Cover Image

The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Walker, Thomas, Humayun, Ahmed Imtiaz, Balestriero, Randall, Baraniuk, Richard
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

GrokAlign: Geometric Characterisation and Acceleration of Grokking
by: Walker, Thomas, et al.
Published: (2025)

On the Geometry of Deep Learning
by: Balestriero, Randall, et al.
Published: (2024)

The Geometric Structure of Models Learning Sparse Data
by: Walker, Thomas, et al.
Published: (2026)

Deep Networks Always Grok and Here is Why
by: Humayun, Ahmed Imtiaz, et al.
Published: (2024)

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries
by: Humayun, Ahmed Imtiaz, et al.
Published: (2023)

Mitigating over-exploration in latent space optimization using LES
by: Ronen, Omer, et al.
Published: (2024)

Self-Improving Diffusion Models with Synthetic Data
by: Alemohammad, Sina, et al.
Published: (2024)

Learning by Reconstruction Produces Uninformative Features For Perception
by: Balestriero, Randall, et al.
Published: (2024)

Eidetic Learning: an Efficient and Provable Solution to Catastrophic Forgetting
by: Dronen, Nicholas, et al.
Published: (2025)

ALLoRA: Adaptive Learning Rate Mitigates LoRA Fatal Flaws
by: Huang, Hai, et al.
Published: (2024)

Task Priors: Enhancing Model Evaluation by Considering the Entire Space of Downstream Tasks
by: Patel, Niket, et al.
Published: (2025)

No Location Left Behind: Measuring and Improving the Fairness of Implicit Representations for Earth Data
by: Cai, Daniel, et al.
Published: (2025)

SAFE: A Novel Approach to AI Weather Evaluation through Stratified Assessments of Forecasts over Earth
by: Masi, Nick, et al.
Published: (2025)

Occam's Razor for Self Supervised Learning: What is Sufficient to Learn Good Representations?
by: Ibrahim, Mark, et al.
Published: (2024)

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
by: Hsu, Chia-Hong, et al.
Published: (2026)

The Common Intuition to Transfer Learning Can Win or Lose: Case Studies for Linear Regression
by: Dar, Yehuda, et al.
Published: (2021)

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
by: Balestriero, Randall, et al.
Published: (2025)

Fast and Exact Enumeration of Deep Networks Partitions Regions
by: Balestriero, Randall, et al.
Published: (2024)

Curvature Tuning: Provable Training-free Model Steering From a Single Parameter
by: Hu, Leyang, et al.
Published: (2025)

Max-Affine Spline Insights Into Deep Network Pruning
by: You, Haoran, et al.
Published: (2021)

Improving Routing in Sparse Mixture of Experts with Graph of Tokens
by: Nguyen, Tam, et al.
Published: (2025)

Learning Transferable Features for Implicit Neural Representations
by: Vyas, Kushal, et al.
Published: (2024)

Semantic Tube Prediction: Beating LLM Data Efficiency with JEPA
by: Huang, Hai, et al.
Published: (2026)

Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations
by: Mialon, Grégoire, et al.
Published: (2022)

Gradient-Direction Sensitivity Reveals Linear-Centroid Coupling Hidden by Optimizer Trajectories
by: Xu, Yongzhong
Published: (2026)

Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research
by: Reizinger, Patrik, et al.
Published: (2025)

Characterizing Large Language Model Geometry Helps Solve Toxicity Detection and Generation
by: Balestriero, Randall, et al.
Published: (2023)

The Fair Language Model Paradox
by: Pinto, Andrea, et al.
Published: (2024)

Self-Supervised Anomaly Detection in the Wild: Favor Joint Embeddings Methods
by: Otero, Daniel, et al.
Published: (2024)

Your Attention Matters: to Improve Model Robustness to Noise and Spurious Correlations
by: Tamayo-Rousseau, Camilo, et al.
Published: (2025)

LNUCB-TA: Linear-nonlinear Hybrid Bandit Learning with Temporal Attention
by: Khosravi, Hamed, et al.
Published: (2025)

Is your algorithm unlearning or untraining?
by: Triantafillou, Eleni, et al.
Published: (2026)

MazeNet: An Accurate, Fast, and Scalable Deep Learning Solution for Steiner Minimum Trees
by: Ramos, Gabriel Díaz, et al.
Published: (2024)

Double Descent and Other Interpolation Phenomena in GANs
by: Luzi, Lorenzo, et al.
Published: (2021)

Gaussian Embeddings: How JEPAs Secretly Learn Your Data Density
by: Balestriero, Randall, et al.
Published: (2025)

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
by: Feizi, Aarash, et al.
Published: (2024)

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
by: Lu, Wenquan, et al.
Published: (2025)

PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning
by: Lu, Wenquan, et al.
Published: (2026)

On Hypothesis Transfer Learning of Functional Linear Models
by: Lin, Haotian, et al.
Published: (2022)

Circuit Complexity of Hierarchical Knowledge Tracing and Implications for Log-Precision Transformers
by: Liu, Naiming, et al.
Published: (2026)