Joshua Loftus
Assistant Professor
Department of Statistics, London School of Economics
About
I am a statistician working to improve practices in data science to reduce the impact of bias, particularly biases associated with social harms and scientific reproducibility. I research algorithmic fairness, high-dimensional inference, and interpretable machine learning, and I teach ethical and responsible data science, machine learning, and causal inference.
Current Positions
Jan. 2021-
London School of
Economics Assistant Professor of Statistics (London, UK)
Jan. 2021-
LSE Data Science
Institute Affiliate Faculty (London, UK)
Education
2016
Stanford University PhD in
Statistics (Stanford, CA)
- Dissertation: Post-selection inference for models characterized by quadratic constraints
- Committee: Jonathan Taylor (advisor), Emmanuel Candes, Joseph Romano, Robert Tibshirani
2011
Rutgers University M.S. in
Mathematics (New Brunswick, NJ)
- Thesis: Logarithmic norms and applications to differential equations
- Supervisor: Eduardo Sontag
2009
Western Michigan University
B.S. in Mathematics (Kalamazoo, MI)
- Summa cum laude
- Elected to Phi Beta Kappa
2007
Kalamazoo Valley Community
College A.A. in General Studies (Kalamazoo, MI)
Experience
2017-2020
New York University
Assistant Professor of Statistics (New York, NY)
2019-2020
NYU Center for Data
Science Affiliate Faculty (New York, NY)
2016-
Statistical Consultant
Freelance (Various)
2016-2017
University of Cambridge
Research Fellow (Cambridge, UK)
2016-2017
Alan Turing Institute
Research Fellow (London, UK)
2014-2015
Stanford University
Statistical Consulting Lab Manager (Stanford, CA)
Selected Publications
Google Scholar citation count: 2098
Journals
2018
Selective inference with unknown variance via
the square‐root lasso. Tian, X., Loftus, J. R.,
Taylor, J. E
Biometrika. (arXiv, link)
2016
Inference in adaptive regression via the
Kac–Rice formula. Taylor, J. E., Loftus, J. R.,
Tibshirani, R. J.
Annals of Statistics. (arXiv, link)
Conferences
2023
Counterfactuals for the future. Bynum, L. E.,
Loftus, J. R., Stoyanovich, J.
Proceedings of the AAAI Conference on Artificial
Intelligence. (arXiv, link)
2021
Causal Intersectionality and Fair Ranking. Yang,
K., Loftus, J. R., Stoyanovich, J.
2nd
Symposium on Foundations of Responsible Computing. (arXiv, link)
2021
Disaggregated interventions to reduce
inequality. Bynum, L., Loftus, J. R.,
Stoyanovich, J.
Equity and Access in Algorithms,
Mechanisms, and Optimization. (arXiv, link)
2019
Making decisions that reduce discriminatory
impacts. Kusner, M., Russell, C., Loftus, J. R.,
Silva, R.
International Conference on Machine
Learning. (arXiv, link)
2017
When worlds collide: Integrating different
counterfactual assumptions in fairness. Russell et al.
Advances in Neural Information Processing Systems. (arXiv, link)
2017
Counterfactual fairness. Kusner, M. J.,
Loftus, J. R., Russell, C., Silva, R.
Advances in Neural Information Processing Systems. (arXiv, link)
Software
2022
unbiasedgoodness: Goodness-of-Fit Tests After
Model Selection. Loftus, J. R.
R
Package. (arXiv, link)
2015
selectiveInference: Tools for selective
inference. Tibshirani et al.
CRAN R Package. (arXiv, link)
Preprints, Misc.
2023
Causal Dependence Plots for Interpretable
Machine Learning. Loftus, J. R. et al.
Preprint. (arXiv, link)
2022
An Interactive Introduction to Causal Inference.
Bynum et al.
IEEE VISxAI: Workshop on Visualization for
AI Explainability. (arXiv, link)
2020
The long road to fairer algorithms. Kusner, M.
J., Loftus, J. R..
Nature
Comment. (arXiv, link)
2018
Causal reasoning for algorithmic fairness.
Loftus, J. R., Russell, C., Kusner, M. J., Silva,
R.
Preprint. (arXiv, link)
2015
Selective inference after cross‐validation.
Loftus, J. R.
Preprint. (arXiv, link)
Awards and Honors
2015
NIH Grant Trainee in Biostatistics for
Personalized Medicine (Stanford University)
2015
Alan M. Abrams Memorial Fellowship (Stanford
University)
2014
Statistics Department Teaching Award (Stanford
University)
2013
Best Potential Prize (Stanford-Columbia
DataFest)
2012
NSF VIGRE Fellowship (Stanford University)
2010
GAANN Fellowship (Rutgers University)
Selected Talks
2022
IMS International Conference on Statistics and
Data Science (Florence, IT)
2022
Panelist at NeurIPS Workshop on Algorithmic
Fairness (New Orleans, LA)
2022
Keynote at International Meeting of Psychometric
Society (Bologna, IT)
2021
Bernoulli-IMS 10th World Congress in Probability
and Statistics (Seoul (virtual))
2021
NYU Workshop on Race and Racism in Science (New
York (virtual))
2021
Conference on Machine Learning and Economic
Inequality (Oxford (virtual))
2019
International Indian Statistical Association
Conference (Mumbai, India)
2019
DataEngConf (New York, NY)
2019
INFORMS Annual Meeting. Session on Fairness in
Machine Learning (Seattle, WA)
2019
Joint Statistical Meetings (Denver, CO)
2019
Econometrics and Statistics Conference
(Taichung, Taiwan)
2019
International Conference on Machine Learning
(Long Beach, CA)
2019
International Chinese Statistical Association
Conference (Raleigh, NC)
2018
Data for Good Seminar (Columbia University)
2018
Workshop on Higher-Order Asymptotics and
Post-Selection Inference (WUSTL)
2018
Conference on Statistical Learning and Data
Science (Columbia University)
2015
IMS session on Post-Selection Inference. Joint
Statistical Meetings (Seattle, WA)
2014
Joint Statistical Meetings (Boston, MA)
Research Experience
2021-
London School of Economics
Assistant Professor of Statistics (London, UK)
- Data science research group
- Supervising PhD students and serving on dissertation committees
2017-2020
New York University
Assistant Professor of Statistics (New York, NY)
- Organizing journal club
- Supervising PhD students and serving on dissertation committees
2016-2017
University of Cambridge / Alan
Turing Institute Research Fellow (Cambridge / London, UK)
- Started research on counterfactual fairness
- Co-supervised summer internship project on privacy
2012-2016
Stanford University
Research Assistant (Stanford, CA)
- Started research on post-selection inference
- Participated in Tibshirani, Hastie, Taylor research group
- Organized statistical consulting lab
2013-2015
Stanford University
Biostatistics Trainee (Stanford, CA)
- Funded by NIH training grant
- Collaborated with Howard Chang lab on ATAC-seq data
2014
Stanford University Data Lab
Team Member (Stanford, CA)
- Poverty alleviation project using survey data for small-area poverty estimation
2013
Stanford University Bi-coastal
DataFest Team Leader (Stanford, CA)
- Led prize winning team with project analyzing election campaign finance data
2013
Google, Inc Decision Support
Analyst Intern (Mountain View, CA)
- Conducted literature review and experiments on crowd-sourcing
Teaching Experience
2021-
London School of Economics
Instructor: Machine learning (undergraduate) (London, UK)
- Designed course based on An Introduction to Statistical Learning
- Taught course in Winter 2021, Fall 2021, Fall 2022
2021-
London School of Economics
Co-instructor: Foundations of Machine learning (graduate) (LSE)
- Lectured on support vector machines, high-dimensional regression, neural networks
- Co-taught in Winter terms 2021, 2022, 2023
2022-
London School of Economics
Instructor: Ethics for data science (undergraduate) (LSE)
- Designed course using professional guidelines and research experience
- Taught course in Fall 2022
2021-
London School of Economics
Supervisor: Capstone project (graduate) (LSE)
- Supervising projects for MSc students in Data Science
2018-2020
New York University
Instructor: Regression and forecasting (undergraduate) (New York,
NY)
- Redesigned course to use R instead of Minitab
- Taught course twice per year
2020
New York University Instructor:
Modern statistics and causal inference for data science (graduate)
(NYU)
- Designed course based on Computer Age Statistical Inference and Statistical Learning with Sparsity
2014-2015
Stanford University
Workshop Instructor (graduate) (Stanford, CA)
- Organized statistical consulting lab, taught applied statistics for consulting
- Taught qualifying exams workshop
2012-2016
Stanford University
Teaching Assistant (Stanford)
- PhD: Modern Applied Statistical Learning, Theory of Statistics, Theory of Probability
- Masters: Introduction to Statistical Inference, Data Mining and Analysis
- Undergraduate: Theory of Probability
2010-2011
Rutgers University
Teaching Assistant (New Brunswick, NJ)
- Undergraduate: Multivariate Calculus, Single Variable Calculus
2008-2009
Western Michigan
University Teaching Assistant (Kalamazoo, MI)
- Undergraduate: Mathematics for Liberal Arts
2007-2008
Western Michigan
University Mathematics Tutor (WMU)
- General mathematics tutoring, mostly for calculus
Professional Service
2023
Area Chair (ACM Conference on Fairness,
Accountability, and Transparency)
2022
Reviewer (Philosophy and Technology)
2021-
Reviewer (Annals of Statistics)
2021-
Reviewer (Journal of Machine Learning Research)
2020-
Reviewer (Proceedings of the National Academy
of Sciences)
2020-
Reviewer (International Conference on Learning
Representations)
2020-
Reviewer (Journal of the Royal Statistical
Society, Series B)
2019-
Reviewer (Harvard Data Science Review)
2019-
Reviewer (Biometrics)
2019-
Reviewer (International Conference on Machine
Learning)
2019-
Reviewer (Annals of Applied Statistics)
2019-
Program Committee (ACM Conference on Fairness,
Accountability, and Transparency)
2018
Reviewer (Applied and Computational Harmonic
Analysis)
2017-
Reviewer (Neural Information Processing
Systems)
2016
Reviewer (Bernoulli)
2015-
Reviewer (Biometrika)
University Service
2021-
Statistics Seminar organizer (London School of
Economics)
2021-
Faculty Search Committee member (London School
of Economics)
2018-2020
Statistics Seminar co-organizer (New York
University)
2018-2020
Data Science Reading Group organizer (New
York University)
2017-2018
Faculty Search Committee member (New York
University)
Students
PhD Co-advisor
2022-
Sakina Hansen (London School of Economics)
2020-
Lucius Bynum (New York University)
2018-
Weichi Yao (New York University)
PhD Committee
2020-
Vishwali Mhasawade (New York University)
2019-
Margarita Boyarskaya (New York University)
MS Supervisor
2022-2023
J. Hoekstra, M. Solomon, C. Mosk, Z. Liu
(London School of Economics)
2021-2022
E. Goel, A. Kansal, L. Wagner (London
School of Economics)
Mentoring
2021-
Statistics Programme Advisor (London School of
Economics)
2021-
General Course Mentor (London School of
Economics)
2019-2020
First-Gen Students Mentor (New York
University)