[ICLR'24] "DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training" by Aochuan Chen*, Yimeng Zhang*, Jinghan Jia, James Diffenderfer, Jiancheng Liu, Konstantinos Parasyris, Yihua Zhang, Zheng Zhang, Bhavya Kailkhura, Sijia Liu
☆72Oct 9, 2024Updated last year
Alternatives and similar repositories for DeepZero
Users that are interested in DeepZero are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- This project is a implementation in PyTorch for ZO-AdaMU optimization: Adapting Perturbation with the Momentum and Uncertainty in Zeroth-…☆15Dec 12, 2023Updated 2 years ago
- [ICML‘24] Official code for the paper "Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ".☆128Jul 6, 2025Updated last year
- Code the ICML 2024 paper: "Variance-reduced Zeroth-Order Methods for Fine-Tuning Language Models"☆12Jun 25, 2024Updated 2 years ago
- Second-Order Fine-Tuning without Pain for LLMs: a Hessian Informed Zeroth-Order Optimizer☆26Feb 11, 2025Updated last year
- [EMNLP 24] Source code for paper 'AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tu…☆13Dec 15, 2024Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- [NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333☆1,171Jan 11, 2024Updated 2 years ago
- Robustify Black-Box Models (ICLR'22 - Spotlight)☆23Jan 29, 2023Updated 3 years ago
- Fine-tuning Quantized Neural Networks with Zeroth-order Optimization☆20Sep 17, 2025Updated 10 months ago
- [ICLR 2023] Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation☆12Jul 31, 2023Updated 3 years ago
- ZOSVRG-BlackBox-Adv☆12Oct 30, 2018Updated 7 years ago
- LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning☆38Apr 4, 2024Updated 2 years ago
- Source code for the TMLR paper "Black-Box Prompt Learning for Pre-trained Language Models"☆59Sep 7, 2023Updated 2 years ago
- Code for "Thinking Forward: Memory-Efficient Federated Finetuning of Language Models" (NeurIPS 2024). Spry is a federated learning al…☆13Oct 8, 2024Updated last year
- [CVPR23] "Understanding and Improving Visual Prompting: A Label-Mapping Perspective" by Aochuan Chen, Yuguang Yao, Pin-Yu Chen, Yihua Zha…☆52Sep 17, 2023Updated 2 years 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.
- Implementation of "Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes" (https://…☆13May 6, 2024Updated 2 years ago
- This is the implementation for IEEE S&P 2022 paper "Model Orthogonalization: Class Distance Hardening in Neural Networks for Better Secur…☆11Aug 24, 2022Updated 3 years ago
- ☆10Oct 31, 2022Updated 3 years ago
- "ZINB-based Graph Embedding Autoencoder for Single-cell RNA-seq Interpretations" in AAAI 2022☆28Feb 5, 2023Updated 3 years ago
- Official repo for PAC-Bayes Information Bottleneck. ICLR 2022.☆49May 11, 2022Updated 4 years ago
- [ICLR 2025] Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization☆28Jan 27, 2026Updated 6 months ago
- Official code for the paper "Examining Post-Training Quantization for Mixture-of-Experts: A Benchmark"☆31Jun 30, 2025Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆44Aug 14, 2024Updated last year
- ☆28Nov 9, 2022Updated 3 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆19Apr 10, 2017Updated 9 years ago
- [ICML2022] Training Your Sparse Neural Network Better with Any Mask. Ajay Jaiswal, Haoyu Ma, Tianlong Chen, ying Ding, and Zhangyang Wang☆30Jul 24, 2022Updated 4 years ago
- The source code of the paper "Efficient Privacy-Preserving Federated Learning with Compressed Sensing"☆21May 23, 2024Updated 2 years ago
- [ICLR26] Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs☆24Apr 8, 2026Updated 4 months ago
- Revisiting Parameter Sharing for Automatic Neural Channel Number Search, NeurIPS 2020☆21Nov 15, 2020Updated 5 years ago
- [ICLR 2025] REFINE: Inversion-Free Backdoor Defense via Model Reprogramming☆13Feb 13, 2025Updated last year
- Clustered Federated Learning via Gradient-based Partitioning (ICML 2024)☆15Jun 15, 2025Updated last year
- Disguising Attacks with Explanation-Aware Backdoors (IEEE S&P 2023)☆12Jan 3, 2026Updated 7 months ago
- Source code for ECCV 2022 Poster: Data-free Backdoor Removal based on Channel Lipschitzness☆36Jan 9, 2023Updated 3 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- [Neurips 2022] “ Back Razor: Memory-Efficient Transfer Learning by Self-Sparsified Backpropogation”, Ziyu Jiang*, Xuxi Chen*, Xueqin Huan…☆19Mar 14, 2023Updated 3 years ago
- This is the proof-of-concept CPU implementation of ASPEN used for the NeurIPS'23 paper ASPEN: Breaking Operator Barriers for Efficient Pa…☆13Apr 4, 2024Updated 2 years ago
- ☆30Jun 27, 2022Updated 4 years ago
- Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793☆457May 13, 2025Updated last year
- [NeurIPS2023] "Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning" by Yihua Zhang*, Yimeng Zhang*,…☆14Oct 12, 2023Updated 2 years ago
- ☆35Dec 14, 2023Updated 2 years ago
- [ASPDAC23] High Dimensional Yield Estimation using Shrinkage Deep Features and Maximization of Integral Entropy Reduction☆14Oct 9, 2022Updated 3 years ago