Neural Network Optimization

AutoLR: Layer-wise Pruning and Auto-tuning of Learning Rates in Fine-tuning of Deep Networks AAAI 2021 Automated Concatenation of Embeddings for Structured Prediction ACL 2021 Automated Machine Learning on Graphs: A Survey IJCAI 2021 AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression IJCAI 2021 AutoSpace: Neural Architecture Search With Less Human Interference ICCV 2021 Benefit of deep learning with non-convex noisy gradient descent: Provable excess risk bound and superiority to kernel methods ICLR 2021 Benign Overfitting of Constant-Stepsize SGD for Linear Regression COLT 2021 BERTAC: Enhancing Transformer-based Language Models with Adversarially Pretrained Convolutional Neural Networks ACL 2021 BERxiT: Early Exiting for BERT with Better Fine-Tuning and Extension to Regression EACL 2021 Beyond Reptile: Meta-Learned Dot-Product Maximization between Gradients for Improved Single-Task Regularization EMNLP 2021 Bidirectional Hierarchical Attention Networks based on Document-level Context for Emotion Cause Extraction EMNLP 2021 BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining NeurIPS 2021 calibrated adversarial training ACML 2021 Can Selfless Learning Improve Accuracy of a Single Classification Task? WACV 2021 Catastrophic Fisher Explosion: Early Phase Fisher Matrix Impacts Generalization ICML 2021 Catformer: Designing Stable Transformers via Sensitivity Analysis ICML 2021 Channel Permutations for N:M Sparsity NeurIPS 2021 Characterizing possible failure modes in physics-informed neural networks NeurIPS 2021 CLUZH at SIGMORPHON 2021 Shared Task on Multilingual Grapheme-to-Phoneme Conversion: Variations on a Baseline ACL 2021 Combinatorial Learning of Graph Edit Distance via Dynamic Embedding CVPR 2021 Combined Depth Space Based Architecture Search for Person Re-Identification CVPR 2021 Compatibility-Aware Heterogeneous Visual Search CVPR 2021 Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks WACV 2021 Consistent Accelerated Inference via Confident Adaptive Transformers EMNLP 2021 Constrained Weight Optimization for Learning Without Activation Normalization WACV 2021