Optimization

Optimization and Adaptive Generalization of Three layer Neural Networks ICLR 2022 Optimizer Amalgamation ICLR 2022 Orthogonal Graph Neural Networks AAAI 2022 Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models COLING 2022 Paramixer: Parameterizing Mixing Links in Sparse Factors Works Better Than Dot-Product Self-Attention CVPR 2022 PatchFormer: An Efficient Point Transformer With Patch Attention CVPR 2022 Perception Prioritized Training of Diffusion Models CVPR 2022 Permutation-Based SGD: Is Random Optimal? ICLR 2022 PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication ICLR 2022 Practical Schemes for Finding Near-Stationary Points of Convex Finite-Sums AISTATS 2022 Private Adaptive Optimization with Side information ICML 2022 Programmatic Reinforcement Learning without Oracles ICLR 2022 Projective Manifold Gradient Layer for Deep Rotation Regression CVPR 2022 Proof of Learning: Towards a Practical Blockchain Consensus Mechanism Using Directed Guiding Gradients (Student Abstract) AAAI 2022 Proppo: a Message Passing Framework for Customizable and Composable Learning Algorithms NeurIPS 2022 Provable Acceleration of Heavy Ball beyond Quadratics for a Class of Polyak-Lojasiewicz Functions when the Non-Convexity is Averaged-Out ICML 2022 Proximal and Federated Random Reshuffling ICML 2022 Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularization ICML 2022 ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally! ICML 2022 Quality-Aware Decoding for Neural Machine Translation NAACL 2022 Quantization-Aware Deep Optics for Diffractive Snapshot Hyperspectral Imaging CVPR 2022 Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022 Revisit last-iterate convergence of mSGD under milder requirement on step size NeurIPS 2022 RID-Noise: Towards Robust Inverse Design under Noisy Environments AAAI 2022 Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks JMLR 2022