Identifying and Attacking the Saddle Point Problem in High-Dimensional Non-Convex Optimization.¶
Dauphin, Y. N., Pascanu, R., Gulcehre, C., Cho, K., Ganguli, S., & Bengio, Y. (2014). Identifying and Attacking the Saddle Point Problem in High-Dimensional Non-Convex Optimization. Advances in Neural Information Processing Systems.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Optimization Landscape
- In machine learning, the topology of neural-network loss surfaces — saddle points versus minima, flat versus sharp minima, basin connectivity in over-parameterised models — predicts training behaviour.
This sourceArgues that in high dimensions most critical points of neural loss surfaces are saddles, not minima.
- In machine learning, the topology of neural-network loss surfaces — saddle points versus minima, flat versus sharp minima, basin connectivity in over-parameterised models — predicts training behaviour.
Verification¶
This reference passed the adversarial substantiation pipeline: it was checked to exist and to support the claim it is attached to. See how references were verified.
Registry ID ref:5971b4e864db · see in the full table