Edgar Dobriban

95 papers A* 23A 1Misc 1Journal 67Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning. KDD (1) Dongyue Li, Zhenshuo Zhang, Minxuan Duan, Edgar Dobriban, Hongyang R. Zhang
2026	J	`jnl`	Online Conformal Prediction via Universal Portfolio Algorithms. CoRR Tuo Liu, Edgar Dobriban, Francesco Orabona
2026	J	`jnl`	Optimal Decision-Making Based on Prediction Sets. CoRR Tao Wang, Edgar Dobriban
2026	J	`jnl`	Statistical Early Stopping for Reasoning Models. CoRR Yangxinyu Xie, Tao Wang, Soham Mallick, Yan Sun, Georgy Noarov, Mengxin Yu, Tanwi Mallick, Weijie J. Su, Edgar Dobriban
2026	J	`jnl`	Synthetic-Powered Multiple Testing with FDR Control. CoRR Yonghoon Lee, Meshi Bashari, Edgar Dobriban, Yaniv Romano
2025	J	`jnl`	Conformal Information Pursuit for Interactively Guiding Large Language Models. CoRR Kwan Ho Ryan Chan, Yuyan Ge, Edgar Dobriban, Hamed Hassani, René Vidal
2025	J	`jnl`	Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning. CoRR Dongyue Li, Zhenshuo Zhang, Minxuan Duan, Edgar Dobriban, Hongyang R. Zhang
2025	—	`conf`	Evaluating the Performance of Large Language Models via Debates. NAACL (Findings) Behrad Moniri, Hamed Hassani, Edgar Dobriban
2025	J	`jnl`	Fair Classification by Direct Intervention on Operating Characteristics. CoRR Kevin Jiang, Edgar Dobriban
2025	J	`jnl`	Foundations of Top- CoRR Georgy Noarov, Soham Mallick, Tao Wang, Sunay Joshi, Yan Sun, Yangxinyu Xie, Mengxin Yu, Edgar Dobriban
2025	—	`conf`	Jailbreaking Black Box Large Language Models in Twenty Queries. SaTML Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J. Pappas, Eric Wong
2025	J	`jnl`	Likelihood-Ratio Regularized Quantile Regression: Adapting Conformal Prediction to High-Dimensional Covariate Shifts. CoRR Sunay Joshi, Shayan Kiyani, George J. Pappas, Edgar Dobriban, Hamed Hassani
2025	J	`jnl`	MultiRisk: Multiple Risk Control via Iterative Score Thresholding. CoRR Sunay Joshi, Yan Sun, Hamed Hassani, Edgar Dobriban
2025	J	`jnl`	Singleton-Optimized Conformal Prediction. CoRR Tao Wang, Yan Sun, Edgar Dobriban
2025	J	`jnl`	Solving a Research Problem in Mathematical Statistics with AI Assistance. CoRR Edgar Dobriban
2025	J	`jnl`	Statistical Inference Leveraging Synthetic Data with Distribution-Free Guarantees. CoRR Meshi Bashari, Yonghoon Lee, Roy Maor Lotan, Edgar Dobriban, Yaniv Romano
2025	J	`jnl`	Statistical Methods in Generative AI. CoRR Edgar Dobriban
2025	J	`jnl`	Synthetic-Powered Predictive Inference. CoRR Meshi Bashari, Roy Maor Lotan, Yonghoon Lee, Edgar Dobriban, Yaniv Romano
2024	J	`jnl`	A Confidence Interval for the ℓ CoRR Yan Sun, Pratik Chaudhari, Ian J. Barnett, Edgar Dobriban
2024	A*	`conf`	A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks. ICML Behrad Moniri, Donghwan Lee, Hamed Hassani, Edgar Dobriban
2024	J	`jnl`	Bayes-Optimal Fair Classification with Linear Disparity Constraints via Pre-, In-, and Post-processing. CoRR Xianli Zeng, Guang Cheng, Edgar Dobriban
2024	J	`jnl`	Evaluating the Performance of Large Language Models via Debates. CoRR Behrad Moniri, Hamed Hassani, Edgar Dobriban
2024	A*	`conf`	JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models. NeurIPS Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, Eric Wong
2024	J	`jnl`	JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models. CoRR Patrick Chao, Edoardo Debenedetti, Alexander Robey, Maksym Andriushchenko, Francesco Croce, Vikash Sehwag, Edgar Dobriban, Nicolas Flammarion, George J. Pappas, Florian Tramèr, Hamed Hassani, Eric Wong
2024	J	`jnl`	Minimax Optimal Fair Classification with Bounded Demographic Disparity. CoRR Xianli Zeng, Guang Cheng, Edgar Dobriban
2024	A*	`conf`	One-Shot Safety Alignment for Large Language Models via Optimal Dualization. NeurIPS Xinmeng Huang, Shuo Li, Edgar Dobriban, Osbert Bastani, Hamed Hassani, Dongsheng Ding
2024	J	`jnl`	One-Shot Safety Alignment for Large Language Models via Optimal Dualization. CoRR Xinmeng Huang, Shuo Li, Edgar Dobriban, Osbert Bastani, Hamed Hassani, Dongsheng Ding
2024	A*	`conf`	PAC Prediction Sets Under Label Shift. ICLR Wenwen Si, Sangdon Park, Insup Lee, Edgar Dobriban, Osbert Bastani
2024	A*	`conf`	Uncertainty in Language Models: Assessment through Rank-Calibration. EMNLP Xinmeng Huang, Shuo Li, Mengxin Yu, Matteo Sesia, Hamed Hassani, Insup Lee, Osbert Bastani, Edgar Dobriban
2024	J	`jnl`	Uncertainty in Language Models: Assessment through Rank-Calibration. CoRR Xinmeng Huang, Shuo Li, Mengxin Yu, Matteo Sesia, Hamed Hassani, Insup Lee, Osbert Bastani, Edgar Dobriban
2024	J	`jnl`	Watermarking Language Models with Error Correcting Codes. CoRR Patrick Chao, Edgar Dobriban, Hamed Hassani
2023	J	`jnl`	A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks. CoRR Behrad Moniri, Donghwan Lee, Hamed Hassani, Edgar Dobriban
2023	A	`conf`	Automatically Predicting Perceived Conversation Quality in a Pediatric Sample Enriched for Autism. INTERSPEECH Yahan Yang, Sunghye Cho, Maxine Covello, Azia Knox, Osbert Bastani, James Weimer, Edgar Dobriban, Robert T. Schultz, Insup Lee, Julia Parish-Morris
2023	J	`jnl`	Conformal Frequency Estimation using Discrete Sketched Data with Coverage for Distinct Queries. J. Mach. Learn. Res. Matteo Sesia, Stefano Favaro, Edgar Dobriban
2023	A*	`conf`	Demystifying Disagreement-on-the-Line in High Dimensions. ICML Donghwan Lee, Behrad Moniri, Xinmeng Huang, Edgar Dobriban, Hamed Hassani
2023	J	`jnl`	Demystifying Disagreement-on-the-Line in High Dimensions. CoRR Donghwan Lee, Behrad Moniri, Xinmeng Huang, Edgar Dobriban, Hamed Hassani
2023	J	`jnl`	Jailbreaking Black Box Large Language Models in Twenty Queries. CoRR Patrick Chao, Alexander Robey, Edgar Dobriban, Hamed Hassani, George J. Pappas, Eric Wong
2023	J	`jnl`	Learning Augmentation Distributions using Transformed Risk Minimization. Trans. Mach. Learn. Res. Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, Kostas Daniilidis, Edgar Dobriban
2023	J	`jnl`	Optimal Heterogeneous Collaborative Linear Regression and Contextual Bandits. CoRR Xinmeng Huang, Kan Xu, Donghwan Lee, Hamed Hassani, Hamsa Bastani, Edgar Dobriban
2023	J	`jnl`	PAC Prediction Sets Under Label Shift. CoRR Wenwen Si, Sangdon Park, Insup Lee, Edgar Dobriban, Osbert Bastani
2023	J	`jnl`	Provable Tradeoffs in Adversarially Robust Classification. IEEE Trans. Inf. Theory Edgar Dobriban, Hamed Hassani, David Hong, Alexander Robey
2023	J	`jnl`	Pursuit of a discriminative representation for multiple subspaces via sequential games. J. Frankl. Inst. Druv Pai, Michael Psenka, Chih-Yuan Chiu, Manxi Wu, Edgar Dobriban, Yi Ma
2023	A*	`conf`	SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space. ICLR Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, Edgar Dobriban, Kostas Daniilidis
2023	J	`jnl`	Statistical Estimation Under Distribution Shift: Wasserstein Perturbations and Minimax Theory. CoRR Patrick Chao, Edgar Dobriban
2023	J	`jnl`	SymmPI: Predictive Inference for Data with Group Symmetries. CoRR Edgar Dobriban, Mengxin Yu
2023	J	`jnl`	T-Cal: An Optimal Test for the Calibration of Predictive Models. J. Mach. Learn. Res. Donghwan Lee, Xinmeng Huang, Hamed Hassani, Edgar Dobriban
2022	J	`jnl`	Bayes-Optimal Classifiers under Group Fairness. CoRR Xianli Zeng, Edgar Dobriban, Guang Cheng
2022	A*	`conf`	Collaborative Learning of Discrete Distributions under Heterogeneity and Communication Constraints. NeurIPS Xinmeng Huang, Donghwan Lee, Edgar Dobriban, Hamed Hassani
2022	J	`jnl`	Collaborative Learning of Distributions under Heterogeneity and Communication Constraints. CoRR Xinmeng Huang, Donghwan Lee, Edgar Dobriban, Hamed Hassani
2022	Misc	`conf`	Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates. CoRL Souradeep Dutta, Kaustubh Sridhar, Osbert Bastani, Edgar Dobriban, James Weimer, Insup Lee, Julia Parish-Morris
2022	J	`jnl`	Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates. CoRR Souradeep Dutta, Kaustubh Sridhar, Osbert Bastani, Edgar Dobriban, James Weimer, Insup Lee, Julia Parish-Morris
2022	A*	`conf`	Fair Bayes-Optimal Classifiers Under Predictive Parity. NeurIPS Xianli Zeng, Edgar Dobriban, Guang Cheng
2022	J	`jnl`	Fair Bayes-Optimal Classifiers Under Predictive Parity. CoRR Xianli Zeng, Edgar Dobriban, Guang Cheng
2022	J	`jnl`	Memory Classifiers: Two-stage Classification for Robustness in Machine Learning. CoRR Souradeep Dutta, Yahan Yang, Elena Bernardis, Edgar Dobriban, Insup Lee
2022	A*	`conf`	PAC Prediction Sets Under Covariate Shift. ICLR Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani
2022	A*	`conf`	PAC Prediction Sets for Meta-Learning. NeurIPS Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani
2022	J	`jnl`	PAC Prediction Sets for Meta-Learning. CoRR Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani
2022	A*	`conf`	PAC-Wrap: Semi-Supervised PAC Anomaly Detection. KDD Shuo Li, Xiayan Ji, Edgar Dobriban, Oleg Sokolsky, Insup Lee
2022	J	`jnl`	PAC-Wrap: Semi-Supervised PAC Anomaly Detection. CoRR Shuo Li, Xiayan Ji, Edgar Dobriban, Oleg Sokolsky, Insup Lee
2022	J	`jnl`	Pursuit of a Discriminative Representation for Multiple Subspaces via Sequential Games. CoRR Druv Pai, Michael Psenka, Chih-Yuan Chiu, Manxi Wu, Edgar Dobriban, Yi Ma
2022	J	`jnl`	SE(3)-Equivariant Attention Networks for Shape Reconstruction in Function Space. CoRR Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, Edgar Dobriban, Kostas Daniilidis
2022	J	`jnl`	T-Cal: An optimal test for the calibration of predictive models. CoRR Donghwan Lee, Xinmeng Huang, Hamed Hassani, Edgar Dobriban
2022	A*	`conf`	Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces. ICML Yinshuang Xu, Jiahui Lei, Edgar Dobriban, Kostas Daniilidis
2022	J	`jnl`	Unified Fourier-based Kernel and Nonlinearity Design for Equivariant Networks on Homogeneous Spaces. CoRR Yinshuang Xu, Jiahui Lei, Edgar Dobriban, Kostas Daniilidis
2022	A*	`conf`	iDECODe: In-Distribution Equivariance for Conformal Out-of-Distribution Detection. AAAI Ramneet Kaur, Susmit Jha, Anirban Roy, Sangdon Park, Edgar Dobriban, Oleg Sokolsky, Insup Lee
2022	J	`jnl`	iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection. CoRR Ramneet Kaur, Susmit Jha, Anirban Roy, Sangdon Park, Edgar Dobriban, Oleg Sokolsky, Insup Lee
2021	J	`jnl`	Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models? CoRR Dominic Richards, Edgar Dobriban, Patrick Rebeschini
2021	J	`jnl`	How to Reduce Dimension With PCA and Random Projections? IEEE Trans. Inf. Theory Fan Yang, Sifan Liu, Edgar Dobriban, David P. Woodruff
2021	J	`jnl`	Learning Augmentation Distributions using Transformed Risk Minimization. CoRR Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, Edgar Dobriban, Kostas Daniilidis
2021	J	`jnl`	PAC Prediction Sets Under Covariate Shift. CoRR Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani
2021	J	`jnl`	Solon: Communication-efficient Byzantine-resilient Distributed Training via Redundant Gradients. CoRR Lingjiao Chen, Leshang Chen, Hongyi Wang, Susan B. Davidson, Edgar Dobriban
2021	A*	`conf`	Sparse sketches with small inversion bias. COLT Michal Derezinski, Zhenyu Liao, Edgar Dobriban, Michael W. Mahoney
2021	J	`jnl`	Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition. CoRR Yaodong Yu, Zitong Yang, Edgar Dobriban, Jacob Steinhardt, Yi Ma
2021	J	`jnl`	What Causes the Test Error? Going Beyond Bias-Variance via ANOVA. J. Mach. Learn. Res. Licong Lin, Edgar Dobriban
2020	A*	`conf`	A Group-Theoretic Framework for Data Augmentation. NeurIPS Shuxiao Chen, Edgar Dobriban, Jane H. Lee
2020	A*	`conf`	DeltaGrad: Rapid retraining of machine learning models. ICML Yinjun Wu, Edgar Dobriban, Susan B. Davidson
2020	J	`jnl`	DeltaGrad: Rapid retraining of machine learning models. CoRR Yinjun Wu, Edgar Dobriban, Susan B. Davidson
2020	A*	`conf`	Implicit Regularization and Convergence for Weight Normalization. NeurIPS Xiaoxia Wu, Edgar Dobriban, Tongzheng Ren, Shanshan Wu, Zhiyuan Li, Suriya Gunasekar, Rachel A. Ward, Qiang Liu
2020	J	`jnl`	Limiting Spectrum of Randomized Hadamard Transform and Optimal Iterative Sketching Methods. CoRR Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci
2020	A*	`conf`	One-shot Distributed Ridge Regression in High Dimensions. ICML Yue Sheng, Edgar Dobriban
2020	A*	`conf`	Optimal Iterative Sketching Methods with the Subsampled Randomized Hadamard Transform. NeurIPS Jonathan Lacotte, Sifan Liu, Edgar Dobriban, Mert Pilanci
2020	J	`jnl`	Provable tradeoffs in adversarially robust classification. CoRR Edgar Dobriban, Hamed Hassani, David Hong, Alexander Robey
2020	A*	`conf`	Ridge Regression: Structure, Cross-Validation, and Sketching. ICLR Sifan Liu, Edgar Dobriban
2020	J	`jnl`	Sparse sketches with small inversion bias. CoRR Michal Derezinski, Zhenyu Liao, Edgar Dobriban, Michael W. Mahoney
2020	A*	`conf`	The Implicit Regularization of Stochastic Gradient Flow for Least Squares. ICML Alnur Ali, Edgar Dobriban, Ryan J. Tibshirani
2020	J	`jnl`	The Implicit Regularization of Stochastic Gradient Flow for Least Squares. CoRR Alnur Ali, Edgar Dobriban, Ryan J. Tibshirani
2020	J	`jnl`	WONDER: Weighted One-shot Distributed Ridge Regression in High Dimensions. J. Mach. Learn. Res. Edgar Dobriban, Yue Sheng
2020	J	`jnl`	What causes the test error? Going beyond bias-variance via ANOVA. CoRR Licong Lin, Edgar Dobriban
2019	A*	`conf`	Asymptotics for Sketching in Least Squares Regression. NeurIPS Edgar Dobriban, Sifan Liu
2019	J	`jnl`	Implicit Regularization of Normalization Methods. CoRR Xiaoxia Wu, Edgar Dobriban, Tongzheng Ren, Shanshan Wu, Zhiyuan Li, Suriya Gunasekar, Rachel A. Ward, Qiang Liu
2019	J	`jnl`	Invariance reduces Variance: Understanding Data Augmentation in Deep Learning and Beyond. CoRR Shuxiao Chen, Edgar Dobriban, Jane H. Lee
2019	J	`jnl`	One-shot distributed ridge regression in high dimensions. CoRR Edgar Dobriban, Yue Sheng
2018	J	`jnl`	A New Theory for Sketching in Linear Regression. CoRR Edgar Dobriban, Sifan Liu
2013	J	`jnl`	Certifying the Restricted Isometry Property is Hard. IEEE Trans. Inf. Theory Afonso S. Bandeira, Edgar Dobriban, Dustin G. Mixon, William F. Sawin
2012	J	`jnl`	Certifying the restricted isometry property is hard CoRR Afonso S. Bandeira, Edgar Dobriban, Dustin G. Mixon, William F. Sawin