neural network optimization

Improving Stability of Fine-Tuning Pretrained Language Models via Component-Wise Gradient Norm Clipping EMNLP 2022 Improving Transformer with an Admixture of Attention Heads NeurIPS 2022 In Defense of the Unitary Scalarization for Deep Multi-Task Learning NeurIPS 2022 Instability and Local Minima in GAN Training with Kernel Discriminators NeurIPS 2022 Is Integer Arithmetic Enough for Deep Learning Training? NeurIPS 2022 It's All in the Teacher: Zero-Shot Quantization Brought Closer to the Teacher CVPR 2022 JFB: Jacobian-Free Backpropagation for Implicit Networks AAAI 2022 Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC CVPR 2022 KOALA: A Kalman Optimization Algorithm with Loss Adaptivity AAAI 2022 Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training NeurIPS 2022 LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL ICLR 2022 Learning to Optimize: A Primer and A Benchmark JMLR 2022 Learning to Schedule Learning rate with Graph Neural Networks ICLR 2022 Less Is More: Pay Less Attention in Vision Transformers AAAI 2022 LocoProp: Enhancing BackProp via Local Loss Optimization AISTATS 2022 LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness NeurIPS 2022 Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape AISTATS 2022 M³ViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design NeurIPS 2022 Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach NeurIPS 2022 MAML and ANIL Provably Learn Representations ICML 2022 Mask More and Mask Later: Efficient Pre-training of Masked Language Models by Disentangling the [MASK] Token EMNLP 2022 Memory-Efficient Training of RNN-Transducer with Sampled Softmax Interspeech 2022 Minimizing Control for Credit Assignment with Strong Feedback ICML 2022 Modify Self-Attention via Skeleton Decomposition for Effective Point Cloud Transformer AAAI 2022 Multirate Training of Neural Networks ICML 2022