Imagen de Portada

HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ullah, Nasib, Zhang, Jinbin, Randrianantenaina, Jean Lucien, Schultheis, Erik, Babbar, Rohit
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models
por: Zhang, Jinbin, et al.
Publicado: (2025)

Navigating Extremes: Dynamic Sparsity in Large Output Spaces
por: Ullah, Nasib, et al.
Publicado: (2024)

ELMO: Efficiency via Low-precision and Peak Memory Optimization in Large Output Spaces
por: Zhang, Jinbin, et al.
Publicado: (2025)

Labels in Extremes: How Well Calibrated are Extreme Multi-label Classifiers?
por: Ullah, Nasib, et al.
Publicado: (2024)

Large Language Model as a Teacher for Zero-shot Tagging at Extreme Scales
por: Zhang, Jinbin, et al.
Publicado: (2024)

UniDEC : Unified Dual Encoder and Classifier Training for Extreme Multi-Label Classification
por: Kharbanda, Siddhant, et al.
Publicado: (2024)

FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models
por: Modoranu, Ionut-Vlad, et al.
Publicado: (2025)

Generalized test utilities for long-tail performance in extreme multi-label classification
por: Schultheis, Erik, et al.
Publicado: (2023)

A General Online Algorithm for Optimizing Complex Performance Metrics
por: Kotłowski, Wojciech, et al.
Publicado: (2024)

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

InceptionXML: A Lightweight Framework with Synchronized Negative Sampling for Short Text Extreme Classification
por: Kharbanda, Siddhant, et al.
Publicado: (2021)

"What is Different Between These Datasets?" A Framework for Explaining Data Distribution Shifts
por: Babbar, Varun, et al.
Publicado: (2024)

SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention
por: Xu, Hongtao, et al.
Publicado: (2026)

Steering Large Language Model Activations in Sparse Spaces
por: Bayat, Reza, et al.
Publicado: (2025)

NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling
por: Grooten, Bram, et al.
Publicado: (2025)

Hardware-Aware DNN Compression for Homogeneous Edge Devices
por: Zhang, Kunlong, et al.
Publicado: (2025)

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
por: Yuan, Jingyang, et al.
Publicado: (2025)

HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inference
por: Gong, Ping, et al.
Publicado: (2025)

Consistent algorithms for multi-label classification with macro-at-$k$ metrics
por: Schultheis, Erik, et al.
Publicado: (2024)

Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity
por: Sinha, Nilotpal, et al.
Publicado: (2024)

BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative Decoding
por: He, Liang, et al.
Publicado: (2026)

packetLSTM: Dynamic LSTM Framework for Streaming Data with Varying Feature Space
por: Agarwal, Rohit, et al.
Publicado: (2024)

Group-Aware Reinforcement Learning for Output Diversity in Large Language Models
por: Anschel, Oron, et al.
Publicado: (2025)

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces
por: Yu, Shixing, et al.
Publicado: (2026)

Perturbation-efficient Zeroth-order Optimization for Hardware-friendly On-device Training
por: Tan, Qitao, et al.
Publicado: (2025)

Bitwidth-Specific Logarithmic Arithmetic for Future Hardware-Accelerated Training
por: Hamad, Hassan, et al.
Publicado: (2025)

HEAPr: Hessian-based Efficient Atomic Expert Pruning in Output Space
por: Li, Ke, et al.
Publicado: (2025)

Hardware Aware Ensemble Selection for Balancing Predictive Accuracy and Cost
por: Maier, Jannis, et al.
Publicado: (2024)

Improving Sparse Autoencoder with Dynamic Attention
por: Wang, Dongsheng, et al.
Publicado: (2026)

Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
por: Qu, Xingwei, et al.
Publicado: (2025)

DAFOS: Dynamic Adaptive Fanout Optimization Sampler
por: Ullah, Irfan, et al.
Publicado: (2025)

Advancing On-Device Neural Network Training with TinyPropv2: Dynamic, Sparse, and Efficient Backpropagation
por: Rüb, Marcus, et al.
Publicado: (2024)

OATS: Outlier-Aware Pruning Through Sparse and Low Rank Decomposition
por: Zhang, Stephen, et al.
Publicado: (2024)

Efficient On-Policy Reinforcement Learning via Exploration of Sparse Parameter Space
por: Zhang, Xinyu, et al.
Publicado: (2025)

HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
por: Sukthanker, Rhea Sanjay, et al.
Publicado: (2024)

From Rashomon Theory to PRAXIS: Efficient Decision Tree Rashomon Sets
por: Heile, Zakk, et al.
Publicado: (2026)

Gradient-Congruity Guided Federated Sparse Training
por: Tian, Chris Xing, et al.
Publicado: (2024)

Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
por: Choi, Jaemoo, et al.
Publicado: (2026)

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
por: Akkerman, Fabian, et al.
Publicado: (2023)

Accumulator-Aware Post-Training Quantization for Large Language Models
por: Colbert, Ian, et al.
Publicado: (2024)