds. For a broader class of piecewise Lipschitz functions, we leverage the multi-armed bandit literature to show that interpretability produces tighter (regret) bounds on the maximum deviation. We present case studies, including one on mortgage approval, to illustrate our methods and the insights about models that may be obtained from deviation maximization.

PDF Details

NeurIPS Conference 2021 Conference Paper

CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions

Isha Puri
Amit Dhurandhar
Tejaswini Pedapati
Karthikeyan Shanmugam
Dennis Wei
Kush R. Varshney

In recent years there has been a considerable amount of research on local post hoc explanations for neural networks. However, work on building interpretable neural architectures has been relatively sparse. In this paper, we present a novel neural architecture, CoFrNet, inspired by the form of continued fractions which are known to have many attractive properties in number theory, such as fast convergence of approximations to real numbers. We show that CoFrNets can be efficiently trained as well as interpreted leveraging their particular functional form. Moreover, we prove that such architectures are universal approximators based on a proof strategy that is different than the typical strategy used to prove universal approximation results for neural networks based on infinite width (or depth), which is likely to be of independent interest. We experiment on nonlinear synthetic functions and are able to accurately model as well as estimate feature attributions and even higher order terms in some cases, which is a testament to the representational power as well as interpretability of such architectures. To further showcase the power of CoFrNets, we experiment on seven real datasets spanning tabular, text and image modalities, and show that they are either comparable or significantly better than other interpretable models and multilayer perceptrons, sometimes approaching the accuracies of state-of-the-art models.

PDF Details

UAI Conference 2021 Conference Paper

Conditionally independent data generation

Kartik Ahuja
Prasanna Sattigeri
Karthikeyan Shanmugam 0001
Dennis Wei
Karthikeyan Natesan Ramamurthy
Murat Kocaoglu

Conditional independence (CI) is a fundamental concept with wide applications in machine learning and causal inference. Although the problems of testing CI and estimating divergences have been extensively studied, the complementary problem of generating data that satisfies CI has received much less attention. A special case of the generation problem is to produce conditionally independent predictions. Given samples from an input data distribution, we formulate the problem of generating samples from a distribution that is close to the input distribution and satisfies CI. We establish a characterization of CI in terms of a general divergence identity. Based on one version of this identity, an architecture is proposed that leverages the capabilities of generative adversarial networks (GANs) to enforce CI in an end-to-end differentiable manner. As one illustration of the problem formulation and architecture, we consider applications to notions of fairness that can be written as CIs, specifically equalized odds and conditional statistical parity. We demonstrate conditionally independent prediction that trades off adherence to fairness criteria against classification accuracy.

Details

ICML Conference 2021 Conference Paper

Decision-Making Under Selective Labels: Optimal Finite-Domain Policies and Beyond

Dennis Wei

Selective labels are a common feature of high-stakes decision-making applications, referring to the lack of observed outcomes under one of the possible decisions. This paper studies the learning of decision policies in the face of selective labels, in an online setting that balances learning costs against future utility. In the homogeneous case in which individuals’ features are disregarded, the optimal decision policy is shown to be a threshold policy. The threshold becomes more stringent as more labels are collected; the rate at which this occurs is characterized. In the case of features drawn from a finite domain, the optimal policy consists of multiple homogeneous policies in parallel. For the general infinite-domain case, the homogeneous policy is extended by using a probabilistic classifier and bootstrapping to provide its inputs. In experiments on synthetic and real data, the proposed policies achieve consistently superior utility with no parameter tuning in the finite-domain case and lower parameter sensitivity in the general case.

Details

JMLR Journal 2021 Journal Article

Optimized Score Transformation for Consistent Fair Classification

Dennis Wei
Karthikeyan Natesan Ramamurthy
Flavio P. Calmon

This paper considers fair probabilistic binary classification where the outputs of primary interest are predicted probabilities, commonly referred to as scores. We formulate the problem of transforming scores to satisfy fairness constraints that are linear in conditional means of scores while minimizing a cross-entropy objective. The formulation can be applied directly to post-process classifier outputs and we also explore a pre-processing extension, thus allowing maximum freedom in selecting a classification algorithm. We derive a closed-form expression for the optimal transformed scores and a convex optimization problem for the transformation parameters. In the population limit, the transformed score function is the fairness-constrained minimizer of cross-entropy with respect to the true conditional probability of the outcome. In the finite sample setting, we propose a method called FairScoreTransformer to approach this solution using a combination of standard probabilistic classifiers and ADMM. We provide several consistency and finite-sample guarantees for FairScoreTransformer, relating to the transformation parameters and transformed score function that it obtains. Comprehensive experiments comparing to 10 existing methods show that FairScoreTransformer has advantages for score-based metrics such as Brier score and AUC while remaining competitive for binary label-based metrics such as accuracy. [abs] [ pdf ][ bib ] &copy JMLR 2021. ( edit, beta )

PDF Details

IJCAI Conference 2021 Conference Paper

What Changed? Interpretable Model Comparison

Rahul Nair
Massimiliano Mattetti
Elizabeth Daly
Dennis Wei
Oznur Alkan
Yunfeng Zhang

We consider the problem of distinguishing two machine learning (ML) models built for the same task in a human-interpretable way. As models can fail or succeed in different ways, classical accuracy metrics may mask crucial qualitative differences. This problem arises in a few contexts. In business applications with periodically retrained models, an updated model may deviate from its predecessor for some segments without a change in overall accuracy. In automated ML systems, where several ML pipelines are generated, the top pipelines have comparable accuracy but may have more subtle differences. We present a method for interpretable comparison of binary classification models by approximating them with Boolean decision rules. We introduce stabilization conditions that allow for the two rule sets to be more directly comparable. A method is proposed to compare two rule sets based on their statistical and semantic similarity by solving assignment problems and highlighting changes. An empirical evaluation on several benchmark datasets illustrates the insights that may be obtained and shows that artificially induced changes can be reliably recovered by our method.

PDF Details DOI

JMLR Journal 2020 Journal Article

AI Explainability 360: An Extensible Toolkit for Understanding Data and Machine Learning Models

Vijay Arya
Rachel K. E. Bellamy
Pin-Yu Chen
Amit Dhurandhar
Michael Hind
Samuel C. Hoffman
Stephanie Houde
Q. Vera Liao

As artificial intelligence algorithms make further inroads in high-stakes societal applications, there are increasing calls from multiple stakeholders for these algorithms to explain their outputs. To make matters more challenging, different personas of consumers of explanations have different requirements for explanations. Toward addressing these needs, we introduce AI Explainability 360, an open-source Python toolkit featuring ten diverse and state-of-the-art explainability methods and two evaluation metrics. Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of interpretation and explanation methods, not only those in the toolkit but also in the broader literature on explainability. For data scientists and other users of the toolkit, we have implemented an extensible software architecture that organizes methods according to their place in the AI modeling pipeline. The toolkit is not only the software, but also guidance material, tutorials, and an interactive web demo to introduce AI explainability to different audiences. Together, our toolkit and taxonomy can help identify gaps where more explainability methods are needed and provide a platform to incorporate them as they are developed. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2020. ( edit, beta )

PDF Details

NeurIPS Conference 2020 Conference Paper

DAGs with No Fears: A Closer Look at Continuous Optimization for Learning Bayesian Networks

Dennis Wei
Tian Gao
Yue Yu

This paper re-examines a continuous optimization framework dubbed NOTEARS for learning Bayesian networks. We first generalize existing algebraic characterizations of acyclicity to a class of matrix polynomials. Next, focusing on a one-parameter-per-edge setting, it is shown that the Karush-Kuhn-Tucker (KKT) optimality conditions for the NOTEARS formulation cannot be satisfied except in a trivial case, which explains a behavior of the associated algorithm. We then derive the KKT conditions for an equivalent reformulation, show that they are indeed necessary, and relate them to explicit constraints that certain edges be absent from the graph. If the score function is convex, these KKT conditions are also sufficient for local minimality despite the non-convexity of the constraint. Informed by the KKT conditions, a local search post-processing algorithm is proposed and shown to substantially and universally improve the structural Hamming distance of all tested algorithms, typically by a factor of 2 or more. Some combinations with local search are both more accurate and more efficient than the original NOTEARS.

PDF Details

ICML Conference 2020 Conference Paper

Is There a Trade-Off Between Fairness and Accuracy? A Perspective Using Mismatched Hypothesis Testing

Sanghamitra Dutta
Dennis Wei
Hazar Yueksel
Pin-Yu Chen
Sijia Liu 0001
Kush R. Varshney

A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease with increased fairness. Novel to this work, we examine fair classification through the lens of mismatched hypothesis testing: trying to find a classifier that distinguishes between two ideal distributions when given two mismatched distributions that are biased. Using Chernoff information, a tool in information theory, we theoretically demonstrate that, contrary to popular belief, there always exist ideal distributions such that optimal fairness and accuracy (with respect to the ideal distributions) are achieved simultaneously: there is no trade-off. Moreover, the same classifier yields the lack of a trade-off with respect to ideal distributions while yielding a trade-off when accuracy is measured with respect to the given (possibly biased) dataset. To complement our main result, we formulate an optimization to find ideal distributions and derive fundamental limits to explain why a trade-off exists on the given biased dataset. We also derive conditions under which active data collection can alleviate the fairness-accuracy trade-off in the real world. Our results lead us to contend that it is problematic to measure accuracy with respect to data that reflects bias, and instead, we should be considering accuracy with respect to ideal, unbiased data.

Details

ICML Conference 2019 Conference Paper

Generalized Linear Rule Models

Dennis Wei
Sanjeeb Dash
Tian Gao
Oktay Günlük

This paper considers generalized linear models using rule-based features, also referred to as rule ensembles, for regression and probabilistic classification. Rules facilitate model interpretation while also capturing nonlinear dependences and interactions. Our problem formulation accordingly trades off rule set complexity and prediction accuracy. Column generation is used to optimize over an exponentially large space of rules without pre-generating a large subset of candidates or greedily boosting rules one by one. The column generation subproblem is solved using either integer programming or a heuristic optimizing the same objective. In experiments involving logistic and linear regression, the proposed methods obtain better accuracy-complexity trade-offs than existing rule ensemble algorithms. At one end of the trade-off, the methods are competitive with less interpretable benchmark models.

Details

NeurIPS Conference 2018 Conference Paper

Boolean Decision Rules via Column Generation

Sanjeeb Dash
Oktay Gunluk
Dennis Wei

This paper considers the learning of Boolean rules in either disjunctive normal form (DNF, OR-of-ANDs, equivalent to decision rule sets) or conjunctive normal form (CNF, AND-of-ORs) as an interpretable model for classification. An integer program is formulated to optimally trade classification accuracy for rule simplicity. Column generation (CG) is used to efficiently search over an exponential number of candidate clauses (conjunctions or disjunctions) without the need for heuristic rule mining. This approach also bounds the gap between the selected rule set and the best possible rule set on the training data. To handle large datasets, we propose an approximate CG algorithm using randomization. Compared to three recently proposed alternatives, the CG algorithm dominates the accuracy-simplicity trade-off in 8 out of 16 datasets. When maximized for accuracy, CG is competitive with rule learners designed for this purpose, sometimes finding significantly simpler solutions that are no less accurate.

PDF Details

ICML Conference 2018 Conference Paper

Parallel Bayesian Network Structure Learning

Tian Gao
Dennis Wei

Recent advances in Bayesian Network (BN) structure learning have focused on local-to-global learning, where the graph structure is learned via one local subgraph at a time. As a natural progression, we investigate parallel learning of BN structures via multiple learning agents simultaneously, where each agent learns one local subgraph at a time. We find that parallel learning can reduce the number of subgraphs requiring structure learning by storing previously queried results and communicating (even partial) results among agents. More specifically, by using novel rules on query subset and superset inference, many subgraph structures can be inferred without learning. We provide a sound and complete parallel structure learning (PSL) algorithm, and demonstrate its improved efficiency over state-of-the-art single-thread learning algorithms.

Details

NeurIPS Conference 2017 Conference Paper

Optimized Pre-Processing for Discrimination Prevention

Flavio Calmon
Dennis Wei
Bhanukiran Vinzamuri
Karthikeyan Natesan Ramamurthy
Kush Varshney

Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a data transformation with three goals: controlling discrimination, limiting distortion in individual data samples, and preserving utility. We characterize the impact of limited sample size in accomplishing this objective. Two instances of the proposed optimization are applied to datasets, including one on real-world criminal recidivism. Results show that discrimination can be greatly reduced at a small cost in classification accuracy.

PDF Details

NeurIPS Conference 2016 Conference Paper

A Constant-Factor Bi-Criteria Approximation Guarantee for k-means++

Dennis Wei

This paper studies the $k$-means++ algorithm for clustering as well as the class of $D^\ell$ sampling algorithms to which $k$-means++ belongs. It is shown that for any constant factor $\beta > 1$, selecting $\beta k$ cluster centers by $D^\ell$ sampling yields a constant-factor approximation to the optimal clustering with $k$ centers, in expectation and without conditions on the dataset. This result extends the previously known $O(\log k)$ guarantee for the case $\beta = 1$ to the constant-factor bi-criteria regime. It also improves upon an existing constant-factor bi-criteria result that holds only with constant probability.

PDF Details