gradient descent

How do Transformers Perform In-Context Autoregressive Learning ? ICML 2024 How Graph Neural Networks Learn: Lessons from Training Dynamics ICML 2024 How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization ICLR 2024 How Transformers Learn Causal Structure with Gradient Descent ICML 2024 How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression NeurIPS 2024 How Two-Layer Neural Networks Learn, One (Giant) Step at a Time JMLR 2024 Implicit Maximum a Posteriori Filtering via Adaptive Optimization ICLR 2024 Implicit Optimization Bias of Next-token Prediction in Linear Models NeurIPS 2024 Implicit Regularization in Deep Tucker Factorization: Low-Rankness via Structured Sparsity AISTATS 2024 Implicit Regularization of Decentralized Gradient Descent for Sparse Regression NeurIPS 2024 Improving Adaptivity via Over-Parameterization in Sequence Models NeurIPS 2024 Improving Computational Complexity in Statistical Models with Local Curvature Information ICML 2024 Improving Sharpness-Aware Minimization by Lookahead ICML 2024 In-context Convergence of Transformers ICML 2024 In-context Learning and Gradient Descent Revisited NAACL 2024 In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization NeurIPS 2024 In-context Learning on Function Classes Unveiled for Transformers ICML 2024 In-Context Learning State Vector with Inner and Momentum Optimization NeurIPS 2024 In-Context Learning with Representations: Contextual Generalization of Trained Transformers NeurIPS 2024 Initializing Services in Interactive ML Systems for Diverse Users NeurIPS 2024 Ink Dot-Oriented Differentiable Optimization for Neural Image Halftoning CVPR 2024 Interpreting and Improving Diffusion Models from an Optimization Perspective ICML 2024 IPO: Interpretable Prompt Optimization for Vision-Language Models NeurIPS 2024 Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning NeurIPS 2024 Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency COLT 2024