OPTML-Group / DeepZero
[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
☆35Updated 6 months ago
Related projects: ⓘ
- [ICML 2024] Official code for the paper "Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ".☆62Updated 2 months ago
- ☆31Updated last year
- Deep Learning & Information Bottleneck☆45Updated last year
- [NeurIPS 2022] Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach -- Official Implementation☆40Updated last year
- Code for the paper "Efficient Dataset Distillation using Random Feature Approximation"☆36Updated last year
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆31Updated 5 months ago
- [ICLR 2024] Improving Convergence and Generalization Using Parameter Symmetries☆26Updated 3 months ago
- Sharpness-Aware Minimization Leads to Low-Rank Features [NeurIPS 2023]☆24Updated 11 months ago
- [NeurIPS‘2021] "MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge", Geng Yuan, Xiaolong Ma, Yanzhi Wang et al…☆17Updated 2 years ago
- [ICML2022] Training Your Sparse Neural Network Better with Any Mask. Ajay Jaiswal, Haoyu Ma, Tianlong Chen, ying Ding, and Zhangyang Wang☆23Updated 2 years ago
- Reproducing RigL (ICML 2020) as a part of ML Reproducibility Challenge 2020☆26Updated 2 years ago
- Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation (ICML'24 Oral)☆8Updated last month
- SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining☆15Updated 2 months ago
- A curated list of Model Merging methods.☆71Updated this week
- [TPAMI 2023] Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces☆38Updated 2 years ago
- Good Subnetworks Provably Exist: Pruning via Greedy Forward Selection☆21Updated 3 years ago
- [IJCAI 2023] Black-box Prompt Tuning for Vision-Language Model as a Service☆14Updated last year
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆14Updated 3 months ago
- FusionBench: A Comprehensive Benchmark of Deep Model Fusion☆42Updated 2 weeks ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆40Updated 2 weeks ago
- [NeurIPS 2021] A Geometric Analysis of Neural Collapse with Unconstrained Features☆50Updated 2 years ago
- [ICLR 2023] "Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!" Shiwei Liu, Tianlong Chen, Zhenyu Zhang, Xuxi Chen…☆27Updated last year
- [AAAI-2022] Up to 100x Faster Data-free Knowledge Distillation☆66Updated last year
- Weight-Averaged Sharpness-Aware Minimization (NeurIPS 2022)☆25Updated last year
- [ICLR 2021] "Long Live the Lottery: The Existence of Winning Tickets in Lifelong Learning" by Tianlong Chen*, Zhenyu Zhang*, Sijia Liu, S…☆22Updated 2 years ago
- Code for the paper: Why Transformers Need Adam: A Hessian Perspective☆27Updated 4 months ago
- [NeurIPS 2023] Code release for "Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity"☆15Updated 11 months ago
- Can GPT-4 Perform Neural Architecture Search?☆82Updated last year
- Implementation of Effective Sparsification of Neural Networks with Global Sparsity Constraint☆28Updated 2 years ago
- ☆44Updated 11 months ago