1 code implementation • 3 Apr 2024 • Hussein Mozannar, Valerie Chen, Mohammed Alsobay, Subhro Das, Sebastian Zhao, Dennis Wei, Manish Nagireddy, Prasanna Sattigeri, Ameet Talwalkar, David Sontag
Evaluation of large language models (LLMs) for code has primarily relied on static benchmarks, including HumanEval (Chen et al., 2021), which measure the ability of LLMs to generate complete code that passes unit tests.
no code implementations • 21 Mar 2024 • Lucas Monteiro Paes, Dennis Wei, Hyo Jin Do, Hendrik Strobelt, Ronny Luss, Amit Dhurandhar, Manish Nagireddy, Karthikeyan Natesan Ramamurthy, Prasanna Sattigeri, Werner Geyer, Soumya Ghosh
To address the challenges of text as output and long text inputs, we propose a general framework called MExGen that can be instantiated with different attribution algorithms.
no code implementations • 9 Mar 2024 • Swapnaja Achintalwar, Adriana Alvarado Garcia, Ateret Anaby-Tavor, Ioana Baldini, Sara E. Berger, Bishwaranjan Bhattacharjee, Djallel Bouneffouf, Subhajit Chaudhury, Pin-Yu Chen, Lamogha Chiazor, Elizabeth M. Daly, Rogério Abreu de Paula, Pierre Dognin, Eitan Farchi, Soumya Ghosh, Michael Hind, Raya Horesh, George Kour, Ja Young Lee, Erik Miehling, Keerthiram Murugesan, Manish Nagireddy, Inkit Padhi, David Piorkowski, Ambrish Rawat, Orna Raz, Prasanna Sattigeri, Hendrik Strobelt, Sarathkrishna Swaminathan, Christoph Tillmann, Aashka Trivedi, Kush R. Varshney, Dennis Wei, Shalisha Witherspooon, Marcel Zalmanovici
Large language models (LLMs) are susceptible to a variety of risks, from non-faithful output to biased and toxic generations.
no code implementations • 1 Mar 2024 • Zirui Yan, Dennis Wei, Dmitriy Katz-Rogozhnikov, Prasanna Sattigeri, Ali Tajer
First, the structural causal models (SCMs) are assumed to be unknown and drawn arbitrarily from a general class $\mathcal{F}$ of Lipschitz-continuous functions.
no code implementations • 17 Feb 2024 • Amit Dhurandhar, Swagatam Haldar, Dennis Wei, Karthikeyan Natesan Ramamurthy
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.
1 code implementation • NeurIPS 2023 • Hussein Mozannar, Jimin J Lee, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag
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.
1 code implementation • 19 Oct 2023 • Chongyu Fan, Jiancheng Liu, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu
To address these challenges, we introduce the concept of 'weight saliency' for MU, drawing parallels with input saliency in model explanation.
1 code implementation • 10 Jun 2023 • Swagatam Haldar, Diptikalyan Saha, Dennis Wei, Rahul Nair, 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.
1 code implementation • 3 Mar 2023 • Dennis Wei, Haoze Wu, Min Wu, Pin-Yu Chen, Clark Barrett, Eitan Farchi
The softmax function is a ubiquitous component at the output of neural networks and increasingly in intermediate layers as well.
1 code implementation • 15 Jan 2023 • Hussein Mozannar, Hunter Lang, Dennis Wei, Prasanna Sattigeri, Subhro Das, David Sontag
We show that prior approaches can fail to find a human-AI system with low misclassification error even when there exists a linear classifier and rejector that have zero error (the realizable setting).
no code implementations • 2 Nov 2022 • Dennis Wei, Rahul Nair, Amit Dhurandhar, Kush R. Varshney, Elizabeth M. Daly, Moninder Singh
Interpretable and explainable machine learning has seen a recent surge of interest.
no code implementations • 9 Mar 2022 • Karan Bhanot, Ioana Baldini, Dennis Wei, Jiaming Zeng, Kristin P. Bennett
In this paper, we evaluate the fairness of models generated on two healthcare datasets for gender and race biases.
no code implementations • 2 Feb 2022 • Karthikeyan Natesan Ramamurthy, Amit Dhurandhar, Dennis Wei, Zaid Bin Tariq
We first propose a method that provides feature attributions to explain the similarity between a pair of inputs as determined by a black box similarity learner.
no code implementations • 4 Jan 2022 • Öznur Alkan, Dennis Wei, Massimiliano Mattetti, Rahul Nair, Elizabeth M. Daly, Diptikalyan Saha
However, in such scenarios, it may take time for sufficient training data to accumulate in order to retrain the model to reflect the new decision boundaries.
no code implementations • 7 Dec 2021 • Kofi Arhin, Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy, Moninder Singh
The use of machine learning (ML)-based language models (LMs) to monitor content online is on the rise.
no code implementations • NeurIPS 2021 • Isha Puri, Amit Dhurandhar, Tejaswini Pedapati, Karthikeyan Shanmugam, Dennis Wei, Kush R. Varshney
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.
no code implementations • 16 Nov 2021 • 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.
no code implementations • 24 Sep 2021 • Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilovic, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang
As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these algorithms to provide explanations.
no code implementations • Findings (ACL) 2022 • Ioana Baldini, Dennis Wei, Karthikeyan Natesan Ramamurthy, Mikhail Yurochkin, Moninder Singh
Through the analysis of more than a dozen pretrained language models of varying sizes on two toxic text classification tasks (English), we demonstrate that focusing on accuracy measures alone can lead to models with wide variation in fairness characteristics.
2 code implementations • 13 Mar 2021 • Abhin Shah, Kartik Ahuja, Karthikeyan Shanmugam, Dennis Wei, Kush Varshney, Amit Dhurandhar
Inferring causal individual treatment effect (ITE) from observational data is a challenging problem whose difficulty is exacerbated by the presence of treatment assignment bias.
no code implementations • 2 Nov 2020 • Dennis Wei
Selective labels are a common feature of consequential decision-making applications, referring to the lack of observed outcomes under one of the possible decisions.
1 code implementation • NeurIPS 2020 • Dennis Wei, Tian Gao, Yue Yu
This paper re-examines a continuous optimization framework dubbed NOTEARS for learning Bayesian networks.
no code implementations • 15 Oct 2020 • Charvi Rastogi, Yunfeng Zhang, Dennis Wei, Kush R. Varshney, Amit Dhurandhar, Richard Tomsett
We, then, conduct a second user experiment which shows that our time allocation strategy with explanation can effectively de-anchor the human and improve collaborative performance when the AI model has low confidence and is incorrect.
no code implementations • 13 Jan 2020 • Michael Hind, Dennis Wei, Yunfeng Zhang
Many proposed methods for explaining machine learning predictions are in fact challenging to understand for nontechnical consumers.
no code implementations • ICML 2020 • Sanghamitra Dutta, Dennis Wei, Hazar Yueksel, Pin-Yu Chen, Sijia Liu, Kush R. Varshney
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.
2 code implementations • 6 Sep 2019 • Vijay Arya, Rachel K. E. Bellamy, Pin-Yu Chen, Amit Dhurandhar, Michael Hind, Samuel C. Hoffman, Stephanie Houde, Q. Vera Liao, Ronny Luss, Aleksandra Mojsilović, Sami Mourad, Pablo Pedemonte, Ramya Raghavendra, John Richards, Prasanna Sattigeri, Karthikeyan Shanmugam, Moninder Singh, Kush R. Varshney, Dennis Wei, Yunfeng Zhang
Equally important, we provide a taxonomy to help entities requiring explanations to navigate the space of explanation methods, not only those in the toolkit but also in the broader literature on explainability.
1 code implementation • 9 Jul 2019 • Michael Oberst, Fredrik D. Johansson, Dennis Wei, Tian Gao, Gabriel Brat, David Sontag, Kush R. Varshney
Overlap between treatment groups is required for non-parametric estimation of causal effects.
no code implementations • 5 Jun 2019 • Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush R. Varshney, Dennis Wei, Aleksandra Mojsilović
Using machine learning in high-stakes applications often requires predictions to be accompanied by explanations comprehensible to the domain user, who has ultimate responsibility for decisions and outcomes.
no code implementations • 5 Jun 2019 • Dennis Wei, Sanjeeb Dash, Tian Gao, Oktay Günlük
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.
no code implementations • 31 May 2019 • Dennis Wei, Karthikeyan Natesan Ramamurthy, Flavio du Pin Calmon
We derive a closed-form expression for the optimal transformed scores and a convex optimization problem for the transformation parameters.
no code implementations • 8 May 2019 • Chirag Nagpal, Dennis Wei, Bhanukiran Vinzamuri, Monica Shekhar, Sara E. Berger, Subhro Das, Kush R. Varshney
The dearth of prescribing guidelines for physicians is one key driver of the current opioid epidemic in the United States.
no code implementations • 12 Nov 2018 • Michael Hind, Dennis Wei, Murray Campbell, Noel C. F. Codella, Amit Dhurandhar, Aleksandra Mojsilović, Karthikeyan Natesan Ramamurthy, Kush R. Varshney
Artificial intelligence systems are being increasingly deployed due to their potential to increase the efficiency, scale, consistency, fairness, and accuracy of decisions.
no code implementations • ICML 2018 • 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.
no code implementations • 29 May 2018 • Noel C. F. Codella, Michael Hind, Karthikeyan Natesan Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush R. Varshney, Dennis Wei, Aleksandra Mojsilovic
The adoption of machine learning in high-stakes applications such as healthcare and law has lagged in part because predictions are not accompanied by explanations comprehensible to the domain user, who often holds the ultimate responsibility for decisions and outcomes.
no code implementations • NeurIPS 2018 • Sanjeeb Dash, Oktay Günlük, 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.
no code implementations • 9 Apr 2018 • Pin-Yu Chen, Dennis Wei
Active graph-based semi-supervised learning (AG-SSL) aims to select a small set of labeled examples and utilize their graph-based relation to other unlabeled examples to aid in machine learning tasks.
no code implementations • NeurIPS 2017 • Flavio Calmon, Dennis Wei, Bhanukiran Vinzamuri, Karthikeyan Natesan Ramamurthy, Kush R. Varshney
Non-discrimination is a recognized objective in algorithmic decision making.
no code implementations • 5 Nov 2017 • Dennis Wei, Karthikeyan Natesan Ramamurthy, Kush R. Varshney
Preserving the privacy of individuals by protecting their sensitive attributes is an important consideration during microdata release.
1 code implementation • 11 Apr 2017 • Flavio P. Calmon, Dennis Wei, Karthikeyan Natesan Ramamurthy, Kush R. Varshney
Non-discrimination is a recognized objective in algorithmic decision making.
no code implementations • NeurIPS 2016 • 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.
no code implementations • 18 Jun 2016 • Guolong Su, Dennis Wei, Kush R. Varshney, Dmitry M. Malioutov
As a contribution to interpretable machine learning research, we develop a novel optimization framework for learning accurate and sparse two-level Boolean rules.
no code implementations • 16 May 2016 • 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.
no code implementations • 23 Nov 2015 • Guolong Su, Dennis Wei, Kush R. Varshney, Dmitry M. Malioutov
Experiments show that the two-level rules can yield noticeably better performance than one-level rules due to their dramatically larger modeling capacity, and the two algorithms based on the Hamming distance formulation are generally superior to the other two-level rule learning methods in our comparison.
no code implementations • 15 Mar 2015 • Yu-Hui Chen, Dennis Wei, Gregory Newstadt, Marc DeGraef, Jeffrey Simmons, Alfred Hero
We treat the problem of estimation of orientation parameters whose values are invariant to transformations from a spherical symmetry group.
no code implementations • 26 Feb 2015 • Yu-Hui Chen, Se Un Park, Dennis Wei, Gregory Newstadt, Michael Jackson, Jeff P. Simmons, Marc De Graef, Alfred O. Hero
We discretize the domain of the forward model onto a dense grid of Euler angles and for each measured pattern we identify the most similar patterns in the dictionary.
no code implementations • 26 Feb 2015 • Yu-Hui Chen, Dennis Wei, Gregory Newstadt, Jeffrey Simmons, Alfred Hero
We propose a coercive approach to simultaneously register and segment multi-modal images which share similar spatial structure.
no code implementations • 10 Nov 2014 • Yu-Hui Chen, Dennis Wei, Gregory Newstadt, Marc DeGraef, Jeffrey Simmons, Alfred Hero
This paper considers statistical estimation problems where the probability distribution of the observed random variable is invariant with respect to actions of a finite topological group.
no code implementations • 13 Mar 2014 • Hamed Firouzi, Dennis Wei, Alfred O. Hero III
This property permits independent correlation analysis at each frequency, alleviating the computational and statistical challenges of high-dimensional time series.
no code implementations • 19 Mar 2013 • Zhaoshi Meng, Dennis Wei, Ami Wiesel, Alfred O. Hero III
In this paper, we propose a general framework for distributed estimation based on a maximum marginal likelihood (MML) approach.