Lunjia Hu

13 papers · 2017–2024 · 5 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (15) 🗺️ Taxonomy Completionist (14) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (5) 🏃 Academic Marathon (7) 🌉 Interdisciplinary Bridge 💎 Century Club (13) ❓ The Questioner 🗃️ Keyword Collector (56)

Conferences

NIPS (5) COLT (3) AISTATS (2) ICML (2) ALT (1)

Top co-authors

Omer Reingold (3) Chutong Yang (2) Parikshit Gopalan (2) Charlotte Peale (2) Liwei Wang (2) Moses Charikar (2) Kun He (1) Ruihan Wu (1) Maximilian Vötsch (1) Zhiqiang Hu (1)

Keywords

approximation algorithm (2) learning theory (1) label complexity (1) binary classification (1) principal component analysis (1) k-means clustering (1) sample complexity (1) pac learning (1) mean estimation (1) constrained optimization (1) outlier detection (1) dynamic programming (1) distance estimation (1) agnostic learning (1) algorithmic fairness (1) robust estimation (1) query complexity (1) fat-shattering dimension (1) correlation clustering (1) representation learning (1)

Papers

On Computationally Efficient Multi-Class Calibration COLT 2024

Testing Calibration in Nearly-Linear Time NIPS 2024

Multigroup Robustness ICML 2024

Omnipredictors for Constrained Optimization ICML 2023

Simple, Scalable and Effective Clustering via One-Dimensional Projections NIPS 2023

When Does Optimizing a Proper Loss Yield Calibration? NIPS 2023

Subspace Recovery from Heterogeneous Data with Non-isotropic Noise NIPS 2022

Metric Entropy Duality and the Sample Complexity of Outcome Indistinguishability ALT 2022

Approximation Algorithms for Orthogonal Non-negative Matrix Factorization AISTATS 2021

Robust Mean Estimation on Highly Incomplete Data with Arbitrary Outliers AISTATS 2021

Active Tolerant Testing COLT 2018

Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same Representation NIPS 2018

Quadratic Upper Bound for Recursive Teaching Dimension of Finite VC Classes COLT 2017