The Effect of Optimization Methods on the Robustness of Out-of-Distribution Detection Approaches

by   Vahdat Abdelzad, et al.
University of Waterloo

Deep neural networks (DNNs) have become the de facto learning mechanism in different domains. Their tendency to perform unreliably on out-of-distribution (OOD) inputs hinders their adoption in critical domains. Several approaches have been proposed for detecting OOD inputs. However, existing approaches still lack robustness. In this paper, we shed light on the robustness of OOD detection (OODD) approaches by revealing the important role of optimization methods. We show that OODD approaches are sensitive to the type of optimization method used during training deep models. Optimization methods can provide different solutions to a non-convex problem and so these solutions may or may not satisfy the assumptions (e.g., distributions of deep features) made by OODD approaches. Furthermore, we propose a robustness score that takes into account the role of optimization methods. This provides a sound way to compare OODD approaches. In addition to comparing several OODD approaches using our proposed robustness score, we demonstrate that some optimization methods provide better solutions for OODD approaches.


page 1

page 2

page 3

page 4


iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection

Machine learning methods such as deep neural networks (DNNs), despite th...

Optimization Methods for Supervised Machine Learning: From Linear Models to Deep Learning

The goal of this tutorial is to introduce key models, algorithms, and op...

Analytical Benchmark Problems for Multifidelity Optimization Methods

The paper presents a collection of analytical benchmark problems specifi...

BAMSProd: A Step towards Generalizing the Adaptive Optimization Methods to Deep Binary Model

Recent methods have significantly reduced the performance degradation of...

Multiplicative update rules for accelerating deep learning training and increasing robustness

Even nowadays, where Deep Learning (DL) has achieved state-of-the-art pe...

Overparameterized Neural Networks Can Implement Associative Memory

Identifying computational mechanisms for memorization and retrieval is a...

Please sign up or login with your details

Forgot password? Click here to reset