Hugging Face Trending Papers June 29, 2026

SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model

Read the original on Hugging Face Trending Papers →

Neural networks are known to be susceptible to over-reliance on spurious correlations. However, the precise mechanism by which models exploit shortcut features is not fully understood, and algorithms to mitigate this behavior rely on as yet unjustified assumptions about the learned representations.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

safety

arXiv Machine Learning

Jun 30

SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model

arXiv:2606. 30444v1 Announce Type: cross Abstract: Neural networks are known to be susceptible to over-reliance on spurious correlations.

By Tyler LaBonte, Vidya Muthukumar

safety

arXiv Machine Learning

Jun 5

Deciphering Two Training Clocks in Grokking via Deep Linear Network Theory with Conditional ReLU Reduction

arXiv:2606. 05863v1 Announce Type: new Abstract: Grokking suggests that fitting the training data and learning a simple underlying rule may occur on different time scales.

By Hu Tan, Kuo Gai, Shihua Zhang

rag

arXiv Machine Learning

Jun 30

Favorability of Loss Landscape with Weight Decay Requires Both Large Overparametrization and Initialization

arXiv:2505. 22578v2 Announce Type: replace Abstract: The optimization of neural networks under weight decay remains poorly understood from a theoretical standpoint.

By Etienne Boursier, Matthew Bowditch, Matthias Englert, Ranko Lazic

arXiv AI

Jun 11

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

arXiv:2606. 12138v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training runs.

By Gleb Gerasimov, Timofei Rusalev, Nikita Balagansky, Daniil Laptev, Vadim Kurochkin, Daniil Gavrilov

arXiv Machine Learning

Jun 18

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?

arXiv:2603. 04895v2 Announce Type: replace-cross Abstract: Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima.

By Kuo-Wei Lai, Guanghui Wang, Molei Tao, Vidya Muthukumar

safety

arXiv Machine Learning

Jun 2

How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations

arXiv:2606. 02385v1 Announce Type: cross Abstract: Sparse Autoencoders (SAEs) have found success parsing neural representations into interpretable concepts, providing a basis for understanding and control.

By William Dorrell

Related stories

SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model

Deciphering Two Training Clocks in Grokking via Deep Linear Network Theory with Conditional ReLU Reduction

Favorability of Loss Landscape with Weight Decay Requires Both Large Overparametrization and Initialization

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?

How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations