gradient descent

Semi-Supervised Learning with Meta-Gradient AISTATS 2021 Sharpness-aware Minimization for Efficiently Improving Generalization ICLR 2021 Shuffling Recurrent Neural Networks AAAI 2021 Small random initialization is akin to spectral learning: Optimization and generalization guarantees for overparameterized low-rank matrix reconstruction NeurIPS 2021 SMG: A Shuffling Gradient-Based Method with Momentum ICML 2021 Stability & Generalisation of Gradient Descent for Shallow Neural Networks without the Neural Tangent Kernel NeurIPS 2021 Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation ICML 2021 SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients NeurIPS 2021 Task similarity aware meta learning: theory-inspired improvement on MAML UAI 2021 Temporal Difference Learning as Gradient Splitting ICML 2021 Tensor Programs IV: Feature Learning in Infinite-Width Neural Networks ICML 2021 The complexity of nonconvex-strongly-concave minimax optimization UAI 2021 The Contour to Classification Game AAAI 2021 The Dynamics of Gradient Descent for Overparametrized Neural Networks L4DC 2021 The Implicit Bias for Adaptive Optimization Algorithms on Homogeneous Neural Networks ICML 2021 The Limits of Min-Max Optimization Algorithms: Convergence to Spurious Non-Critical Sets ICML 2021 The Neural Tangent Link Between CNN Denoisers and Non-Local Filters CVPR 2021 The staircase property: How hierarchical structure can guide deep learning NeurIPS 2021 Tight Bounds on the Smallest Eigenvalue of the Neural Tangent Kernel for Deep ReLU Networks ICML 2021 Towards Impartial Multi-task Learning ICLR 2021 Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning ICLR 2021 Understanding Decoupled and Early Weight Decay AAAI 2021 Understanding End-to-End Model-Based Reinforcement Learning Methods as Implicit Parameterization NeurIPS 2021 Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron ACML 2021 Understanding Over-parameterization in Generative Adversarial Networks ICLR 2021