Cover Image

Navigating Extremes: Dynamic Sparsity in Large Output Spaces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ullah, Nasib, Schultheis, Erik, Lasby, Mike, Ioannou, Yani, Babbar, Rohit
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces
by: Ullah, Nasib, et al.
Published: (2026)

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

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

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

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

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

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression
by: Lasby, Mike, et al.
Published: (2025)

Learning Fine-grained Parameter Sharing via Sparse Tensor Decomposition
by: Üyük, Cem, et al.
Published: (2024)

Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks
by: Mohammadizadeh, Mahdi, et al.
Published: (2024)

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

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

SD$^2$: Self-Distilled Sparse Drafters
by: Lasby, Mike, et al.
Published: (2025)

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

Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
by: Guo, Wentao, et al.
Published: (2024)

Learning label-label correlations in Extreme Multi-label Classification via Label Features
by: Kharbanda, Siddhant, et al.
Published: (2024)

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

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

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

FedPaI: Achieving Extreme Sparsity in Federated Learning via Pruning at Initialization
by: Wang, Haonan, et al.
Published: (2025)

Beyond One-Way Pruning: Bidirectional Pruning-Regrowth for Extreme Accuracy-Sparsity Tradeoff
by: Liu, Junchen, et al.
Published: (2025)

EXION: Exploiting Inter- and Intra-Iteration Output Sparsity for Diffusion Models
by: Heo, Jaehoon, et al.
Published: (2025)

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

Revisiting Transformers through the Lens of Low Entropy and Dynamic Sparsity
by: Ren, Ruifeng, et al.
Published: (2025)

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

Activation Sparsity Opportunities for Compressing General Large Language Models
by: Dhar, Nobel, et al.
Published: (2024)

Large Language Model Compression with Global Rank and Sparsity Optimization
by: Zhou, Changhai, et al.
Published: (2025)

Extreme Model Compression with Structured Sparsity at Low Precision
by: Liu, Dan, et al.
Published: (2025)

Dynamic Sparsity: Challenging Common Sparsity Assumptions for Learning World Models in Robotic Reinforcement Learning Benchmarks
by: Pandaram, Muthukumar, et al.
Published: (2025)

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

Enhancing Large Multimodal Models with Adaptive Sparsity and KV Cache Compression
by: Zhang, Te, et al.
Published: (2025)

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

Improving Decision Sparsity
by: Sun, Yiyang, et al.
Published: (2024)

Homeostasis and Sparsity in Transformer
by: Kotyuzanskiy, Leonid, et al.
Published: (2024)

Polar Sparsity: High Throughput Batched LLM Inferencing with Scalable Contextual Sparsity
by: Shrestha, Susav, et al.
Published: (2025)

Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling
by: Xiao, Qiao, et al.
Published: (2026)

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

Expressiveness of Multi-Neuron Convex Relaxations in Neural Network Certification
by: Mao, Yuhao, et al.
Published: (2024)

Evaluating the Limits of Large Language Models in Multilingual Legal Reasoning
by: Ioannou, Antreas, et al.
Published: (2025)

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

Sparsity-Aware Low-Rank Representation for Efficient Fine-Tuning of Large Language Models
by: Zhang, Longteng, et al.
Published: (2026)