loss functions
Loss functions are mathematical formulations used to quantify the difference between predicted outcomes and actual targets during model training, guiding the optimization process to improve model performance.
- APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction
- Feasibility-Aware Decision-Focused Learning for Predicting Parameters in the Constraints
- Learning Task-Agnostic Representations through Multi-Teacher Distillation
- Learning from Interval Targets
- Learning to Integrate Diffusion ODEs by Averaging the Derivatives
- Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization
- Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification
- Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models
- Sampled Estimators For Softmax Must Be Biased
- Selective Omniprediction and Fair Abstention
- SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models
- Towards Multi-Table Learning: A Novel Paradigm for Complementarity Quantification and Integration