gradient descent

Understanding the failure modes of out-of-distribution generalization ICLR 2021 Understanding the role of importance weighting for deep learning ICLR 2021 Understanding Unintended Memorization in Language Models Under Federated Learning NAACL 2021 Unitary Branching Programs: Learnability and Lower Bounds ICML 2021 Vector-output ReLU Neural Network Problems are Copositive Programs: Convex Analysis of Two Layer Networks and Polynomial-time Algorithms ICLR 2021 When Does Gradient Descent with Logistic Loss Find Interpolating Two-Layer Networks? JMLR 2021 When does gradient descent with logistic loss interpolate using deep networks with smoothed ReLU activations? COLT 2021 When Expressivity Meets Trainability: Fewer than n Neurons Can Work NeurIPS 2021 When MAML Can Adapt Fast and How to Assist When It Cannot AISTATS 2021 Why Adversarial Interaction Creates Non-Homogeneous Patterns: A Pseudo-Reaction-Diffusion Model for Turing Instability AAAI 2021 99% of Worker-Master Communication in Distributed Optimization Is Not Needed UAI 2020 Accelerated Factored Gradient Descent for Low-Rank Matrix Factorization AISTATS 2020 A Closer Look at the Optimization Landscapes of Generative Adversarial Networks ICLR 2020 Adaptive Gradient Descent without Descent ICML 2020 Adversarial Dynamic Shapelet Networks AAAI 2020 A Dynamical Central Limit Theorem for Shallow Neural Networks NeurIPS 2020 A Fast Anderson-Chebyshev Acceleration for Nonlinear Optimization AISTATS 2020 A Generalized Neural Tangent Kernel Analysis for Two-layer Neural Networks NeurIPS 2020 Agnostic Learning of a Single Neuron with Gradient Descent NeurIPS 2020 Alleviation of Gradient Exploding in GANs: Fake Can Be Real CVPR 2020 An Efficient Framework for Clustered Federated Learning NeurIPS 2020 A New Ensemble Adversarial Attack Powered by Long-Term Gradient Memories AAAI 2020 An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint AAAI 2020 A Sample Complexity Separation between Non-Convex and Convex Meta-Learning ICML 2020 A Score-and-Search Approach to Learning Bayesian Networks with Noisy-OR Relations PGM 2020