Optimization

The Complexity of Finding Stationary Points with Stochastic Gradient Descent ICML 2020 The Convex Relaxation Barrier, Revisited: Tightened Single-Neuron Relaxations for Neural Network Verification NeurIPS 2020 The Differentiable Cross-Entropy Method ICML 2020 The Error-Feedback framework: SGD with Delayed Gradients JMLR 2020 The estimation error of general first order methods COLT 2020 The Generalized Lasso with Nonlinear Observations and Generative Priors NeurIPS 2020 The Gradient Complexity of Linear Regression COLT 2020 The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent ICML 2020 The Implicit and Explicit Regularization Effects of Dropout ICML 2020 The Lottery Ticket Hypothesis for Pre-trained BERT Networks NeurIPS 2020 Themis: Fair and Efficient GPU Cluster Scheduling NSDI 2020 The Optimal Ridge Penalty for Real-world High-dimensional Data Can Be Zero or Negative due to the Implicit Ridge Regularization JMLR 2020 Theory-Inspired Path-Regularized Differential Network Architecture Search NeurIPS 2020 Theory of Curriculum Learning, with Convex Loss Functions JMLR 2020 The Performance Analysis of Generalized Margin Maximizers on Separable Data ICML 2020 The Statistical Complexity of Early-Stopped Mirror Descent NeurIPS 2020 The Strong Screening Rule for SLOPE NeurIPS 2020 The Surprising Power of Hiding Information in Facility Location AAAI 2020 Thunder: a Fast Coordinate Selection Solver for Sparse Learning NeurIPS 2020 Thunderbolt: Throughput-Optimized, Quality-of-Service-Aware Power Capping at Scale OSDI 2020 Tight Analysis of Privacy and Utility Tradeoff in Approximate Differential Privacy AISTATS 2020 Tight Convergence Rate of Gradient Descent for Eigenvalue Computation IJCAI 2020 Tightening Exploration in Upper Confidence Reinforcement Learning ICML 2020 Tighter Theory for Local SGD on Identical and Heterogeneous Data AISTATS 2020 Tight last-iterate convergence rates for no-regret learning in multi-player games NeurIPS 2020