Cover Image

Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wen, Yuxiao, Jacot, Arthur
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff
by: Jacot, Arthur
Published: (2023)

Hamiltonian Mechanics of Feature Learning: Bottleneck Structure in Leaky ResNets
by: Jacot, Arthur, et al.
Published: (2024)

How DNNs break the Curse of Dimensionality: Compositionality and Symmetry Learning
by: Jacot, Arthur, et al.
Published: (2024)

Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
by: Tu, Zhenfeng, et al.
Published: (2024)

Saddle-To-Saddle Dynamics in Deep ReLU Networks: Low-Rank Bias in the First Saddle Escape
by: Bantzis, Ioannis, et al.
Published: (2025)

Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
by: Xiong, Jiafeng, et al.
Published: (2025)

Learning to Intervene on Concept Bottlenecks
by: Steinmann, David, et al.
Published: (2023)

Group and Exclusive Sparse Regularization-based Continual Learning of CNNs
by: Tousside, Basile, et al.
Published: (2026)

Understanding Emergent Abilities of Language Models from the Loss Perspective
by: Du, Zhengxiao, et al.
Published: (2024)

These Are Not All the Features You Are Looking For: A Fundamental Bottleneck in Supervised Pretraining
by: Yang, Xingyu Alice, et al.
Published: (2025)

GaGSL: Global-augmented Graph Structure Learning via Graph Information Bottleneck
by: Li, Shuangjie, et al.
Published: (2024)

Understanding Emergent Misalignment via Feature Superposition Geometry
by: Minegishi, Gouki, et al.
Published: (2026)

The Geometry of Concepts: Sparse Autoencoder Feature Structure
by: Li, Yuxiao, et al.
Published: (2024)

Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
by: Yang, Yuxiao, et al.
Published: (2026)

On The Potential of The Fractal Geometry and The CNNs Ability to Encode it
by: Zini, Julia El, et al.
Published: (2024)

Thought Anchors: Which LLM Reasoning Steps Matter?
by: Bogdan, Paul C., et al.
Published: (2025)

Deep Learning with CNNs: A Compact Holistic Tutorial with Focus on Supervised Regression (Preprint)
by: Tejeda, Yansel Gonzalez, et al.
Published: (2024)

Credal Concept Bottleneck Models: Structural Separation of Epistemic and Aleatoric Uncertainty
by: Mukherjee, Tanmoy, et al.
Published: (2026)

Is Value Learning Really the Main Bottleneck in Offline RL?
by: Park, Seohong, et al.
Published: (2024)

Learning Concept Bottleneck Models from Mechanistic Explanations
by: De Santis, Antonio, et al.
Published: (2026)

IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning
by: Zou, Xiandong, et al.
Published: (2025)

Prediction Bottlenecks Don't Discover Causal Structure (But Here's What They Actually Do)
by: Lade, Ankit Hemant, et al.
Published: (2026)

TimeX++: Learning Time-Series Explanations with Information Bottleneck
by: Liu, Zichuan, et al.
Published: (2024)

Learning Fair Graph Representations with Multi-view Information Bottleneck
by: Liu, Chuxun, et al.
Published: (2025)

Phase-Aware Deep Learning with Complex-Valued CNNs for Audio Signal Applications
by: Agrawal, Naman
Published: (2025)

The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulation
by: Deng, Huiqi, et al.
Published: (2025)

Handling Long and Richly Constrained Tasks through Constrained Hierarchical Reinforcement Learning
by: Lu, Yuxiao, et al.
Published: (2023)

No More Adam: Learning Rate Scaling at Initialization is All You Need
by: Xu, Minghao, et al.
Published: (2024)

Deep Learning as a Convex Paradigm of Computation: Minimizing Circuit Size with ResNets
by: Jacot, Arthur
Published: (2025)

Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?
by: Vahedifar, Mohammad Ali, et al.
Published: (2026)

SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
by: Zhang, Hanwei, et al.
Published: (2026)

Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
by: Zhao, Zhe, et al.
Published: (2024)

Invariant Graph Learning Meets Information Bottleneck for Out-of-Distribution Generalization
by: Mao, Wenyu, et al.
Published: (2024)

Dynamic Graph Information Bottleneck
by: Yuan, Haonan, et al.
Published: (2024)

Counterfactual Concept Bottleneck Models
by: Dominici, Gabriele, et al.
Published: (2024)

Object Centric Concept Bottlenecks
by: Steinmann, David, et al.
Published: (2025)

Mixture of Concept Bottleneck Experts
by: De Santis, Francesco, et al.
Published: (2026)

Conditional Clifford-Steerable CNNs with Complete Kernel Basis for PDE Modeling
by: Szarvas, Bálint László, et al.
Published: (2025)

From Predictive Importance to Causality: Which Machine Learning Model Reflects Reality?
by: Arshad, Muhammad Arbab, et al.
Published: (2024)

Policy Learning with a Language Bottleneck
by: Srivastava, Megha, et al.
Published: (2024)