Global Convergence of SGD For Logistic Loss on Two Layer Neural Nets.
Pulkit GopalaniSamyak JhaAnirbit MukherjeePublished in: Trans. Mach. Learn. Res. (2024)
Keyphrases
- neural nets
- global convergence
- multi layer
- single layer
- global optimum
- convergence analysis
- convergence rate
- optimization methods
- convergence speed
- convex minimization
- neural network
- feed forward
- back propagation
- particle swarm
- learning tasks
- artificial neural networks
- hybrid algorithm
- simulated annealing
- step size
- learning rate
- decision making
- feature selection