Sparse Learning

A Differential Inclusion Approach for Learning Heterogeneous Sparsity in Neuroimaging Analysis AISTATS 2025 Joint Reference Microphone Selection and Filter Order Determination in Multi-channel Active Noise Control Interspeech 2025 Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention ACL 2025 SpinSVAR: Estimating Structural Vector Autoregression Assuming Sparse Input UAI 2025 Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models EMNLP 2024 How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective NeurIPS 2024 Improving Decision Sparsity NeurIPS 2024 Locality Sensitive Sparse Encoding for Learning World Models Online ICLR 2024 Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NeurIPS 2024 Solving Sparse \& High-Dimensional-Output Regression via Compression NeurIPS 2024 Sparse maximal update parameterization: A holistic approach to sparse training dynamics NeurIPS 2024 Symmetry-Informed Governing Equation Discovery NeurIPS 2024 UltraSparseBERT: 99% Conditionally Sparse Language Modelling ACL 2024 XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection ACL 2024 Feature Adaptation for Sparse Linear Regression NeurIPS 2023 L0Learn: A Scalable Package for Sparse Learning using L0 Regularization JMLR 2023 Sparse Low-rank Adaptation of Pre-trained Language Models EMNLP 2023 Sparse Parameterization for Epitomic Dataset Distillation NeurIPS 2023 Acceleration in Distributed Sparse Regression NeurIPS 2022 Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning CVPR 2022 Early-Bird GCNs: Graph-Network Co-optimization towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Tickets AAAI 2022 Get More at Once: Alternating Sparse Training with Gradient Correction NeurIPS 2022 Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation COLT 2022 Learning the Structure of Large Networked Systems Obeying Conservation Laws NeurIPS 2022 Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks NeurIPS 2022