Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"
☆437Dec 12, 2024Updated last year
Alternatives and similar repositories for adopt
Users that are interested in adopt are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆290Dec 2, 2024Updated last year
- Schedule-Free Optimization in PyTorch☆2,337Jul 28, 2026Updated 3 months ago
- For optimization algorithm research and development.☆585Oct 23, 2026Updated 3 weeks ago
- The AdEMAMix Optimizer: Better, Faster, Older.☆187Sep 12, 2024Updated 2 years ago
- Efficient optimizers☆340Sep 9, 2026Updated 2 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Getting crystal-like representations with harmonic loss☆196Apr 2, 2025Updated last year
- A minimal toolset for running UI applications within docker isolated X11 environment☆17Jan 11, 2026Updated 10 months ago
- Grams: Gradient Descent with Adaptive Momentum Scaling (ICLR 2025 Workshop)☆18Mar 6, 2025Updated last year
- ☆13May 20, 2026Updated 5 months ago
- PyTorch Implementation of TecNets (Task-Embedded Control Networks)☆10Dec 8, 2022Updated 3 years ago
- [ICLR 2026] When it comes to optimizers, it's always better to be safe than sorry☆421Sep 26, 2025Updated last year
- lightweight, fast and robust columnar dataframe for data analytics with online update☆23Aug 14, 2021Updated 5 years ago
- ☆14Mar 2, 2025Updated last year
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆463May 13, 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.
- 🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch☆2,206Jul 9, 2026Updated 4 months ago
- ☆313Apr 23, 2025Updated last year
- Codes accompanying the paper "LaProp: a Better Way to Combine Momentum with Adaptive Gradient"☆33Jul 30, 2020Updated 6 years ago
- ☆10May 24, 2021Updated 5 years ago
- Muon is an optimizer for hidden layers in neural networks☆2,947May 24, 2026Updated 5 months ago
- ☆72Sep 11, 2026Updated 2 months ago
- a simple exploratory repo for low step flow model☆17Aug 7, 2025Updated last year
- DeMo: Decoupled Momentum Optimization☆202Dec 2, 2024Updated last year
- Triton Implementation of HyperAttention Algorithm☆48Dec 11, 2023Updated 2 years ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- EIPL: Embodied Intelligence with Deep Predictive Learning☆46Dec 12, 2024Updated last year
- MiSS is a novel PEFT method that features a low-rank structure but introduces a new update mechanism distinct from LoRA, achieving an exc…☆37Mar 9, 2026Updated 8 months ago
- Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models☆826Jun 8, 2025Updated last year
- Train VAE like a boss☆313Oct 21, 2024Updated 2 years ago
- ☆69Mar 21, 2025Updated last year
- Official Code for MIMETIC^2☆13Nov 19, 2024Updated 2 years ago
- Official repository for Parallax (Parameterized Local Linear Attention)☆71Jul 30, 2026Updated 3 months ago
- Agent-assisted hyperparameter optimization 📈☆20Aug 2, 2026Updated 3 months ago
- Pixyz Tutorial in RL Architecture Study Group☆11Apr 25, 2019Updated 7 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.
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆94Oct 30, 2024Updated 2 years ago
- Universal Transformer with Memory Tokens. Pure JAX NNX. TPU-ready.☆13May 12, 2026Updated 6 months ago
- [ACL 2023] The official implementation of "CAME: Confidence-guided Adaptive Memory Optimization"☆100Mar 22, 2025Updated last year
- Unofficial Re-implementation of "Dream to Control: Learning Behaviors by Latent Imagination" (https://arxiv.org/abs/1912.01603 ) with PyT…☆32Aug 22, 2020Updated 6 years ago
- ☆13Nov 14, 2024Updated 2 years ago
- Decode a ROS bag once. Query it like a database — and bake it into LeRobot training data, as many times as you like. 🍞☆14Jun 10, 2026Updated 5 months ago
- APOLLO: SGD-like Memory, AdamW-level Performance; MLSys'25 Oustanding Paper Honorable Mention☆368Nov 29, 2025Updated 11 months ago
Are these results useful?