Search Results for author:
Found 16 papers, 7 papers with code
On the Standardization of Behavioral Use Clauses and Their Adoption for Responsible Licensing of AI
As of the end of 2023, on the order of 40, 000 software and model repositories have adopted responsible AI licenses licenses.
Scalable Extraction of Training Data from (Production) Language Models
This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset.
CommonCanvas: An Open Diffusion Model Trained with Creative-Commons Images
This task presents two challenges: (1) high-resolution CC images lack the captions necessary to train text-to-image generative models; (2) CC images are relatively scarce.
Coordinating Distributed Example Orders for Provably Accelerated Training
Recent research on online Gradient Balancing (GraB) has revealed that there exist permutation-based example orderings for SGD that are guaranteed to outperform random reshuffling (RR).
Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
Variance in predictions across different trained models is a significant, under-explored source of error in fair binary classification.
Non-Determinism and the Lawlessness of Machine Learning Code
In this paper, we clarify the overlap and differences between these two concepts, and show that the effects of non-determinism, and consequently its implications for the law, become clearer from the perspective of reasoning about ML outputs as distributions over possible outcomes.
Repairing Regressors for Fair Binary Classification at Any Decision Threshold
We study the problem of post-processing a supervised machine-learned regressor to maximize fair binary classification at all decision thresholds.
Accountability in an Algorithmic Society: Relationality, Responsibility, and Robustness in Machine Learning
In 1996, Accountability in a Computerized Society [95] issued a clarion call concerning the erosion of accountability in society due to the ubiquitous delegation of consequential functions to computerized systems.
Tecnologica cosa: Modeling Storyteller Personalities in Boccaccio's Decameron
We explore Boccaccio's Decameron to see how digital humanities tools can be used for tasks that have limited data in a language no longer in contemporary use: medieval Italian.
Model Selection's Disparate Impact in Real-World Deep Learning Applications
Algorithmic fairness has emphasized the role of biased data in automated decision outcomes.
Hyperparameter Optimization Is Deceiving Us, and How to Stop It
Recent empirical work shows that inconsistent results based on choice of hyperparameter optimization (HPO) configuration are a widespread problem in ML research.
Emergent Unfairness in Algorithmic Fairness-Accuracy Trade-Off Research
Across machine learning (ML) sub-disciplines, researchers make explicit mathematical assumptions in order to facilitate proof-writing.
Where Is the Normative Proof? Assumptions and Contradictions in ML Fairness Research
This is because, similar to how mathematical assumptions constrain applicability, normative assumptions also limit algorithm applicability to certain problem domains.
Accuracy-Efficiency Trade-Offs and Accountability in Distributed ML Systems
Trade-offs between accuracy and efficiency pervade law, public health, and other non-computing domains, which have developed policies to guide how to balance the two in conditions of uncertainty.
Asymptotically Optimal Exact Minibatch Metropolis-Hastings
Metropolis-Hastings (MH) is a commonly-used MCMC algorithm, but it can be intractable on large datasets due to requiring computations over the whole dataset.
AMAGOLD: Amortized Metropolis Adjustment for Efficient Stochastic Gradient MCMC
This improves performance, but introduces bias that can cause SGHMC to converge to the wrong distribution.
