The following pages link to Matthieu Wyart (Q1396853):
Displaying 20 items.
- Statistical models for company growth (Q1396854) (← links)
- Landscape and training regimes in deep learning (Q2231925) (← links)
- Geometric compression of invariant manifolds in neural networks (Q3382321) (← links)
- Relation between bid–ask spread, impact and volatility in order-driven markets (Q3518387) (← links)
- Fluctuations and response in financial markets: the subtle nature of ‘random’ price changes (Q4610223) (← links)
- Friction law and hysteresis in granular materials (Q4646200) (← links)
- Locality defeats the curse of dimensionality in convolutional teacher–student scenarios* (Q5055428) (← links)
- Relative stability toward diffeomorphisms indicates performance in deep nets* (Q5055429) (← links)
- Infinitesimal asphericity changes the universality of the jamming transition (Q5135090) (← links)
- Hydrodynamic-driven morphogenesis of karst draperies: spatio-temporal analysis of the two-dimensional impulse response – CORRIGENDUM (Q5155017) (← links)
- Universality of jamming of nonspherical particles (Q5222820) (← links)
- Hydrodynamic-driven morphogenesis of karst draperies: spatio-temporal analysis of the two-dimensional impulse response (Q5853508) (← links)
- Comparing dynamics: deep neural networks versus glassy systems (Q5854115) (← links)
- Scaling description of generalization with number of parameters in deep learning (Q5856249) (← links)
- Disentangling feature and lazy training in deep neural networks (Q5857444) (← links)
- Asymptotic learning curves of kernel methods: empirical data versus teacher–student paradigm (Q5857446) (← links)
- A jamming transition from under- to over-parametrization affects generalization in deep learning (Q5872795) (← links)
- Dynamics and Correlations among Soft Excitations in Marginally Stable Glasses (Q6258082) (← links)
- Learning sparse features can lead to overfitting in neural networks (Q6611436) (← links)
- Armouring of a frictional interface by mechanical noise (Q6635286) (← links)
