Code for the paper: Why Transformers Need Adam: A Hessian Perspective
☆66Mar 11, 2025Updated last year
Alternatives and similar repositories for hessian-spectrum
Users that are interested in hessian-spectrum are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆14May 5, 2025Updated last year
- ☆11Mar 18, 2025Updated last year
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆462May 13, 2025Updated last year
- The official code of "Mano: Restriking Manifold Optimization for LLM Training".☆26Jun 1, 2026Updated 5 months ago
- Code for "What really matters in matrix-whitening optimizers?"☆25Oct 31, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICLR 2025] This repository contains the code to reproduce the results from our paper From Sparse Dependence to Sparse Attention: Unveili…☆12Mar 7, 2025Updated last year
- Minimal pretraining script for language modeling in PyTorch. Supporting torch compilation and DDP. It includes a model implementation and…☆52Apr 27, 2026Updated 6 months ago
- ☆10Jul 27, 2026Updated 3 months ago
- Using PyTorch autograd to compute Hessian of Perplexity for Large Language Models☆30Apr 17, 2025Updated last year
- ☆290Dec 2, 2024Updated last year
- Spectral Sphere Optimizer☆135Mar 23, 2026Updated 7 months ago
- ☆40Feb 26, 2024Updated 2 years ago
- Code for Paper (Policy Optimization in RLHF: The Impact of Out-of-preference Data)☆29Dec 19, 2023Updated 2 years ago
- Official implementation for the paper "Controlled Sparsity via Constrained Optimization"☆12Aug 10, 2022Updated 4 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- A tale of works on the complexity of second-order (and high-order) min-max optimization.☆12Oct 12, 2026Updated 3 weeks ago
- Second-Order Fine-Tuning without Pain for LLMs: a Hessian Informed Zeroth-Order Optimizer☆28Feb 11, 2025Updated last year
- The loss landscape of Large Language Models resemble basin!☆49Jul 8, 2025Updated last year
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆30Oct 14, 2025Updated last year
- Code for the NeurIPS 2020 paper "Improved analysis of clippind algorithms for non-convex optimization", including various clipping algori…☆10Feb 17, 2021Updated 5 years ago
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Aug 30, 2023Updated 3 years ago
- My attempt to improve the speed of the newton schulz algorithm, starting from the dion implementation.☆42Apr 30, 2026Updated 6 months ago
- Code for Dayal Kalra's research internship on scalable curvature measures for neural networks.☆33Feb 3, 2026Updated 9 months ago
- ☆16Apr 15, 2026Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Code for DASH, a faster alternative to Distributed Shampoo via block stacking.☆13Feb 18, 2026Updated 8 months ago
- ☆15May 4, 2024Updated 2 years ago
- ☆11Sep 20, 2024Updated 2 years ago
- [ICML 2025] Flat-LoRA: Low-Rank Adaptation over a Flat Loss Landscape☆18May 18, 2025Updated last year
- Kinetics: Rethinking Test-Time Scaling Laws☆87Jul 11, 2025Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆94Oct 30, 2024Updated 2 years ago
- An implementation of the penalty-based bilevel gradient descent (PBGD) algorithm and the iterative differentiation (ITD/RHG) methods.☆20Feb 13, 2023Updated 3 years ago
- Implementation of various equivariant models in JAX☆18Apr 12, 2024Updated 2 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs with LoRA support.☆30Feb 19, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆291Updated this week
- Benchmarking Optimizers for LLM Pretraining. NeurIPS 2026, EurIPS 2025☆61May 3, 2026Updated 6 months ago
- Irene is a python package that aims to be a toolkit for global optimization problems that can be realized algebraically. It generalizes L…☆15Oct 27, 2026Updated last week
- GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection☆1,712Oct 28, 2024Updated 2 years ago
- Muon is Scalable for LLM Training☆1,560Aug 3, 2025Updated last year
- NeurIPS'24 - LLM Safety Landscape☆41Oct 21, 2025Updated last year
- Code for reproducing figures and results in the paper ``Early stopping in deep networks: Double descent and how to eliminate it''☆15Jun 27, 2022Updated 4 years ago