Loss Functions

Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation ACL 2022 Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences JMLR 2022 Hard Gate Knowledge Distillation - Leverage Calibration for Robust and Reliable Language Model EMNLP 2022 HaRiM+: Evaluating Summary Quality with Hallucination Risk AACL 2022 Heatmap Distribution Matching for Human Pose Estimation NeurIPS 2022 Hierarchical classification at multiple operating points NeurIPS 2022 Hierarchical Shrinkage: Improving the accuracy and interpretability of tree-based models. ICML 2022 Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning CVPR 2022 iFlood: A Stable and Effective Regularizer ICLR 2022 Improving abstractive summarization with energy-based re-ranking EMNLP 2022 Improving Speech Enhancement through Fine-Grained Speech Characteristics Interspeech 2022 Injecting Logical Constraints into Neural Networks via Straight-Through Estimators ICML 2022 Is Importance Weighting Incompatible with Interpolating Classifiers? ICLR 2022 Knowledge Distillation via the Target-Aware Transformer CVPR 2022 Knowledge Graph Embedding by Adaptive Limit Scoring Loss Using Dynamic Weighting Strategy ACL 2022 Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation COLT 2022 Learnable Adaptive Cosine Estimator (LACE) for Image Classification WACV 2022 Learning Energy Networks with Generalized Fenchel-Young Losses NeurIPS 2022 Learning sparse representations of preferences within Choquet expected utility theory UAI 2022 Learning to Detect Noisy Labels Using Model-Based Features EMNLP 2022 Learning Towards The Largest Margins ICLR 2022 Logit Perturbation AAAI 2022 Long-Tailed Visual Recognition via Gaussian Clouded Logit Adjustment CVPR 2022 Loss as the Inconsistency of a Probabilistic Dependency Graph: Choose Your Model, Not Your Loss Function AISTATS 2022 Loss Function Learning for Domain Generalization by Implicit Gradient ICML 2022