Parameter tuning for convergence / divergence of global model

kdmalc / personalization-privacy-risk

Privacy analysis for ML and classical filtering personalization parameters

0 stars 0 forks source link

Parameter tuning for convergence / divergence of global model #11

Open kdmalc opened 1 year ago

kdmalc commented 1 year ago

What is optimal global aggregation and model push down strat? What is optimal number of iters per update? What is optimal eta for each training loop? This presumably affects the above