Loss Functions

Neuron-level Structured Pruning using Polarization Regularizer NeurIPS 2020 Normalized Loss Functions for Deep Learning with Noisy Labels ICML 2020 Obtaining Adjustable Regularization for Free via Iterate Averaging ICML 2020 On Long-Tailed Phenomena in Neural Machine Translation EMNLP 2020 On Losses for Modern Language Models EMNLP 2020 On Parameter Adaptation in Softmax-Based Cross-Entropy Loss for Improved Convergence Speed and Accuracy in DNN-Based Speaker Recognition Interspeech 2020 On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks AAAI 2020 Optimizing Nondecomposable Data Dependent Regularizers via Lagrangian Reparameterization Offers Significant Performance and Efficiency Gains AAAI 2020 Parameterized Rate-Distortion Stochastic Encoder ICML 2020 Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates ICML 2020 Photon: A Robust Cross-Domain Text-to-SQL System ACL 2020 Piecewise linear activations substantially shape the loss surfaces of neural networks ICLR 2020 PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss Interspeech 2020 Posterior Calibrated Training on Sentence Classification Tasks ACL 2020 Prime Sample Attention in Object Detection CVPR 2020 Proxy Anchor Loss for Deep Metric Learning CVPR 2020 Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting EMNLP 2020 Regularization via Structural Label Smoothing AISTATS 2020 Regularizing activations in neural networks via distribution matching with the Wasserstein metric ICLR 2020 Regularizing Class-Wise Predictions via Self-Knowledge Distillation CVPR 2020 Regularizing CNN Transfer Learning With Randomised Regression CVPR 2020 Rescuing neural spike train models from bad MLE NeurIPS 2020 Rethinking Softmax Cross-Entropy Loss for Adversarial Robustness ICLR 2020 Revisiting Knowledge Distillation via Label Smoothing Regularization CVPR 2020 Re-Weighted Interval Loss for Handling Data Imbalance Problem of End-to-End Keyword Spotting Interspeech 2020