AINewsnow

Raising the Batch Size Makes Batch Norm's Inference Statistics 13x Worse

This story is from 2026-09-03. It is preserved in the archive; the latest stories are on the live feed.

In training, batch norm normalises each row with the statistics of the batch it happens to be in. At inference there is no batch, so it uses a running average collected during training. Those are two different functions, and the layer swaps one for the other silently. See it: https://dev48.infy.uk/…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-09-03 05:46 · DEV Community — Machine Learning
    Raising the Batch Size Makes Batch Norm's Inference Statistics 13x Worse

More stories

  1. Anthropic says Claude 'leads' 26 percent of its AI R&D work — Engadget
  2. Google Joins OpenAI, Anthropic, Meta in Disclosing AI Hacks — Bloomberg AI
  3. Introducing Kimi K3 on Amazon Bedrock — AWS Machine Learning Blog
  4. Optimizing agent system prompts with Amazon Bedrock AgentCore — AWS Machine Learning Blog
  5. Introducing Amazon SageMaker HyperPod Inference Gateway — AWS Machine Learning Blog
  6. Introducing Astra for Law — OpenAI News
  7. Gemini Hacked Three Companies in First Known Breakout by Google’s AI — Wall Street Journal Technology
  8. OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system — The Guardian AI

Get the daily brief of stories like this at 6:30 every morning →