neural network optimization

Efficient Riemannian Meta-Optimization by Implicit Differentiation AAAI 2022 Efficient Training of Low-Curvature Neural Networks NeurIPS 2022 Efficient Two-Stage Progressive Quantization of BERT EMNLP 2022 Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise ICLR 2022 Exploiting Explainable Metrics for Augmented SGD CVPR 2022 Exploring Mode Connectivity for Pre-trained Language Models EMNLP 2022 Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks NeurIPS 2022 Fast and Efficient Restoration of Extremely Dark Light Fields WACV 2022 Fast Finite Width Neural Tangent Kernel ICML 2022 Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs AAAI 2022 Fire Together Wire Together: A Dynamic Pruning Approach With Self-Supervised Mask Prediction CVPR 2022 Fortuitous Forgetting in Connectionist Networks ICLR 2022 FPT: Improving Prompt Tuning Efficiency via Progressive Training EMNLP 2022 Fractional Adaptive Linear Units AAAI 2022 GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization EMNLP 2022 Generalization Bounds using Lower Tail Exponents in Stochastic Optimizers ICML 2022 Globally Gated Deep Linear Networks NeurIPS 2022 Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit NeurIPS 2022 HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks CVPR 2022 HoD-Net: High-Order Differentiable Deep Neural Networks and Applications AAAI 2022 Homography Loss for Monocular 3D Object Detection CVPR 2022 How many degrees of freedom do we need to train deep networks: a loss landscape perspective ICLR 2022 Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks ICLR 2022 Implicit Gradient Alignment in Distributed and Federated Learning AAAI 2022 Implicit Regularization with Polynomial Growth in Deep Tensor Factorization ICML 2022