Copertina

Efficient Dynamic Structured Sparse Training with Learned Shuffles

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tyagi, Abhishek, Iyer, Arjun, Young, Liam, Renninger, William H, Kanan, Christopher, Zhu, Yuhao
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

Dynamic Sparse Training of Diagonally Sparse Networks
di: Tyagi, Abhishek, et al.
Pubblicazione: (2025)

Efficient Sparse Training with Structured Dropout
di: Lo, Andy
Pubblicazione: (2024)

Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
di: Zhu, Linghao, et al.
Pubblicazione: (2025)

GraVAC: Adaptive Compression for Communication-Efficient Distributed DL Training
di: Tyagi, Sahil, et al.
Pubblicazione: (2023)

Scalable Structure Learning for Sparse Context-Specific Systems
di: Rios, Felix Leopoldo, et al.
Pubblicazione: (2024)

Overcoming the Stability Gap in Continual Learning
di: Harun, Md Yousuf, et al.
Pubblicazione: (2023)

Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning
di: Harun, Md Yousuf, et al.
Pubblicazione: (2025)

A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initialization
di: Harun, Md Yousuf, et al.
Pubblicazione: (2025)

To Shuffle or not to Shuffle: Auditing DP-SGD with Shuffling
di: Annamalai, Meenatchi Sundaram Muthu Selva, et al.
Pubblicazione: (2024)

Thales: Formulating and Estimating Architectural Vulnerability Factors for DNN Accelerators
di: Tyagi, Abhishek, et al.
Pubblicazione: (2022)

OccamNets: Mitigating Dataset Bias by Favoring Simpler Hypotheses
di: Shrestha, Robik, et al.
Pubblicazione: (2022)

Dynamic Sparse Training with Structured Sparsity
di: Lasby, Mike, et al.
Pubblicazione: (2023)

GRASP: A Rehearsal Policy for Efficient Online Continual Learning
di: Harun, Md Yousuf, et al.
Pubblicazione: (2023)

Are Bias Mitigation Techniques for Deep Learning Effective?
di: Shrestha, Robik, et al.
Pubblicazione: (2021)

Grass: Compute Efficient Low-Memory LLM Training with Structured Sparse Gradients
di: Muhamed, Aashiq, et al.
Pubblicazione: (2024)

Group and Shuffle: Efficient Structured Orthogonal Parametrization
di: Gorbunov, Mikhail, et al.
Pubblicazione: (2024)

Joint Learning of Linear Dynamical Systems under Smoothness Constraints
di: Tyagi, Hemant
Pubblicazione: (2024)

WASH: Train your Ensemble with Communication-Efficient Weight Shuffling, then Average
di: Fournier, Louis, et al.
Pubblicazione: (2024)

Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning
di: Ma, Guozheng, et al.
Pubblicazione: (2025)

DART-ing Through the Drift: Dynamic Tracing of Knowledge Neurons for Adaptive Inference-Time Pruning
di: Tyagi, Abhishek, et al.
Pubblicazione: (2026)

Adjusted Shuffling SARAH: Advancing Complexity Analysis via Dynamic Gradient Weighting
di: Nguyen, Duc Toan, et al.
Pubblicazione: (2025)

Efficient Learning of Quantum States Prepared With Few Non-Clifford Gates
di: Grewal, Sabee, et al.
Pubblicazione: (2023)

Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
di: Hu, Pihe, et al.
Pubblicazione: (2024)

Learning Page Order in Shuffled WOO Releases
di: Kahraman, Efe, et al.
Pubblicazione: (2026)

Tula: Optimizing Time, Cost, and Generalization in Distributed Large-Batch Training
di: Tyagi, Sahil, et al.
Pubblicazione: (2026)

OmniLearn: A Framework for Distributed Deep Learning over Heterogeneous Clusters
di: Tyagi, Sahil, et al.
Pubblicazione: (2025)

SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning
di: Pham, Truong, et al.
Pubblicazione: (2026)

Efficient Learning of Quantum States Prepared With Few Non-Clifford Gates II: Single-Copy Measurements
di: Grewal, Sabee, et al.
Pubblicazione: (2023)

Nesterov acceleration in benignly non-convex landscapes
di: Gupta, Kanan, et al.
Pubblicazione: (2024)

Understanding the Effect of Noise in LLM Training Data with Algorithmic Chains of Thought
di: Havrilla, Alex, et al.
Pubblicazione: (2024)

Can Kans (re)discover predictive models for Direct-Drive Laser Fusion?
di: Ejaz, Rahman, et al.
Pubblicazione: (2024)

Shuffling Momentum Gradient Algorithm for Convex Optimization
di: Tran, Trang H., et al.
Pubblicazione: (2024)

Topology-Aware Revival for Efficient Sparse Training
di: Jin, Meiling, et al.
Pubblicazione: (2026)

Temporal Patch Shuffle (TPS): Leveraging Patch-Level Shuffling to Boost Generalization and Robustness in Time Series Forecasting
di: Bakhshaliyev, Jafar, et al.
Pubblicazione: (2026)

Sparse-ProxSkip: Accelerated Sparse-to-Sparse Training in Federated Learning
di: Meinhardt, Georg, et al.
Pubblicazione: (2024)

Dynamic Sparse Learning: A Novel Paradigm for Efficient Recommendation
di: Wang, Shuyao, et al.
Pubblicazione: (2024)

Dynamics of Transient Structure in In-Context Linear Regression Transformers
di: Carroll, Liam, et al.
Pubblicazione: (2025)

Disentangling Dense Embeddings with Sparse Autoencoders
di: O'Neill, Charles, et al.
Pubblicazione: (2024)

Sparse Bayesian Deep Functional Learning with Structured Region Selection
di: Zhu, Xiaoxian, et al.
Pubblicazione: (2026)

Improving Multimodal Large Language Models Using Continual Learning
di: Srivastava, Shikhar, et al.
Pubblicazione: (2024)