gradient descent

On Convergence of Gradient Descent Ascent: A Tight Local Analysis ICML 2022 On global convergence of ResNets: From finite to infinite width using linear parameterization NeurIPS 2022 Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback ICML 2022 On the Benefits of Large Learning Rates for Kernel Methods COLT 2022 On the Convergence of Certified Robust Training with Interval Bound Propagation ICLR 2022 On the Convergence of Local Stochastic Compositional Gradient Descent with Momentum ICML 2022 On the Convergence of Stochastic Multi-Objective Gradient Manipulation and Beyond NeurIPS 2022 On the difficulty of learning chaotic dynamics with RNNs NeurIPS 2022 On the Implicit Bias of Gradient Descent for Temporal Extrapolation AISTATS 2022 On the Interpretability of Regularisation for Neural Networks Through Model Gradient Similarity NeurIPS 2022 On the non-universality of deep learning: quantifying the cost of symmetry NeurIPS 2022 On the SDEs and Scaling Rules for Adaptive Gradient Algorithms NeurIPS 2022 Optimality and Stability in Non-Convex Smooth Games JMLR 2022 Optimization-Based Separations for Neural Networks COLT 2022 Optimizer Amalgamation ICLR 2022 Optimizing Early Warning Classifiers to Control False Alarms via a Minimum Precision Constraint AISTATS 2022 Optimizing Neural Networks with Gradient Lexicase Selection ICLR 2022 Overparameterization of Deep ResNet: Zero Loss and Mean-field Analysis JMLR 2022 Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences ICLR 2022 Pareto navigation gradient descent: a first-order algorithm for optimization in pareto set UAI 2022 Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration ICLR 2022 Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models NeurIPS 2022 Projective Manifold Gradient Layer for Deep Rotation Regression CVPR 2022 Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out ICML 2022 Reverse-mode differentiation in arbitrary tensor network format: with application to supervised learning JMLR 2022