Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts
Autor: | Bui, Ha Manh, Liu, Anqi |
---|---|
Rok vydání: | 2023 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | Sampling-based methods, e.g., Deep Ensembles and Bayesian Neural Nets have become promising approaches to improve the quality of uncertainty estimation and robust generalization. However, they suffer from a large model size and high latency at test-time, which limits the scalability needed for low-resource devices and real-time applications. To resolve these computational issues, we propose Density-Softmax, a sampling-free deterministic framework via combining a density function built on a Lipschitz-constrained feature extractor with the softmax layer. Theoretically, we show that our model is the solution of minimax uncertainty risk and is distance-aware on feature space, thus reducing the over-confidence of the standard softmax under distribution shifts. Empirically, our method enjoys competitive results with state-of-the-art techniques in terms of uncertainty and robustness, while having a lower number of model parameters and a lower latency at test-time. Comment: International Conference on Machine Learning, 2024 |
Databáze: | arXiv |
Externí odkaz: |