#optimization
topicoptimization
2 papers · 1 filter
cs.LG2020★ 10 cited
Reconciling Modern Deep Learning with Traditional Optimization Analyses: The Intrinsic Learning Rate
Zhiyuan Li, Kaifeng Lyu, Sanjeev Arora
The paper proposes an 'intrinsic learning rate' that combines the usual learning rate and weight decay to model the training dynamics of normalized deep networks via stochastic dif…
cs.CV2019
Unsupervised Image Matching and Object Discovery as Optimization
Huy V. Vo, Francis Bach, Minsu Cho +4
The paper reformulates unsupervised object category discovery and image matching as a formal optimization problem and demonstrates its effectiveness on benchmark datasets.