Cover Image

Beyond Outliers: A Study of Optimizers Under Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Vlassis, Georgios, Ashkboos, Saleh, Volkova, Alexandra, Hoefler, Torsten, Alistarh, Dan
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs
by: Ashkboos, Saleh, et al.
Published: (2025)

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

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

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

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

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

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

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

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

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

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

Mitigating the Impact of Outlier Channels for Language Model Quantization with Activation Regularization
by: Nrusimha, Aniruddha, et al.
Published: (2024)

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

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

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

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

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

Unified Scaling Laws for Compressed Representations
by: Panferov, Andrei, et al.
Published: (2025)

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

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

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

Compression Scaling Laws:Unifying Sparsity and Quantization
by: Frantar, Elias, et al.
Published: (2025)

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

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem
by: Malinovskii, Vladimir, et al.
Published: (2024)

"Give Me BF16 or Give Me Death"? Accuracy-Performance Trade-Offs in LLM Quantization
by: Kurtic, Eldar, et al.
Published: (2024)

Extreme Compression of Large Language Models via Additive Quantization
by: Egiazarian, Vage, et al.
Published: (2024)

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

Layer-wise Quantization for Quantized Optimistic Dual Averaging
by: Nguyen, Anh Duc, et al.
Published: (2025)

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

Powerset Convolutional Neural Networks
by: Wendler, Chris, et al.
Published: (2019)

Confounder Detection via Treatment Intent: A New Observational Study Design
by: Plecko, Drago, et al.
Published: (2026)

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

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

Cache Me If You Must: Adaptive Key-Value Quantization for Large Language Models
by: Shutova, Alina, et al.
Published: (2025)

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

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

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

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

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

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