SourceStalecollected in 47h

2019 Paper Nails Coffin on DL Theory

2019 Paper Nails Coffin on DL Theory
PostLinkedIn
⚖️Read original on AI Alignment Forum
#neural-networks#statistical-learningdeep-learning-theoryzhang-et-al-2016nagarajan-kolter-2019bartlett-foster-telgarsky

💡Discover why data-dependent bounds failed, reshaping DL theory

⚡ 30-Second TL;DR

What Changed

Zhang 2016 showed NNs memorize random labels, breaking data-independent complexity bounds.

Why It Matters

Undermined classical statistical learning theory for NNs, shifting focus to empirical understanding and new paradigms in DL research.

What To Do Next

Read Nagarajan-Kolter 2019 to critique your own generalization bounds for NNs.

Who should care:Researchers & Academics

Key Points

  • Zhang 2016 showed NNs memorize random labels, breaking data-independent complexity bounds.
  • Post-2016 efforts used data-dependent metrics like spectral norms and margins.
  • Nagarajan-Kolter 2019 proved uniform convergence cannot explain deep net generalization.
📰

Weekly AI Recap

Read this week's curated digest of top AI events →

👉Related Updates

AI-curated news aggregator. All content rights belong to original publishers.
Original source: AI Alignment Forum

This is a summary, not the original. Read the source, or get the weekly briefing.

The weekly digest

One email a week. Unsubscribe anytime.