trade-off
In AI, a trade-off refers to the balance between two competing objectives, such as accuracy and computational efficiency. For example, when designing a model, you may need to compromise on model complexity to achieve real-time performance.
- Computational Efficiency under Covariate Shift in Kernel Ridge Regression
- Credal Prediction based on Relative Likelihood
- DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing
- Design-Based Bandits Under Network Interference: Trade-Off Between Regret and Statistical Inference
- Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks
- Fair Deepfake Detectors Can Generalize
- Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets
- Neural Mutual Information Estimation with Vector Copulas
- Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure
- On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels
- Robustifying Learning-Augmented Caching Efficiently without Compromising 1-Consistency
- Strategyproof Reinforcement Learning from Human Feedback
- T-norm Selection for Object Detection in Autonomous Driving with Logical Constraints
- Taming Adversarial Constraints in CMDPs
- The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements
- Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach
- When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization
- Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering