Imagen de Portada

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ashkboos, Saleh, Nikdan, Mahdi, Tabesh, Soroush, Castro, Roberto L., Hoefler, Torsten, Alistarh, Dan
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Quartet: Native FP4 Training Can Be Optimal for Large Language Models
por: Castro, Roberto L., et al.
Publicado: (2025)

QuEST: Stable Training of LLMs with 1-Bit Weights and Activations
por: Panferov, Andrei, et al.
Publicado: (2025)

RoSA: Accurate Parameter-Efficient Fine-Tuning via Robust Adaptation
por: Nikdan, Mahdi, et al.
Publicado: (2024)

GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
por: Dadgarnia, Alireza, et al.
Publicado: (2026)

Beyond Outliers: A Study of Optimizers Under Quantization
por: Vlassis, Georgios, et al.
Publicado: (2025)

ECO: Quantized Training without Full-Precision Master Weights
por: Nikdan, Mahdi, et al.
Publicado: (2026)

MARLIN: Mixed-Precision Auto-Regressive Parallel Inference on Large Language Models
por: Frantar, Elias, et al.
Publicado: (2024)

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
por: Ashkboos, Saleh, et al.
Publicado: (2024)

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
por: Panferov, Andrei, et al.
Publicado: (2026)

EfQAT: An Efficient Framework for Quantization-Aware Training
por: Ashkboos, Saleh, et al.
Publicado: (2024)

Efficient Data Selection at Scale via Influence Distillation
por: Nikdan, Mahdi, et al.
Publicado: (2025)

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
por: Egiazarian, Vage, et al.
Publicado: (2025)

WUSH: Near-Optimal Adaptive Transforms for LLM Quantization
por: Chen, Jiale, et al.
Publicado: (2025)

CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training
por: Tabesh, Soroush, et al.
Publicado: (2025)

SliceGPT: Compress Large Language Models by Deleting Rows and Columns
por: Ashkboos, Saleh, et al.
Publicado: (2024)

LLMQ: Efficient Lower-Precision Pretraining for Consumer GPUs
por: Schultheis, Erik, et al.
Publicado: (2025)

Grid Games: The Power of Multiple Grids for Quantizing Large Language Models
por: Egiazarian, Vage, et al.
Publicado: (2026)

The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm
por: Chen, Jiale, et al.
Publicado: (2025)

Behemoth: Benchmarking Unlearning in LLMs Using Fully Synthetic Data
por: Iofinova, Eugenia, et al.
Publicado: (2026)

Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations
por: Li, Shigang, et al.
Publicado: (2019)

Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?
por: Zverev, Egor, et al.
Publicado: (2024)

Panza: Design and Analysis of a Fully-Local Personalized Text Writing Assistant
por: Nicolicioiu, Armand, et al.
Publicado: (2024)

Breaking (Global) Barriers in Parallel Stochastic Optimization with Wait-Avoiding Group Averaging
por: Li, Shigang, et al.
Publicado: (2020)

Model Compression with Exact Budget Constraints via Riemannian Manifolds
por: Helcig, Michael, et al.
Publicado: (2026)

Towards Robust Scaling Laws for Optimizers
por: Volkova, Alexandra, et al.
Publicado: (2026)

EntryPrune: Neural Network Feature Selection using First Impressions
por: Zimmer, Felix, et al.
Publicado: (2024)

MatGPTQ: Accurate and Efficient Post-Training Matryoshka Quantization
por: Kleinegger, Maximilian, et al.
Publicado: (2026)

Statistically-Lossless Quantization of Large Language Models
por: Helcig, Michael, et al.
Publicado: (2026)

Powerset Convolutional Neural Networks
por: Wendler, Chris, et al.
Publicado: (2019)

Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence
por: Ansaripour, Matin, et al.
Publicado: (2022)

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics
por: Robert, Thomas, et al.
Publicado: (2024)

Simple Opinion Dynamics for No-Regret Learning
por: Lazarsfeld, John, et al.
Publicado: (2023)

Computational Bottlenecks of Training Small-scale Large Language Models
por: Ashkboos, Saleh, et al.
Publicado: (2024)

Scaling Laws of Global Weather Models
por: Yu, Yuejiang, et al.
Publicado: (2026)

Near-Optimal Sparse Allreduce for Distributed Deep Learning
por: Li, Shigang, et al.
Publicado: (2022)

Chimera: Efficiently Training Large-Scale Neural Networks with Bidirectional Pipelines
por: Li, Shigang, et al.
Publicado: (2021)

Apertus LLM Family Expansion via Distillation and Quantization
por: Panferov, Andrei, et al.
Publicado: (2026)

EvoPress: Accurate Dynamic Model Compression via Evolutionary Search
por: Sieberling, Oliver, et al.
Publicado: (2024)

Communication-Efficient Federated Learning With Data and Client Heterogeneity
por: Zakerinia, Hossein, et al.
Publicado: (2022)

HOT: Hadamard-based Optimized Training
por: Kim, Seonggon, et al.
Publicado: (2025)