PhD Position F/M Generalization bounds for neural networks
Inria
il y a 9 jours
Date de publicationil y a 9 jours
S/O
Niveau d'expérienceS/O
Temps pleinType de contrat
Temps pleinSystèmes d'information / RéseauxCatégorie d'emploi
Systèmes d'information / RéseauxContexte et atouts du poste
The PhD position will be in the framework of the ERC Starting Grant DYNASTY (Dynamics-Aware Theory of Deep Learning).
The position might include traveling to conferences for paper presentation. Travel expenses will be covered within the limits of the scale in force.
Mission confiée
Understanding generalization in deep learning has been one of the major challenges in statistical learning theory over the last decade. While recent work has illustrated that the dataset and the training algorithm must be taken into account in order to obtain meaningful generalization bounds, it is still theoretically not clear which properties of the data and the algorithm determine the generalization performance. In this phd, we will approach this problem from a dynamical systems theory perspective and exploit the fractal structure that the stochastic optimization algorithms produce [1].
We aim to prove that the generalization error of a stochastic optimization algorithm can be understood by using fractal geometry and dynamical systems theory. The results will be evaluated on modern neural networks, and new efficient algorithms will be developed based on the developed theory.
References
[1] Camuto, Alexander, et al. "Fractal structure and generalization properties of stochastic
optimization algorithms." Advances in Neural Information Processing Systems 34 (2021): 18774-18788.
Principales activités
Main activities :
Compétences
Technical skills and level required :
Languages :
Relational skills :
Other valued appreciated :
Avantages
The PhD position will be in the framework of the ERC Starting Grant DYNASTY (Dynamics-Aware Theory of Deep Learning).
The position might include traveling to conferences for paper presentation. Travel expenses will be covered within the limits of the scale in force.
Mission confiée
Understanding generalization in deep learning has been one of the major challenges in statistical learning theory over the last decade. While recent work has illustrated that the dataset and the training algorithm must be taken into account in order to obtain meaningful generalization bounds, it is still theoretically not clear which properties of the data and the algorithm determine the generalization performance. In this phd, we will approach this problem from a dynamical systems theory perspective and exploit the fractal structure that the stochastic optimization algorithms produce [1].
We aim to prove that the generalization error of a stochastic optimization algorithm can be understood by using fractal geometry and dynamical systems theory. The results will be evaluated on modern neural networks, and new efficient algorithms will be developed based on the developed theory.
References
[1] Camuto, Alexander, et al. "Fractal structure and generalization properties of stochastic
optimization algorithms." Advances in Neural Information Processing Systems 34 (2021): 18774-18788.
Principales activités
Main activities :
- Conduct theoretical research
Conduct experiments for empirical verification
Write scientific articles
Disseminate the scientific work in appropriate venues.
Compétences
Technical skills and level required :
Languages :
Relational skills :
Other valued appreciated :
Avantages
- Subsidized meals
- Partial reimbursement of public transport costs
- Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
- Possibility of teleworking and flexible organization of working hours
- Professional equipment available (videoconferencing, loan of computer equipment, etc.)
- Social, cultural and sports events and activities
- Access to vocational training
- Social security coverage
RÉSUMÉ DE L' OFFRE
PhD Position F/M Generalization bounds for neural networks
Inria
Paris
il y a 9 jours
S/O
Temps plein
PhD Position F/M Generalization bounds for neural networks