paper-with-me

홈 › Papers

Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shifts

2023-02-13 · Ha Manh Bui, Anqi Liu

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.

📄 PDF Abstract BibTeX arXiv:2302.06495

Code (1)

angie-lab-jhu/density_softmax 공식 구현 jax

Tasks

Computational Efficiency

Methods 이 논문이 사용한 방법론

Test 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Deep Ensembles 설명 없음

Similar Papers 제목 키워드 기반

Density-Regression: Efficient and Distance-Aware Deep Regressor for Uncertainty Estimation under Distribution Shifts

2024-03-07 · Manh Ha Bui, Anqi Liu

Morden deep ensembles technique achieves strong uncertainty estimation performance by going through multiple forward passes with different models. This is at the price of a high storage space and a slow speed in the infe…

Depth EstimationregressionTime Series

Inhibited Softmax for Uncertainty Estimation in Neural Networks

2018-10-03 · Marcin Możejko, Mateusz Susik, Rafał Karczewski

We present a new method for uncertainty estimation and out-of-distribution detection in neural networks with softmax output. We extend softmax layer with an additional constant input. The corresponding additional output …

Out-of-Distribution DetectionSentiment Analysis

Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts

2023-09-25 · Huy Nguyen, Pedram Akbarian, Fanqi Yan, Nhat Ho

Top-K sparse softmax gating mixture of experts has been widely used for scaling up massive deep-learning architectures without increasing the computational cost. Despite its popularity in real-world applications, the the…

Density EstimationMixture-of-Expertsparameter estimation

Assessing Deep Neural Networks as Probability Estimators

2021-11-16 · Yu Pan, Kwo-Sen Kuo, Michael L. Rilee, Hongfeng Yu

Deep Neural Networks (DNNs) have performed admirably in classification tasks. However, the characterization of their classification uncertainties, required for certain applications, has been lacking. In this work, we inv…

Classification

Learning Calibrated Uncertainties for Domain Shift: A Distributionally Robust Learning Approach

2020-10-08 · Haoxuan Wang, Zhiding Yu, Yisong Yue, Anima Anandkumar 외

We propose a framework for learning calibrated uncertainties under domain shifts, where the source (training) distribution differs from the target (test) distribution. We detect such domain shifts via a differentiable de…

Density Ratio EstimationDomain AdaptationUnsupervised Domain Adaptation