Copertina

MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Sun, Yan, Zhang, Qixin, Yu, Zhiyuan, Zhang, Xikun, Shen, Li, Tao, Dacheng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Convergent Differential Privacy Analysis for General Federated Learning
di: Sun, Yan, et al.
Pubblicazione: (2024)

Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives
di: Zhang, Qixin, et al.
Pubblicazione: (2025)

Toward Efficient Permutation for Hierarchical N:M Sparsity on GPUs
di: Yu, Seungmin, et al.
Pubblicazione: (2024)

Continual Learning on Graphs: Challenges, Solutions, and Opportunities
di: Zhang, Xikun, et al.
Pubblicazione: (2024)

Minimum Variance Unbiased N:M Sparsity for the Neural Gradients
di: Chmiel, Brian, et al.
Pubblicazione: (2022)

Topology-aware Embedding Memory for Continual Learning on Expanding Networks
di: Zhang, Xikun, et al.
Pubblicazione: (2024)

Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers
di: Bambhaniya, Abhimanyu Rajeshkumar, et al.
Pubblicazione: (2024)

Amber Pruner: Leveraging N:M Activation Sparsity for Efficient Prefill in Large Language Models
di: An, Tai, et al.
Pubblicazione: (2025)

SeWA: Selective Weight Average via Probabilistic Masking
di: Wang, Peng, et al.
Pubblicazione: (2025)

Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency
di: Zhang, Qixin, et al.
Pubblicazione: (2025)

ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
di: Huang, Ning-Chi, et al.
Pubblicazione: (2024)

Efficient Differentiable Causal Discovery via Reliable Super-Structure Learning
di: Ma, Pingchuan, et al.
Pubblicazione: (2026)

E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity
di: Li, Yun, et al.
Pubblicazione: (2023)

TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks
di: Meng, Xiang, et al.
Pubblicazione: (2025)

Multinoulli Extension: A Lossless Continuous Relaxation for Partition-Constrained Subset Selection
di: Zhang, Qixin, et al.
Pubblicazione: (2026)

Rethinking the Personalized Relaxed Initialization in the Federated Learning: Consistency and Generalization
di: Shen, Li, et al.
Pubblicazione: (2026)

A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Needs
di: Sun, Yan, et al.
Pubblicazione: (2024)

JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models
di: Chen, Michael K., et al.
Pubblicazione: (2025)

Learning System Dynamics without Forgetting
di: Zhang, Xikun, et al.
Pubblicazione: (2024)

Towards Understanding Generalization and Stability Gaps between Centralized and Decentralized Federated Learning
di: Sun, Yan, et al.
Pubblicazione: (2023)

Near-Oracle KV Selection via Pre-hoc Sparsity for Long-Context Inference
di: Gao, Yifei, et al.
Pubblicazione: (2026)

Improving Large Language Models with Concept-Aware Fine-Tuning
di: Chen, Michael K., et al.
Pubblicazione: (2025)

Accelerating LLM Inference with Flexible N:M Sparsity via A Fully Digital Compute-in-Memory Accelerator
di: Ramachandran, Akshat, et al.
Pubblicazione: (2025)

Sparse by Rule: Probability-Based N:M Pruning for Spiking Neural Networks
di: Ye, Shuhan, et al.
Pubblicazione: (2025)

Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
di: Ma, Guozheng, et al.
Pubblicazione: (2025)

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
di: Sun, Yan, et al.
Pubblicazione: (2025)

Motivating Next-Gen Accelerators with Flexible (N:M) Activation Sparsity via Benchmarking Lightweight Post-Training Sparsification Approaches
di: Alanova, Shirin, et al.
Pubblicazione: (2025)

ProxSparse: Regularized Learning of Semi-Structured Sparsity Masks for Pretrained LLMs
di: Liu, Hongyi, et al.
Pubblicazione: (2025)

Learning Multi-Relational Graph Representations for DNA Methylation-Based Biological Age Estimation
di: Qing, Qing, et al.
Pubblicazione: (2026)

FPGA Co-Design for Efficient N:M Sparse and Quantized Model Inference
di: Hsieh, Fen-Yu, et al.
Pubblicazione: (2025)

Mitigating Barren Plateaus in Quantum Denoising Diffusion Probabilistic Model
di: Cao, Haipeng, et al.
Pubblicazione: (2025)

Learning Multi-Agent Communication from Graph Modeling Perspective
di: Hu, Shengchao, et al.
Pubblicazione: (2024)

ProSparse: Introducing and Enhancing Intrinsic Activation Sparsity within Large Language Models
di: Song, Chenyang, et al.
Pubblicazione: (2024)

SAU: Sparsity-Aware Unlearning for LLMs via Gradient Masking and Importance Redistribution
di: Wang, Yuze, et al.
Pubblicazione: (2026)

HERO: Heterogeneous Continual Graph Learning via Meta-Knowledge Distillation
di: Sun, Guiquan, et al.
Pubblicazione: (2025)

DRIFT: A Benchmark for Task-Free Continual Graph Learning with Continuous Distribution Shifts
di: Sun, Guiquan, et al.
Pubblicazione: (2026)

PermLLM: Learnable Channel Permutation for N:M Sparse Large Language Models
di: Zou, Lancheng, et al.
Pubblicazione: (2025)

RNM-TD3: N:M Semi-structured Sparse Reinforcement Learning From Scratch
di: Vrce, Isam, et al.
Pubblicazione: (2026)

CMKL: Modality-Aware Continual Learning for Evolving Biomedical Knowledge Graphs
di: Radwan, Yousef A., et al.
Pubblicazione: (2026)

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
di: Zhang, Jingyi, et al.
Pubblicazione: (2025)