sparse-learning

Awesome Multitask Learning Resources

Modular and scalable computational imaging in Python with GPU/out-of-core computing.

Sparse Switchable Normalization with sparse activation function SparestMax

SLIDE (Sub-LInear Deep learning Engine) written in Go

Unsupervised Feature Selection based on Adaptive Similarity Learning and Subspace Clustering

SPoT: Subpixel Placement of Tokens in Vision Transformers

Low-rank Dictionary Learning for Unsupervised Feature Selection

A Pytorch library for stochastic variational inference with sparsity inducing priors.

[AAAI 2019] "A Probabilistic Derivation of LASSO and L12-Norm Feature Selections", Di Ming, Chris Ding, Feiping Nie

This repo is an educational POC showing how thermodynamic sampling units can produce sparse polynomial approximations. It’s intended for demonstration, not production.

[JASA] Reconstruct Ising Model with Global Optimality via SLIDE

[IJCAI 2019] "Robust Flexible Feature Selection via Exclusive L21 Regularization", Di Ming, Chris Ding

[ICML24] Better Locally Private Sparse Estimation Given Multiple Samples Per User

34.1M LM on a laptop CPU: 215,771 tok/s, 8,529x Qwen. QSELM beats Qwen3.5-0.8B on sealed long-document QA (90.6% vs 45.8%) and Qwen3-0.6B-FC on cross-turn agent memory (69.6% vs 3.2%). No GPU. | 笔记本CPU训练34.1M模型：21.6万token/s，实测为Qwen的8,529倍；长文档问答，QSELM 90.6%，Qwen3.5-0.8B 45.8%；Agent跨轮次记忆，QSELM 69.6%，Qwen3-0.6B-FC 3.2%；无需独显。

SG-XDEAT: Sparsity-Guided Cross-Dimensional and Cross-Encoding Attention with Target-Aware Conditioning in Tabular Learning

R package for Sparse Learning with weighted SVMs