# Research

Here is an overview over three research directions:

## The impact of data structure on learning

*Realistic images concentrate on a low-dimensional manifold in input space.*

### References

- SG, B. Loureiro, G. Reeves, M. Mézard, F. Krzakala, and L. Zdeborová

*The Gaussian equivalence of generative models for learning with two-layer neural networks*

arXiv:2006.14709 - SG, M. Mézard, F. Krzakala, and L. Zdeborová

*Modelling the influence of data structure on learning in neural networks: the hidden manifold model*

Phys. Rev. X*10*, 041044 (2020) arXiv:1911.00500

## The dynamics of learning

*The learning algorithm shapes the path of neural networks in the losslandscape. Image courtesy of S. d'Ascoli*

### References

- M. Refinetti, S. d’Ascoli, R. Ohana, SG

*The dynamics of learning with feedback alignment*

arXiv:2011.12428 - SG, M.S. Advani, A.M. Saxe, F. Krzakala, L. Zdeborová

*Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup*

Advances in Neural Information Processing (NeurIPS) 6979-6989 (2019) arXiv:1906.08632

## Energetic efficiency of learning

*Video abstact on the energetic efficiency of learning. Click to play!*

### References

- SG, U. Seifert

*Thermodynamic efficiency of learning from a teacher*

New J. of Phys.*19*113001 (2017) arXiv:1706.09713 - SG, U. Seifert

*Stochastic Thermodynamics of Learning*

Phys. Rev. Lett.*118*, 010601 (2017) arXiv:1611.09428