The Ethical Algorithm: The Science of Socially Aware Algorithm Design

2021

Citations in the corpus

• Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020, neutral): “For an accessible discussion of the ideas behind differential privacy and its applications, from which this short summary was adapted, see [99].”
• Towards causal benchmarking of bias in face analysis algorithms (2020, unknown): “Singleattribute analysis may conceal biases affecting groups defined by the combination of multiple attributes [40].”
• Improving Gender Translation Accuracy with Filtered Self-Training (2021, unknown): “Recent work has drawn attention to the harms that machine learning algorithms can cause by reflect-ing or even amplifying data biases against protected groups (Barocas et al., 2019; Kearns and Roth, 2019).”
• Large-Scale Differentially Private BERT (2021, unknown): “The widespread deployment of machine learning in recent years has raised serious concerns about the privacy of users whose data is used during the training process (see, e.g., (Kearns and Roth, 2019)).”
• LQF: Linear Quadratic Fine-Tuning (2020, unknown): “We leave various applications of LQF to future work, including its use in (i) uncertainty quantification, (ii) backward compatibility [44], (iii) leave-one-out cross validation without a validation set [9], (iv) active/online learning [45], (v) counterfactual analysis in the first order, (vi) contin”