gradient descent

Understanding Representation Learnability of Nonlinear Self-Supervised Learning AAAI 2023 Understanding Train-Validation Split in Meta-Learning with Neural Networks ICLR 2023 Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics ICLR 2023 Unifying Nesterov’s Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions ICML 2023 Universal Adaptive Data Augmentation IJCAI 2023 Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization NeurIPS 2023 Unlearning Bias in Language Models by Partitioning Gradients ACL 2023 ​​What learning algorithm is in-context learning? Investigations with linear models ICLR 2023 When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario ACL 2023 Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression ICML 2023 Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers ACL 2023 Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation ICLR 2023 A Combinatorial Perspective on the Optimization of Shallow ReLU Networks NeurIPS 2022 A Convergent and Dimension-Independent Min-Max Optimization Algorithm ICML 2022 AdaLoss: A Computationally-Efficient and Provably Convergent Adaptive Gradient Method AAAI 2022 Adversarial Tracking Control via Strongly Adaptive Online Learning with Memory AISTATS 2022 A global convergence theory for deep ReLU implicit networks via over-parameterization ICLR 2022 A Minimal Model for Compositional Generalization on gSCAN EMNLP 2022 A Momentumized, Adaptive, Dual Averaged Gradient Method JMLR 2022 Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation ICLR 2022 Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability NeurIPS 2022 A Neural Tangent Kernel Perspective of Infinite Tree Ensembles ICLR 2022 An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn ICML 2022 Annihilation of Spurious Minima in Two-Layer ReLU Networks NeurIPS 2022 A NON-PARAMETRIC REGRESSION VIEWPOINT : GENERALIZATION OF OVERPARAMETRIZED DEEP RELU NETWORK UNDER NOISY OBSERVATIONS ICLR 2022