Entropic gradient descent algorithms and wide flat minima.
Fabrizio PittorinoCarlo LucibelloChristoph FeinauerEnrico M. MalatestaGabriele PeruginiCarlo BaldassiMatteo NegriElizaveta DemyanenkoRiccardo ZecchinaPublished in: CoRR (2020)
Keyphrases
- computationally efficient
- times faster
- orders of magnitude
- theoretical analysis
- significant improvement
- stochastic approximation
- objective function
- data structure
- optimization problems
- machine learning
- recently developed
- cost function
- pairwise
- learning algorithm
- real time
- computational cost
- np hard
- evolutionary algorithm
- computationally expensive
- case study
- combinatorial optimization