empirical risk minimization

DORO: Distributional and Outlier Robust Optimization ICML 2021 Empirical or Invariant Risk Minimization? A Sample Complexity Perspective ICLR 2021 Evading the Curse of Dimensionality in Unconstrained Private GLMs AISTATS 2021 Exploiting Local Convergence of Quasi-Newton Methods Globally: Adaptive Sample Size Approach NeurIPS 2021 Exponential Weights Algorithms for Selective Learning COLT 2021 Fast convergence of stochastic subgradient method under interpolation ICLR 2021 Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions AISTATS 2021 Geometry-Aware Gradient Algorithms for Neural Architecture Search ICLR 2021 Gradient-Based Algorithms for Machine Teaching CVPR 2021 Hadamard Wirtinger Flow for Sparse Phase Retrieval AISTATS 2021 Improved Algorithms for Agnostic Pool-based Active Classification ICML 2021 Incentive-Aware PAC Learning AAAI 2021 In Search of Lost Domain Generalization ICLR 2021 Just Train Twice: Improving Group Robustness without Training Group Information ICML 2021 Learning with User-Level Privacy NeurIPS 2021 Localization, Convexity, and Star Aggregation NeurIPS 2021 (Nearly) Dimension Independent Private ERM with AdaGrad Rates\{via Publicly Estimated Subspaces COLT 2021 Newton Method over Networks is Fast up to the Statistical Precision ICML 2021 Oblivious Sketching-based Central Path Method for Linear Programming ICML 2021 On Empirical Risk Minimization with Dependent and Heavy-Tailed Data NeurIPS 2021 On the Minimal Error of Empirical Risk Minimization COLT 2021 PAC-Learning for Strategic Classification ICML 2021 Privately Publishable Per-instance Privacy NeurIPS 2021 Private Non-smooth ERM and SCO in Subquadratic Steps NeurIPS 2021 Private optimization without constraint violations AISTATS 2021