English
Related papers

Related papers: Deciphering Shortcut Learning from an Evolutionary…

200 papers

When training neural networks, it has been widely observed that a large step size is essential in stochastic gradient descent (SGD) for obtaining superior models. However, the effect of large step sizes on the success of SGD is not well…

Machine Learning · Computer Science 2023-02-17 Amirkeivan Mohtashami , Martin Jaggi , Sebastian Stich

Deep neural networks exhibit a simplicity bias, a well-documented tendency to favor simple functions over complex ones. In this work, we cast new light on this phenomenon through the lens of the Minimum Description Length principle,…

Deep neural networks (DNNs) are vulnerable to shortcut learning: rather than learning the intended task, they tend to draw inconclusive relationships between their inputs and outputs. Shortcut learning is ubiquitous among many failure cases…

Machine Learning · Computer Science 2024-08-27 Hadi M. Dolatabadi , Sarah M. Erfani , Christopher Leckie

Models are expected to engage in invariance learning, which involves distinguishing the core relations that remain consistent across varying environments to ensure the predictions are safe, robust and fair. While existing works consider…

Machine Learning · Computer Science 2025-03-11 Yang Xu , Yihong Gu , Cong Fang

Deep Neural Networks are highly susceptible to shortcut learning, frequently memorizing low-dimensional spurious correlations instead of underlying causal mechanisms. This phenomenon not only degrades out-of-distribution robustness but also…

Machine Learning · Computer Science 2026-04-14 Nicolas Rodriguez-Alvarez , Fernando Rodriguez-Merino

Stochastic Gradient Descent (SGD) based training of neural networks with a large learning rate or a small batch-size typically ends in well-generalizing, flat regions of the weight space, as indicated by small eigenvalues of the Hessian of…

Machine Learning · Statistics 2019-12-24 Stanisław Jastrzębski , Zachary Kenton , Nicolas Ballas , Asja Fischer , Yoshua Bengio , Amos Storkey

We identify and formalize a fundamental gradient descent phenomenon resulting in a learning proclivity in over-parameterized neural networks. Gradient Starvation arises when cross-entropy loss is minimized by capturing only a subset of…

Machine Learning · Computer Science 2021-11-25 Mohammad Pezeshki , Sékou-Oumar Kaba , Yoshua Bengio , Aaron Courville , Doina Precup , Guillaume Lajoie

Generalist robot policies trained on large-scale datasets such as Open X-Embodiment (OXE) demonstrate strong performance across a wide range of tasks. However, they often struggle to generalize beyond the distribution of their training…

Robotics · Computer Science 2025-08-11 Youguang Xing , Xu Luo , Junlin Xie , Lianli Gao , Hengtao Shen , Jingkuan Song

We investigate the inherent bias of Stochastic Gradient Descent (SGD) toward learning low-rank weight matrices during the training of deep neural networks. Our results demonstrate that training with mini-batch SGD and weight decay induces a…

Machine Learning · Computer Science 2024-10-22 Tomer Galanti , Zachary S. Siegel , Aparna Gupte , Tomaso Poggio

Often in language and other areas of cognition, whether two components of an object are identical or not determines if it is well formed. We call such constraints identity effects. When developing a system to learn well-formedness from…

Machine Learning · Computer Science 2022-03-03 S. Brugiapaglia , M. Liu , P. Tupper

The representation of functions by artificial neural networks depends on a large number of parameters in a non-linear fashion. Suitable parameters of these are found by minimizing a 'loss functional', typically by stochastic gradient…

Machine Learning · Computer Science 2021-09-16 Stephan Wojtowytsch

Lipschitz continuity characterizes the worst-case sensitivity of neural networks to small input perturbations; yet its dynamics (i.e. temporal evolution) during training remains under-explored. We present a rigorous mathematical framework…

Machine Learning · Computer Science 2025-11-17 Róisín Luo , James McDermott , Christian Gagné , Qiang Sun , Colm O'Riordan

Recent advancements in deep learning have been primarily driven by the use of large models trained on increasingly vast datasets. While neural scaling laws have emerged to predict network performance given a specific level of computational…

Computer Vision and Pattern Recognition · Computer Science 2023-11-13 Elior Benarous , Sotiris Anagnostidis , Luca Biggio , Thomas Hofmann

The deep learning recipe of casting real-world problems as mathematical optimisation and tackling the optimisation by training deep neural networks using gradient-based optimisation has undoubtedly proven to be a fruitful one. The…

Machine Learning · Statistics 2023-10-24 Mihaela Claudia Rosca

Differentially private stochastic gradient descent (DP-SGD) is known to have poorer training and test performance on large neural networks, compared to ordinary stochastic gradient descent (SGD). In this paper, we perform a detailed study…

Machine Learning · Computer Science 2023-11-14 Lauren Watson , Eric Gan , Mohan Dantam , Baharan Mirzasoleiman , Rik Sarkar

In graph classification, attention and pooling-based graph neural networks (GNNs) prevail to extract the critical features from the input graph and support the prediction. They mostly follow the paradigm of learning to attend, which…

Machine Learning · Computer Science 2022-06-14 Yongduo Sui , Xiang Wang , Jiancan Wu , Min Lin , Xiangnan He , Tat-Seng Chua

The dynamics of gradient-based training in neural networks often exhibit nontrivial structures; hence, understanding them remains a central challenge in theoretical machine learning. In particular, a concept of feature unlearning, in which…

Machine Learning · Computer Science 2026-02-10 Shota Imai , Sota Nishiyama , Masaaki Imaizumi

Stochastic gradient descent (SGD) is often applied to train Deep Neural Networks (DNNs), and research efforts have been devoted to investigate the convergent dynamics of SGD and minima found by SGD. The influencing factors identified in the…

Machine Learning · Computer Science 2020-09-25 Victor Luo , Yazhen Wang

Frequency analysis is useful for understanding the mechanisms of representation learning in neural networks (NNs). Most research in this area focuses on the learning dynamics of NNs for regression tasks, while little for classification.…

Machine Learning · Computer Science 2023-08-31 Shunxin Wang , Raymond Veldhuis , Christoph Brune , Nicola Strisciuglio

Shortcut learning is a phenomenon where machine learning models prioritize learning simple, potentially misleading cues from data that do not generalize well beyond the training set. While existing research primarily investigates this in…

Image and Video Processing · Electrical Eng. & Systems 2024-06-28 Manxi Lin , Nina Weng , Kamil Mikolaj , Zahra Bashir , Morten Bo Søndergaard Svendsen , Martin Tolsgaard , Anders Nymark Christensen , Aasa Feragen