Kristian Lum

Artificial Intelligence · 2012–2021

A researcher in the Science corpus: 8 papers; trusts 32 researchers and is trusted by 31 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 67 citations into it; #6,937 of 35,345 by trust here, #11,327 by citations
• Sociology and Political Science — 66 citations into it; #2,562 of 22,756 by trust here, #5,224 by citations
• Safety, Robustness & Interpretability — 54 citations into it
• Safety Research — 44 citations into it; #625 of 5,829 by trust here, #1,193 by citations
• AI Ethics, Fairness & Society — 43 citations into it; #89 of 494 by trust here, #174 by citations
• Statistics and Probability — 36 citations into it
• Clinical Psychology — 24 citations into it
• Evaluation & Benchmarks — 16 citations into it

Whom Kristian Lum trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Faisal Kamiran
2. Toon Calders
3. Kevin A. Clarke
4. Jerome P. Reiter
5. Michael Feldman
6. M. Hoffman
7. S. van Buuren
8. Alexandra Chouldechova
9. Cynthia Dwork
10. Sorelle A. Friedler

Who trusts Kristian Lum overall

1. Luca Oneto
2. Silvia Chiappa
3. Alexandre Louis Lamy
4. Marco Geraci
5. Yunwen Yang
6. Shira Mitchell
7. Alexandra Chouldechova
8. D. Ensign
9. Sirui Yao
10. Simon Caton

Papers from Kristian Lum's perspective

Ordered by how strongly the researchers Kristian Lum trusts endorse each paper. Same corpus, a different order for every researcher.

1. Classifying without discriminating
2. Big Data's Disparate Impact
3. Three naive Bayes approaches for discrimination-free classification
4. A multidisciplinary survey on discrimination analysis
5. Certifying and Removing Disparate Impact
6. Inherent Trade-Offs in the Fair Determination of Risk Scores
7. Counterfactual Fairness (Neural Information Processing Systems)
8. Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification
9. Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
10. Avoiding Discrimination through Causal Reasoning

Their papers

• An algorithm for removing sensitive information: Application to race-independent recidivism prediction (2017) — 178 citations
• It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks (2021) — 118 citations
• Layers of Bias: A Unified Approach for Understanding Problems With Risk Assessment (2018) — 144 citations
• A statistical framework for fair predictive algorithms (2016) — 114 citations
• Spatial Quantile Multiple Regression Using the Asymmetric Laplace Process (2012) — 115 citations
• Algorithmic Fairness: Choices, Assumptions, and Definitions (2021) — 600 citations
• Limitations of mitigating judicial bias with machine learning (2017) — 34 citations
• To predict and serve? (2016)