Greedy Search Algorithm for Mixed Precision in Post-Training Quantization of Convolutional Neural Network Inspired by Submodular Optimization.
Satoki TsujiHiroshi KawaguchiAtsuki InoueYasufumi SakaiFuyuka YamadaPublished in: ACML (2021)
Keyphrases
- search algorithm
- convolutional neural network
- greedy algorithm
- search space
- global search
- global optimization
- optimization problems
- high precision
- heuristic search
- face detection
- branch and bound
- feature selection
- stochastic search
- precision and recall
- tabu search
- optimization algorithm
- test set
- training set
- squeaky wheel
- hill climbing
- training process
- optimization process
- combinatorial optimization
- optimization method
- artificial neural networks
- feature vectors
- energy minimization
- supervised learning
- lower bound
- computational complexity
- stochastic gradient descent
- greedy algorithms
- genetic algorithm
- training samples