Wyart, Matthieu

1. A Phase Transition in Diffusion Models Reveals the Hierarchical Nature of Data
   2024/02/26 by Antonio Sclocchi, Sclocchi, Antonio, Alessandro Favero +3 · 9 citations
   Computer Science · Physics and Astronomy · #Advanced Mathematical Modeling in Engineering #Advanced Thermodynamics and Statistical Mechanics #Computer Vision and Pattern Recognition (cs.CV) #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Theoretical and Computational Physics
2. Relation between Bid-Ask Spread, Impact and Volatility in Double Auction Markets
   2006/03/10 by Matthieu Wyart, Wyart, Matthieu, Jean‐Philippe Bouchaud +7 · 2 citations
   Economics, Econometrics and Finance · Decision Sciences · #Financial Markets and Investment Strategies #Auction Theory and Applications #Complex Systems and Time Series Analysis
3. Inferring the flow properties of epithelial tissues from their geometry
   2020/02/12 by Popović, Marko, Druelle, Valentin, Dye, Natalie A. +2 · 2 citations
   #Biological Physics (physics.bio-ph) #FOS: Physical sciences #Soft Condensed Matter (cond-mat.soft)
4. Learning sparse features can lead to overfitting in neural networks
   2022/06/24 by Leonardo Petrini, Petrini, Leonardo, Francesco Cagnetta +5 · 2 citations
   Computer Science · Mathematics · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Medical Image Segmentation Techniques #Statistical Methods and Inference
5. Towards a theory of how the structure of language is acquired by deep neural networks
   2024/05/28 by Cagnetta, Francesco, Wyart, Matthieu · 3 citations
   #Computation and Language (cs.CL) #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG)
6. Probing the Latent Hierarchical Structure of Data via Diffusion Models
   2024/10/17 by Sclocchi, Antonio, Favero, Alessandro, Levi, Noam Itzhak +1 · 2 citations
   #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
7. Failure and success of the spectral bias prediction for Kernel Ridge Regression: the case of low-dimensional data
   2022/02/07 by Tomasini, Umberto M., Sclocchi, Antonio, Wyart, Matthieu · 1 citation
   #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Statistical Mechanics (cond-mat.stat-mech)
8. Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models
   2025/05/22 by Favero, Alessandro, Sclocchi, Antonio, Wyart, Matthieu · 4 citations
   #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
9. Dissecting the Effects of SGD Noise in Distinct Regimes of Deep Learning
   2023/01/31 by Antonio Sclocchi, Sclocchi, Antonio, Mario Geiger +3 · 1 citation
   Computer Science · Materials Science · #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Generative Adversarial Networks and Image Synthesis #Machine Learning (cs.LG) #Machine Learning in Materials Science #Neural Networks and Applications
10. Learning curves theory for hierarchically compositional data with power-law distributed features
    2025/05/11 by Cagnetta, Francesco, Kang, Hyunmo, Wyart, Matthieu · 2 citations
    #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
11. Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures
    2025/05/11 by Cagnetta, Francesco, Favero, Alessandro, Sclocchi, Antonio +1 · 2 citations
    #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
12. How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
    2025/02/17 by Alessandro Favero, Favero, Alessandro, Antonio Sclocchi +7 · 2 citations
    Psychology · #Creativity in Education and Neuroscience #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)
13. On the Emergence of Linear Analogies in Word Embeddings
    2025/05/24 by Daniel J. Korchinski, Dhruva Karkada, Korchinski, Daniel J. +5 · 1 voice · 1 citation
    Computer Science · Physics and Astronomy · #Computation and Language (cs.CL) #Disordered Systems and Neural Networks (cond-mat.dis-nn) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #cond-mat.dis-nn #cs.CL #cs.LG