Safety, Alignment & InterpretabilityH. Brendan McMahan et al. (Google)Google

Google presents FedAvg / federated learning

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

Presented FedAvg / federated learning — training without collecting data distributed across devices, with 10 to 100 times fewer communication rounds than synchronous SGD

Why it matters

Opened up the path to on-device training on mobile

Source — Primary sources first; secondary reports are labelled “Press”

Paperarxiv.orghttps://arxiv.org/abs/1602.05629

Added in Week 35, 2026 · See that week

On the map — ⑩ Safety, Alignment line

  1. Previous stopThe line starts here
  2. This record · stopFedAvg
  3. Next stopToy Models of Superposition
See it on the map

Nearby on the same axis

Google presents Deep Learning with Differential Privacy (DP-SGD)PaperToy Models of SuperpositionPaperDPOPaperOpenAI launches Superalignment teamOfficial