gradient descent

Learning from Mistakes – a Framework for Neural Architecture Search AAAI 2022 Learning in Stochastic Monotone Games with Decision-Dependent Data AISTATS 2022 Learning Large DAGs by Combining Continuous Optimization and Feedback Arc Set Heuristics AAAI 2022 Learning Strides in Convolutional Neural Networks ICLR 2022 Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures NeurIPS 2022 Learning Versatile Neural Architectures by Propagating Network Codes ICLR 2022 Lightweight Projective Derivative Codes for Compressed Asynchronous Gradient Descent ICML 2022 Local and Global Convergence of General Burer-Monteiro Tensor Optimizations AAAI 2022 Local and Global Linear Convergence of General Low-Rank Matrix Recovery Problems AAAI 2022 Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients NeurIPS 2022 Memorization and Optimization in Deep Neural Networks with Minimum Over-parameterization NeurIPS 2022 Memory Augmented Optimizers for Deep Learning ICLR 2022 Meta Approach to Data Augmentation Optimization WACV 2022 Meta-learning via Language Model In-context Tuning ACL 2022 Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently NeurIPS 2022 Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably) ICML 2022 Module-Aware Optimization for Auxiliary Learning NeurIPS 2022 Momentum Aggregation for Private Non-convex ERM NeurIPS 2022 Multilevel Optimization for Inverse Problems COLT 2022 Multi-Objective Deep Learning with Adaptive Reference Vectors NeurIPS 2022 Nesterov Accelerated Shuffling Gradient Method for Convex Optimization ICML 2022 Neural Networks can Learn Representations with Gradient Descent COLT 2022 Neural Network Weights Do Not Converge to Stationary Points: An Invariant Measure Perspective ICML 2022 Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably AISTATS 2022 Non-asymptotic and Accurate Learning of Nonlinear Dynamical Systems JMLR 2022