PulseAugur
EN
LIVE 09:57:01

Toy models reveal lottery tickets preserve feature-space geometry

Researchers explored the lottery ticket hypothesis, which suggests that sparse subnetworks within dense neural networks can achieve similar performance to the full model. They used a simplified toy model with a structured feature space to investigate what these "winning tickets" preserve. Their findings indicate that these tickets correspond to specific locations in the feature space that are already close to the final learned representations at initialization, with dense training acting as a selection process. AI

IMPACT Provides a mechanistic understanding of lottery ticket subnetworks, potentially informing more efficient model training and compression techniques.

RANK_REASON The cluster contains an academic paper detailing research findings on a specific machine learning concept. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Hugging Face Daily Papers →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Toy models reveal lottery tickets preserve feature-space geometry

COVERAGE [1]

  1. Hugging Face Daily Papers TIER_1 English(EN) ·

    Toy Combinatorial Interpretability Models Reveal Lottery Tickets in Early Feature Space

    The lottery ticket hypothesis posits that dense networks contain sparse subnetworks, ``winning tickets,'' that, when rewound to their initial weights and retrained in isolation, match the performance of the full model. We ask a more mechanistic question: what internal object does…