Lemmy: Bestiverse
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
RSS BotMB to Hacker NewsEnglish · 2 months ago

MHC: Manifold-Constrained Hyper-Connections

arxiv.org

external-link
message-square
0
link
fedilink
3
external-link

MHC: Manifold-Constrained Hyper-Connections

arxiv.org

RSS BotMB to Hacker NewsEnglish · 2 months ago
message-square
0
link
fedilink
mHC: Manifold-Constrained Hyper-Connections
arxiv.org
external-link
Recently, studies exemplified by Hyper-Connections (HC) have extended the ubiquitous residual connection paradigm established over the past decade by expanding the residual stream width and diversifying connectivity patterns. While yielding substantial performance gains, this diversification fundamentally compromises the identity mapping property intrinsic to the residual connection, which causes severe training instability and restricted scalability, and additionally incurs notable memory access overhead. To address these challenges, we propose Manifold-Constrained Hyper-Connections (mHC), a general framework that projects the residual connection space of HC onto a specific manifold to restore the identity mapping property, while incorporating rigorous infrastructure optimization to ensure efficiency. Empirical experiments demonstrate that mHC is effective for training at scale, offering tangible performance improvements and superior scalability. We anticipate that mHC, as a flexible and practical extension of HC, will contribute to a deeper understanding of topological architecture design and suggest promising directions for the evolution of foundational models.

Comments

alert-triangle
You must log in or # to comment.

Hacker News

hackernews

Subscribe from Remote Instance

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !hackernews@lemmy.bestiver.se
lock
Community locked: only moderators can create posts. You can still comment on posts.

Posts from the RSS Feed of HackerNews.

The feed sometimes contains ads and posts that have been removed by the mod team at HN.

Source of the RSS Bot

Visibility: Public
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 389 users / day
  • 1.51K users / week
  • 3.64K users / month
  • 9.26K users / 6 months
  • 2 local subscribers
  • 4.3K subscribers
  • 43.5K Posts
  • 21.1K Comments
  • Modlog
  • mods:
  • patrick
  • RSS Bot
  • BE: 0.19.15
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org