PulseAugur
LIVE 15:25:02
research · [2 sources] ·
0
research

Binary neural networks show compression doesn't always boost generalization

Researchers have analyzed the training dynamics of binary neural networks (BNNs) using information plane analysis, a method that studies mutual information between inputs, representations, and targets. They identified conditions under which mutual information estimates are reliable, noting that outside these regimes, estimates can become uninformative. Their experiments with 375 BNNs revealed that while late-stage compression is common, it does not consistently lead to better generalization performance, with the relationship being highly dependent on specific tasks, architectures, and regularization techniques. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Investigates the complex relationship between compression and generalization in BNNs, potentially informing future model design.

RANK_REASON This is a research paper published on arXiv detailing a new analysis method for binary neural networks.

Read on arXiv cs.LG →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Maximilian Nothnagel, Bernhard C. Geiger ·

    Information Plane Analysis of Binary Neural Networks

    arXiv:2605.03636v1 Announce Type: new Abstract: Information plane (IP) analysis has been suggested to study the training dynamics of deep neural networks through mutual information (MI) between inputs, representations, and targets. However, its statistical validity is often compr…

  2. arXiv cs.LG TIER_1 · Bernhard C. Geiger ·

    Information Plane Analysis of Binary Neural Networks

    Information plane (IP) analysis has been suggested to study the training dynamics of deep neural networks through mutual information (MI) between inputs, representations, and targets. However, its statistical validity is often compromised by the difficulty of estimating MI from s…