Skip to content

PyTorch implementation of the Hessian-free optimizer using GMRES instead of CG

active 2023-08-162025-09-15 (UTC)

Complete coverage26,691 / 26,691 hourly files (100%) · 2 absent upstream2023-08-152026-08-31 (UTC)
Events
51
Pushes
6
Pull requests
4
Issues
5
Stars
19
Forks
4

Activity over time

Daily event counts in the loaded window

Line chart, 762 days from 2023-08-16 to 2025-09-15. Pushes: 6 total, peak 4 in a day. Pull requests: 4 total, peak 1 in a day. Issues: 5 total, peak 2 in a day. Comments: 13 total, peak 3 in a day. Stars: 19 total, peak 8 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
ltatzel17627
f-pfeiffer5003
f-dangel3012
youli-jlu2001
sfetzel1010

Recent activity

Latest issues, pull requests and releases

  • Issue comment#7youli-jlu2024-07-01 09:01
    Can't save model via the pytorch-lighting ModelCheckpoint()
  • Issue comment#7ltatzel2024-07-01 07:18
    Can't save model via the pytorch-lighting ModelCheckpoint()
  • Issue#7ltatzel2024-07-01 07:18
    Can't save model via the pytorch-lighting ModelCheckpoint()
  • Issue#7youli-jlu2024-07-01 05:19
    Can't save model via the pytorch-lighting ModelCheckpoint()
  • Pull request#6ltatzel2024-06-14 09:25
  • Issue comment#6f-dangel2024-06-13 15:05
    [REF] Disable gradients if possible
  • Issue comment#6f-dangel2024-06-13 13:49
    [REF] Disable gradients if possible
  • Issue comment#6ltatzel2024-06-13 08:52
    [REF] Disable gradients if possible
  • Pull request#6f-dangel2024-06-12 16:41
  • Issue comment#5ltatzel2024-06-11 15:09
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Issue comment#5f-pfeiffer2024-06-11 14:56
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Issue comment#5ltatzel2024-06-11 08:00
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Issue comment#5f-pfeiffer2024-06-10 17:43
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Issue comment#5ltatzel2024-06-06 16:16
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Pull request#4ltatzel2024-06-06 13:08
  • Issue#5f-pfeiffer2024-06-05 21:11
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Issue comment#5f-pfeiffer2024-06-05 19:22
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Issue comment#4ltatzel2024-06-05 13:43
    Added preconditioning functionality
  • Issue comment#5ltatzel2024-06-05 12:59
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Issue#5f-pfeiffer2024-06-03 23:29
    Use the HF optimizer for Reinforcement Learning (TD3)
  • Pull request#4sfetzel2024-05-22 13:18
  • Issue#3ltatzel2023-08-16 13:38
    How to plug the Hessian matrix into the loss function in pytorch?

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 19 stars here means stars gained during the window, not the repo's star count.