microsoft / DGTLinks
Learning Accurate Decision Trees with Bandit Feedback via Quantized Gradient Descent
☆17Updated 3 years ago
Alternatives and similar repositories for DGT
Users that are interested in DGT are comparing it to the libraries listed below
Sorting:
- A Learnable LSH Framework for Efficient NN Training☆34Updated 4 years ago
- Using FlexAttention to compute attention with different masking patterns☆47Updated last year
- FlexAttention w/ FlashAttention3 Support☆27Updated last year
- Blog post☆17Updated last year
- Source-to-Source Debuggable Derivatives in Pure Python☆15Updated 2 years ago
- "Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices", official implementation☆30Updated 11 months ago
- ☆21Updated 5 years ago
- ☆16Updated 2 years ago
- ☆11Updated 2 years ago
- Code for testing DCT plus Sparse (DCTpS) networks☆14Updated 4 years ago
- Triton Implementation of HyperAttention Algorithm☆48Updated 2 years ago
- Implementation of Hyena Hierarchy in JAX☆10Updated 2 years ago
- ☆33Updated last year
- ☆27Updated 2 years ago
- Personal solutions to the Triton Puzzles☆20Updated last year
- Implementation for ACProp ( Momentum centering and asynchronous update for adaptive gradient methdos, NeurIPS 2021)☆16Updated 4 years ago
- Nonparametric Score Estimators, ICML 2020☆36Updated 4 years ago
- Experiment of using Tangent to autodiff triton☆82Updated 2 years ago
- [NeurIPS 2023] Sparse Modular Activation for Efficient Sequence Modeling☆40Updated 2 years ago
- Code for the paper: https://arxiv.org/pdf/2309.06979.pdf☆21Updated last year
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆69Updated last year
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆46Updated last year
- Hyperparameter tuning via uncertainty modeling☆49Updated last year
- Efficient Riemannian Optimization on Stiefel Manifold via Cayley Transform☆44Updated 6 years ago
- Supplementary code for the paper "Meta-Solver for Neural Ordinary Differential Equations" https://arxiv.org/abs/2103.08561☆25Updated 4 years ago
- TaskMet Task-driven Metric Learning for Model Learning☆20Updated last year
- Official repository for the paper "Going Beyond Linear Transformers with Recurrent Fast Weight Programmers" (NeurIPS 2021)☆51Updated 7 months ago
- Structured matrices for compressing neural networks☆67Updated 2 years ago
- ☆12Updated 3 years ago
- [ICML'21 Oral] Improving Lossless Compression Rates via Monte Carlo Bits-Back Coding☆14Updated 4 years ago