paper-with-me

Papers

Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization

2021-05-12 · CVPR 2022 1 · Damien Teney, Ehsan Abbasnejad, Simon Lucey, Anton Van Den Hengel

Neural networks trained with SGD were recently shown to rely preferentially on linearly-predictive features and can ignore complex, equally-predictive ones. This simplicity bias can explain their lack of robustness out of distribution (OOD). The more complex the task to learn, the more likely it is that statistical artifacts (i.e. selection biases, spurious correlations) are simpler than the mechanisms to learn. We demonstrate that the simplicity bias can be mitigated and OOD generalization improved. We train a set of similar models to fit the data in different ways using a penalty on the alignment of their input gradients. We show theoretically and empirically that this induces the learning of more complex predictive patterns. OOD generalization fundamentally requires information beyond i.i.d. examples, such as multiple training environments, counterfactual examples, or other side information. Our approach shows that we can defer this requirement to an independent model selection stage. We obtain SOTA results in visual recognition on biased data and generalization across visual domains. The method - the first to evade the simplicity bias - highlights the need for a better understanding and control of inductive biases in deep learning.

📄 PDF Abstract BibTeX arXiv:2105.05612

Code (1)

dteney/collages-dataset 공식 구현

Tasks

counterfactualModel Selection

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

The Rich and the Simple: On the Implicit Bias of Adam and SGD

2025-05-29 · Bhavya Vasudeva, Jung Whan Lee, Vatsal Sharan, Mahdi Soltanolkotabi

Adam is the de facto optimization algorithm for several deep learning applications, but an understanding of its implicit bias and how it differs from other algorithms, particularly standard first-order methods such as (s…

Binary Classification

Mitigating Simplicity Bias in Deep Learning for Improved OOD Generalization and Robustness

2023-10-09 · Bhavya Vasudeva, Kameron Shahabi, Vatsal Sharan

Neural networks (NNs) are known to exhibit simplicity bias where they tend to prefer learning 'simple' features over more 'complex' ones, even when the latter may be more informative. Simplicity bias can lead to the mode…

Fairness

Discovering New Interpretable Conservation Laws as Sparse Invariants

2023-05-31 · Ziming Liu, Patrick Obin Sturm, Saketh Bharadwaj, Sam Silva 외

Discovering conservation laws for a given dynamical system is important but challenging. In a theorist setup (differential equations and basis functions are both known), we propose the Sparse Invariant Detector (SID), an…

Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data

2024-05-27 · Nikita Tsoy, Nikola Konstantinov

Simplicity bias, the propensity of deep models to over-rely on simple features, has been identified as a potential reason for limited out-of-distribution generalization of neural networks (Shah et al., 2020). Despite the…

Out-of-Distribution Generalization

Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks

2022-10-04 · Sravanti Addepalli, Anshul Nasery, R. Venkatesh Babu, Praneeth Netrapalli 외

Deep Neural Networks are known to be brittle to even minor distribution shifts compared to the training distribution. While one line of work has demonstrated that Simplicity Bias (SB) of DNNs - bias towards learning only…