Edgar Dobriban

Research interests:

• AI safety
  • uncertainty quantification for machine learning: predictive inference, calibration
  • robustness in theory and in practice: distribution shift, jailbreaking LLMs
• scalable data analysis
  • randomized algorithms: sketching and random projections
  • distributed learning
• high-dimensional asymptotics
  • simple models of neural nets, random feature models
  • high-dimensional regression
  • dimension reduction, PCA
• statistics in algorithmic fairness
• data augmentation, invariance, and symmetry

The group is always looking to expand. We are recruiting PhD students at Penn to work on problems in statistics and machine learning. PhD applicants interested to work with me should mention this on their application. Please apply through the departments of Statistics & Data Science, Computer and Information Science, and the AMCS program, as it gives higher chances for admission.

Education (cv):

• PhD in Statistics, Stanford University, 2017.  Advisor: David Donoho
• BA in Mathematics (with highest honors/summa cum laude), Princeton University, 2012.

Recent news:

• Apr 2024: New paper “Uncertainty in Language Models: Assessment through Rank-Calibration“.
• Apr 2024: New paper “JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models“. Website.
• Apr 2024: New paper “Inference in Randomized Least Squares and PCA via Normality of Quadratic Forms“
• Mar 2024: New paper “Minimax Optimal Fair Classification with Bounded Demographic Disparity“
• Mar 2024: New paper “Simultaneous Conformal Prediction of Missing Outcomes with Propensity Score ε-Discretization“
• Feb 2024: Links to educational materials about stats+ML posted in the GitHub repository “Statistics and machine learning: from undergraduate to research“
• Feb 2024: New paper “Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing“
• Dec 2023: New paper “SymmPI: Predictive Inference for Data with Group Symmetries“
• Oct 2023: New paper “PAC Prediction Sets Under Label Shift“
• Oct 2023: New paper “Jailbreaking Black Box Large Language Models in Twenty Queries“. Website.
• Oct 2023: New paper “A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks“
• Fall 2023: On sabbatical, visiting the Department of Statistics at Harvard University.
• August 2023: New paper “Statistical Estimation Under Distribution Shift: Wasserstein Perturbations and Minimax Theory“
• July 2023: New paper “A Framework for Statistical Inference via Randomized Algorithms“
• June 2023: New paper “Efficient and Multiply Robust Risk Estimation under General Forms of Dataset Shift“
• June 2023: Shenzhen Conference on Random Matrix Theory and Applications is co-organized
• June 2023: New paper “Optimal Heterogeneous Collaborative Linear Regression and Contextual Bandits“
• April 2023: New paper “Sharp-SSL: Selective high-dimensional axis-aligned random projections for semi-supervised learning“
• March 2023: New paper “Joint Coverage Regions: Simultaneous Confidence and Prediction Sets“
• February 2023: Edgar is granted tenure, starting July 2023
• January 2023: New paper “Demystifying Disagreement-on-the-Line in High Dimensions“
• November 2022: New paper “Conformal Frequency Estimation with Sketched Data under Relaxed Exchangeability“
• October 2022: New paper “Doubly Robust Proximal Synthetic Controls“
• July 2022: New paper “PAC Prediction Sets for Meta-Learning“
• June 2022: New paper  “Pursuit of a Discriminative Representation for Multiple Subspaces via Sequential Games“
• June 2022: New paper  “Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces“
• June 2022: New paper “Memory Classifiers: Two-stage Classification for Robustness in Machine Learning“
• June 2022: New paper “Collaborative Learning of Distributions under Heterogeneity and Communication Constraints“
• May 2022: New paper “PAC-Wrap: Semi-Supervised PAC Anomaly Detection“
• May 2022: New paper “Fair Bayes-Optimal Classifiers Under Predictive Parity“
• Apr 2022: New paper “SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space” with Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, and Kostas Daniilidis.
• Mar 2022: New paper “Distribution-free Prediction Sets Adaptive to Unknown Covariate Shift“
• Mar 2022: New paper “T-Cal: An optimal test for the calibration of predictive models“. Talk video.
• Feb 2022: New paper “Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates“
• Feb 2022: New paper “Bayes-Optimal Classifiers under Group Fairness“
• Jan 2022: New paper “iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection“
• Spring 2022: New class “Topics in Modern Statistical Learning” (STAT-991), surveying uncertainty quantification for machine learning. See the Github page.
• Nov 2021: New paper “Learning Augmentation Distributions using Transformed Risk Minimization” with Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, and Kostas Daniilidis.
• Oct 2021: New paper “Solon: Communication-efficient Byzantine-resilient Distributed Training via Redundant Gradients” with Lingjiao Chen, Leshang Chen, Hongyi Wang, and Susan Davidson.
• Aug 2021: New paper “Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models?“, with Dominic Richards and Patrick Rebeschini.
• June 2021: New paper on PAC Prediction Sets Under Covariate Shift, with Sangdon Park,  Insup Lee, and Osbert Bastani.
• May 2021: Materials for Short Course on Deep Learning in Statistics, 2021 Symposium on Data Science & Statistics: slides, code
• Apr 2021: New paper on the consistency of invariance-based randomization tests. To appear in The Annals of Statistics.
• Mar 2021: New paper “Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition” with Yaodong Yu, Zitong Yang, Jacob Steinhardt, and Yi Ma.
• Mar 2021: New paper on group testing for COVID-19 with David Hong, Rounak Dey, Xihong Lin, and Brian Cleary. See the website and a talk by David.
• Jan 2021: Edgar receives NSF CAREER award in the mathematical sciences.
• Dec 2020: New paper on selecting the number of components in PCA via random signflips with David Hong and Yue Sheng
• Nov 2020: New paper on sparse sketches with small inversion bias with Michał Dereziński, Zhenyu Liao, and Michael W. Mahoney. Accepted at COLT 2021.
• Oct 2020: Co-organizing session on “Open problems in robustness” at the CDTI Workshop on The Analytical Foundations of Deep Learning. Oct 23, 12pm-1:30pm. See the recorded session on YouTube!
• Oct 2020: New paper: What causes the test error? Going beyond bias-variance via ANOVA, with Licong Lin. Accepted by JMLR.
• Sept 2020: Three papers accepted at NeurIPS 2020: A Group-Theoretic Framework for Data Augmentation (oral presentation, 1% of papers selected), Implicit Regularization and Convergence of Weight Normalization, and Optimal Iterative Sketching with the Subsampled Randomized Hadamard Transform
• Sept 2020: Co-organizing online workshop on Equivariance and Data Augmentation with Kostas Daniilidis, Sept 4. Join us! Part of activities for NSF Tripods center FinPenn. Youtube playlist.
• Aug 2020: Edgar is a Co-PI on NSF-Simons Mathematical and Scientific Foundations of Deep Learning award THEORINET (PI: Rene Vidal, JHU). Looking forward to many exciting collaborations that this will enable!
• Aug 2020: Talks at JSM 2020: See slides for talk on stochastic gradient flow, and slides prepared as a discussant for the invited session on the theory of deep learning.
• June 2020: SIAM Mathematics of Data Science minisymposium “High-Dimensional PCA in the High-Noise Regime” co-organized with William Leeb and Amit Singer.
• June 2020: New paper on provable tradeoffs in adversarially robust classification with Hamed Hassani, David Hong, Alexander Robey
• June 2020: Paper on distributed learning with Yue Sheng accepted at the Annals of Statistics.
• June 2020: Papers accepted at ICML 2020: “WONDER: Weighted one-shot distributed ridge regression” (short version), The Implicit Regularization of Stochastic Gradient Flow for Least Squares, and “DeltaGrad: Rapid retraining of machine learning models” (with Yinjun Wu and Susan Davidson).
• May 2020: Paper on How to reduce dimension with PCA and random projections? with Fan Yang, Sifan Liu, and David P. Woodruff.
• Apr 2020: Paper on “WONDER: Weighted one-shot distributed ridge regression” with Yue Sheng accepted to JMLR.
• Mar 2020: New paper on stochastic gradient descent and flow with Alnur Ali and Ryan Tibshirani.
• Feb 2020: New paper on iterative sketching with Jonathan Lacotte, Sifan Liu, and Mert Pilanci.
• Feb 2020: Talk at UMass Amherst (cancelled due to Covid-19).
• Jan 2020: Edgar becomes an affiliate of the Warren Center.
• Dec 2019: Edgar will be teaching Continuing Education course “Machine Learning and Deep Learning,” with Annie Qu and Xiao Wang, at the 2020 Joint Statistical Meetings (JSM). Also teaching short course “Deep Learning in Statistics” at SLDS 2020.
• Dec 2019: Ridge regression paper with Sifan Liu accepted as a spotlight presentation to ICLR 2020 (top 6% of papers).
• Dec 2019: New GPU machines arrive.
• Nov 2019: New paper on Implicit Regularization of Normalization Methods
• Oct 2019: Reading group/group meeting starts.
• Sept-Nov 2019: Edgar is visiting the IAS for the Special year on Statistics, Machine Learning, and Optimization.
• Sept 2019: New seminar: Topics in Deep Learning (STAT-991), surveying advanced topics in deep learning research based on student presentations. See the Github page for the class materials.
• Sept 2019: PCA paper accepted to the Annals of Statistics
• Sept 2019: Multiple testing paper accepted to Biometrika
• Sept 2019: Sketching paper accepted to NeurIPS 2019
• Aug 2019: Edgar contributes to ASA statement “Comment on Statistics, as a Discipline and Practice, in AI Research and Development“
• Aug 2019: David Hong joins the group. Welcome David!
• July 2019: NSF TRIPODS awarded to Edgar as a co-PI, with Alejandro Ribeiro (PI, ESE), and co-PIs Robert Ghrist (Math), Kostas Daniilidis (CIS), Saswati Sarkar (ESE)
• July 2019: New paper on data augmentation.
• Summer 2019: Undergraduate researchers Tianle Liu (THU), Shuo Xie (PKU), and Weichen Zheng (Penn) work in the group
• June-Aug 2019: Edgar is attending the Summer program on the Foundations of Deep Learning at the Simons Institute.
• March 2019: New paper on distributed learning.

Miscellanea:

• I use Twitter to keep up with new research.
• I grew up in Romania, and speak Hungarian as a first language (the real spelling of my name is Dobribán Edgár). These two countries are and were the origin of many great mathematicians and statisticians, including John von Neumann, Abraham Wald, Paul Erdos, Dan-Virgil Voiculescu, etc…