Lunjia Hu

Publication Activity (10 Years)

Years Active: 2017-2024
Publications (10 Years): 45

Top Topics

Incomplete Data

Teaching Dimension

Sample Complexity

Loss Minimization

Top Venues

Publications

Lunjia Hu, Charlotte Peale, Judy Hanwen Shen
Multigroup Robustness. CoRR (2024)
Lunjia Hu, Kevin Tian, Chutong Yang
Testing Calibration in Subquadratic Time. CoRR (2024)
Lunjia Hu, Yifan Wu
Predict to Minimize Swap Regret for All Payoff-Bounded Tasks. CoRR (2024)
Parikshit Gopalan, Lunjia Hu, Guy N. Rothblum
On Computationally Efficient Multi-Class Calibration. CoRR (2024)
Jaroslaw Blasiok, Parikshit Gopalan, Lunjia Hu, Adam Tauman Kalai, Preetum Nakkiran
Loss Minimization Yields Multicalibration for Large Neural Networks. ITCS (2024)
Parikshit Gopalan, Lunjia Hu, Guy N. Rothblum
On Computationally Efficient Multi-Class Calibration. COLT (2024)
Parikshit Gopalan, Lunjia Hu, Michael P. Kim, Omer Reingold, Udi Wieder
Loss Minimization Through the Lens Of Outcome Indistinguishability. ITCS (2023)
Lunjia Hu, Inbal Rachel Livni Navon, Omer Reingold, Chutong Yang
Omnipredictors for Constrained Optimization. ICML (2023)
Lunjia Hu, Inbal Livni Navon, Omer Reingold
Generative Models of Huge Objects. CoRR (2023)
Jaroslaw Blasiok, Parikshit Gopalan, Lunjia Hu, Adam Tauman Kalai, Preetum Nakkiran
Loss minimization yields multicalibration for large neural networks. CoRR (2023)
Lunjia Hu, Inbal Livni Navon, Omer Reingold
Generative Models of Huge Objects. CCC (2023)
Jaroslaw Blasiok, Parikshit Gopalan, Lunjia Hu, Preetum Nakkiran
A Unifying Theory of Distance from Calibration. STOC (2023)
Moses Charikar, Monika Henzinger, Lunjia Hu, Maximilian Vötsch, Erik Waingarten
Simple, Scalable and Effective Clustering via One-Dimensional Projections. NeurIPS (2023)
Jaroslaw Blasiok, Parikshit Gopalan, Lunjia Hu, Preetum Nakkiran
When Does Optimizing a Proper Loss Yield Calibration? NeurIPS (2023)
Moses Charikar, Monika Henzinger, Lunjia Hu, Maximilian Vötsch, Erik Waingarten
Simple, Scalable and Effective Clustering via One-Dimensional Projections. CoRR (2023)
Jaroslaw Blasiok, Parikshit Gopalan, Lunjia Hu, Preetum Nakkiran
When Does Optimizing a Proper Loss Yield Calibration? CoRR (2023)
Lunjia Hu, Charlotte Peale
Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes. ITCS (2023)
Moses Charikar, Lunjia Hu
Near-Optimal Explainable k-Means for All Dimensions. SODA (2022)
Parikshit Gopalan, Lunjia Hu, Michael P. Kim, Omer Reingold, Udi Wieder
Loss Minimization through the Lens of Outcome Indistinguishability. CoRR (2022)
Lunjia Hu, Charlotte Peale, Omer Reingold
Metric Entropy Duality and the Sample Complexity of Outcome Indistinguishability. CoRR (2022)
Vincent Cohen-Addad, Anupam Gupta, Lunjia Hu, Hoon Oh, David Saulpic
An Improved Local Search Algorithm for k-Median. SODA (2022)
Jaroslaw Blasiok, Parikshit Gopalan, Lunjia Hu, Preetum Nakkiran
A Unifying Theory of Distance from Calibration. CoRR (2022)
Lunjia Hu, Charlotte Peale
Comparative Learning: A Sample Complexity Theory for Two Hypothesis Classes. CoRR (2022)
John C. Duchi, Vitaly Feldman, Lunjia Hu, Kunal Talwar
Subspace Recovery from Heterogeneous Data with Non-isotropic Noise. NeurIPS (2022)
Lunjia Hu, Charlotte Peale, Omer Reingold
Metric Entropy Duality and the Sample Complexity of Outcome Indistinguishability. ALT (2022)
Lunjia Hu, Inbal Livni Navon, Omer Reingold, Chutong Yang
Omnipredictors for Constrained Optimization. CoRR (2022)
John Duchi, Vitaly Feldman, Lunjia Hu, Kunal Talwar
Subspace Recovery from Heterogeneous Data with Non-isotropic Noise. CoRR (2022)
Lunjia Hu, Omer Reingold
Robust Mean Estimation on Highly Incomplete Data with Arbitrary Outliers. AISTATS (2021)
Vincent Cohen-Addad, Anupam Gupta, Lunjia Hu, Hoon Oh, David Saulpic
An Improved Local Search Algorithm for k-Median. CoRR (2021)
Moses Charikar, Lunjia Hu
Approximation Algorithms for Orthogonal Non-negative Matrix Factorization. AISTATS (2021)
Moses Charikar, Lunjia Hu
Near-Optimal Explainable k-Means for All Dimensions. CoRR (2021)
Moses Charikar, Lunjia Hu
Approximation Algorithms for Orthogonal Non-negative Matrix Factorization. CoRR (2021)
Jiaming Song, Lunjia Hu, Yann N. Dauphin, Michael Auli, Tengyu Ma
Robust and On-the-fly Dataset Denoising for Image Classification. CoRR (2020)
Andrew Bassilakis, Andrew Drucker, Mika Göös, Lunjia Hu, Weiyun Ma, Li-Yang Tan
The Power of Many Samples in Query Complexity. Electron. Colloquium Comput. Complex. 27 (2020)
Lunjia Hu, Omer Reingold
Robust Mean Estimation on Highly Incomplete Data with Arbitrary Outliers. CoRR (2020)
Andrew Bassilakis, Andrew Drucker, Mika Göös, Lunjia Hu, Weiyun Ma, Li-Yang Tan
The Power of Many Samples in Query Complexity. CoRR (2020)
Andrew Bassilakis, Andrew Drucker, Mika Göös, Lunjia Hu, Weiyun Ma, Li-Yang Tan
The Power of Many Samples in Query Complexity. ICALP (2020)
Avrim Blum, Lunjia Hu
Active Tolerant Testing. COLT (2018)
Liwei Wang, Lunjia Hu, Jiayuan Gu, Zhiqiang Hu, Yue Wu, Kun He, John E. Hopcroft
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation. NeurIPS (2018)
Liwei Wang, Lunjia Hu, Jiayuan Gu, Yue Wu, Zhiqiang Hu, Kun He, John E. Hopcroft
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation. CoRR (2018)
Lunjia Hu, Ruihan Wu, Tianhong Li, Liwei Wang
Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes. COLT (2017)
Hu Ding, Lunjia Hu, Lingxiao Huang, Jian Li
Capacitated Center Problems with Two-Sided Bounds and Outliers. WADS (2017)
Avrim Blum, Lunjia Hu
Active Tolerant Testing. CoRR (2017)
Hu Ding, Lunjia Hu, Lingxiao Huang, Jian Li
Capacitated Center Problems with Two-Sided Bounds and Outliers. CoRR (2017)
Lunjia Hu, Ruihan Wu, Tianhong Li, Liwei Wang
Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes. CoRR (2017)