1 code implementation • 21 Aug 2023 • Arka Pal, Deep Karkhanis, Manley Roberts, Samuel Dooley, Arvind Sundararajan, Siddartha Naidu
To use these models on sequences longer than the train-time context length, one might employ techniques from the growing family of context length extrapolation methods -- most of which focus on modifying the system of positional encodings used in the attention mechanism to indicate where tokens or activations are located in the input sequence.
2 code implementations • 22 Feb 2018 • Darius Lam, Richard Kuzma, Kevin McGee, Samuel Dooley, Michael Laielli, Matthew Klaric, Yaroslav Bulatov, Brendan McCord
We introduce a new large-scale dataset for the advancement of object detection techniques and overhead object detection research.
2 code implementations • NeurIPS 2023 • Samuel Dooley, Rhea Sanjay Sukthanker, John P. Dickerson, Colin White, Frank Hutter, Micah Goldblum
Our search outputs a suite of models which Pareto-dominate all other high-performance architectures and existing bias mitigation methods in terms of accuracy and fairness, often by large margins, on the two most widely used datasets for face identification, CelebA and VGGFace2.
1 code implementation • 20 Feb 2024 • Arka Pal, Deep Karkhanis, Samuel Dooley, Manley Roberts, Siddartha Naidu, Colin White
In this work, first we show theoretically that the standard DPO loss can lead to a \textit{reduction} of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases.
1 code implementation • NeurIPS 2023 • Samuel Dooley, Gurnoor Singh Khurana, Chirag Mohapatra, Siddartha Naidu, Colin White
The vast majority of time-series forecasting approaches require a substantial training dataset.
1 code implementation • NeurIPS 2021 • Neehar Peri, Michael J. Curry, Samuel Dooley, John P. Dickerson
In addition, we introduce a new metric to evaluate an auction allocations' adherence to such socially desirable constraints and demonstrate that our proposed method is competitive with current state-of-the-art neural-network based auction designs.
1 code implementation • 17 Jun 2020 • Vedant Nanda, Samuel Dooley, Sahil Singla, Soheil Feizi, John P. Dickerson
In this paper, we argue that traditional notions of fairness that are only based on models' outputs are not sufficient when the model is vulnerable to adversarial attacks.
1 code implementation • 27 Aug 2021 • Samuel Dooley, Tom Goldstein, John P. Dickerson
Facial detection and analysis systems have been deployed by large companies and critiqued by scholars and activists for the past decade.
2 code implementations • 29 Nov 2022 • Samuel Dooley, George Z. Wei, Tom Goldstein, John P. Dickerson
Many existing algorithmic audits examine the performance of these systems on later stage elements of facial analysis systems like facial recognition and age, emotion, or perceived gender prediction; however, a core component to these systems has been vastly understudied from a fairness perspective: face detection, sometimes called face localization.
1 code implementation • 16 Oct 2023 • Manley Roberts, Himanshu Thakur, Christine Herlihy, Colin White, Samuel Dooley
Recent claims about the impressive abilities of large language models (LLMs) are often supported by evaluating publicly available benchmarks.
1 code implementation • 28 Feb 2024 • Rhea Sanjay Sukthanker, Arber Zela, Benedikt Staffler, Samuel Dooley, Josif Grabocka, Frank Hutter
Pareto front profiling in multi-objective optimization (MOO), i. e. finding a diverse set of Pareto optimal solutions, is challenging, especially with expensive objectives like neural network training.
no code implementations • 7 Aug 2018 • Eliza Mace, Keith Manville, Monica Barbu-McInnis, Michael Laielli, Matthew Klaric, Samuel Dooley
Specifically, we examine how various features of the data affect building detection accuracy with respect to the Intersection over Union metric.
no code implementations • 24 Sep 2020 • Samuel Dooley, John P. Dickerson
We model this affiliate matching problem in a generalization of the classic stable marriage setting by permitting firms to state preferences over not just which workers to whom they are matched, but also to which firms their affiliated workers are matched.
no code implementations • 13 Oct 2020 • Kevin Kuo, Anthony Ostuni, Elizabeth Horishny, Michael J. Curry, Samuel Dooley, Ping-Yeh Chiang, Tom Goldstein, John P. Dickerson
Inspired by these advances, in this paper, we extend techniques for approximating auctions using deep learning to address concerns of fairness while maintaining high revenue and strong incentive guarantees.
no code implementations • 15 Oct 2021 • Samuel Dooley, Ryan Downing, George Wei, Nathan Shankar, Bradon Thymes, Gudrun Thorkelsdottir, Tiye Kurtz-Miott, Rachel Mattson, Olufemi Obiwumi, Valeriia Cherepanova, Micah Goldblum, John P Dickerson, Tom Goldstein
Much recent research has uncovered and discussed serious concerns of bias in facial analysis technologies, finding performance disparities between groups of people based on perceived gender, skin type, lighting condition, etc.
no code implementations • 25 Jan 2022 • Samuel Dooley, George Z. Wei, Tom Goldstein, John P. Dickerson
When we compare the size of these disparities to that of commercial models, we conclude that commercial models - in contrast to their relatively larger development budget and industry-level fairness commitments - are always as biased or more biased than an academic model.
no code implementations • 22 Feb 2022 • Marina Knittel, Samuel Dooley, John P. Dickerson
We also assume the agent's preferences over entire matchings are determined by a general weighted valuation function of their (and their affiliates') matches.
no code implementations • 1 Mar 2022 • Michael Rawson, Samuel Dooley, Mithun Bharadwaj, Rishabh Choudhary
We develop and test a novel unsupervised algorithm for word sense induction and disambiguation which uses topological data analysis.
no code implementations • 15 Mar 2022 • Valeriia Cherepanova, Steven Reich, Samuel Dooley, Hossein Souri, Micah Goldblum, Tom Goldstein
This is an unfortunate omission, as 'imbalance' is a more complex matter in identification; imbalance may arise in not only the training data, but also the testing data, and furthermore may affect the proportion of identities belonging to each demographic group or the number of images belonging to each identity.
no code implementations • 2 Nov 2022 • Samuel Dooley
As such, in this work, I make comparative analyses between humans and machines in three scenarios and seek to understand how sentiment about a technology, performance of that technology, and the impacts of that technology combine to influence how one decides to answer my main research question.
no code implementations • 18 Oct 2023 • Richeek Das, Samuel Dooley
Making models algorithmically fairer in tabular data has been long studied, with techniques typically oriented towards fixes which usually take a neural model with an undesirable outcome and make changes to how the data are ingested, what the model weights are, or how outputs are processed.