Image de couverture de livre

Optimal Quantization for Matrix Multiplication

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Ordentlich, Or, Polyanskiy, Yury
Format:	Preprint
Publié:	2024
Sujets:	Information Theory Artificial Intelligence Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

High-Rate Quantized Matrix Multiplication II
par: Ordentlich, Or, et autres
Publié: (2026)

High-Rate Quantized Matrix Multiplication I
par: Ordentlich, Or, et autres
Publié: (2026)

NestQuant: Nested Lattice Quantization for Matrix Products and LLMs
par: Savkin, Semyon, et autres
Publié: (2025)

Price of universality in vector quantization is at most 0.11 bit
par: Harbuzova, Alina, et autres
Publié: (2026)

WaterSIC: information-theoretically (near) optimal linear layer quantization
par: Lifar, Egor, et autres
Publié: (2026)

SQuat: Subspace-orthogonal KV Cache Quantization
par: Wang, Hao, et autres
Publié: (2025)

Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models
par: Wei, Lai, et autres
Publié: (2024)

Compression Represents Intelligence Linearly
par: Huang, Yuzhen, et autres
Publié: (2024)

A Survey on Large Language Models from Concept to Implementation
par: Wang, Chen, et autres
Publié: (2024)

The Information of Large Language Model Geometry
par: Tan, Zhiquan, et autres
Publié: (2024)

Geometric Signatures of Compositionality Across a Language Model's Lifetime
par: Lee, Jin Hwa, et autres
Publié: (2024)

A Training-free Method for LLM Text Attribution
par: Radvand, Tara, et autres
Publié: (2025)

Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gain
par: Liu, Wei, et autres
Publié: (2026)

Know Your Limits: Entropy Estimation Modeling for Compression and Generalization
par: Badger, Benjamin L., et autres
Publié: (2025)

Analyzing and Improving Chain-of-Thought Monitorability Through Information Theory
par: Anwar, Usman, et autres
Publié: (2026)

Language Modeling Is Compression
par: Delétang, Grégoire, et autres
Publié: (2023)

Memorization-Compression Cycles Improve Generalization
par: Yu, Fangyuan
Publié: (2025)

Measuring Uncertainty in Transformer Circuits with Effective Information Consistency
par: Krasnovsky, Anatoly A.
Publié: (2025)

SPEX: Scaling Feature Interaction Explanations for LLMs
par: Kang, Justin Singh, et autres
Publié: (2025)

A Communication-Theoretic Framework for LLM Agents: Cost-Aware Adaptive Reliability
par: Omidvar, Hamed, et autres
Publié: (2026)

The Stepwise Informativeness Assumption: Why are Entropy Dynamics and Reasoning Correlated in LLMs?
par: Català, Mar Gonzàlez I, et autres
Publié: (2026)

Learning is Forgetting: LLM Training As Lossy Compression
par: Conklin, Henry C., et autres
Publié: (2026)

Subjective Depth and Timescale Transformers: Learning Where and When to Compute
par: Wieser, Frederico, et autres
Publié: (2025)

The Detection-Extraction Gap: Models Know the Answer Before They Can Say It
par: Wang, Hanyang, et autres
Publié: (2026)

An Information Theoretic Perspective on Agentic System Design
par: He, Shizhe, et autres
Publié: (2025)

Optimal Online Bookmaking for Binary Games
par: Bhatt, Alankrita, et autres
Publié: (2025)

PrismQuant: Rate-Distortion-Optimal Vector Quantization for Gaussian-Mixture Sources
par: Park, Bumsu, et autres
Publié: (2026)

Hallucination is a Consequence of Space-Optimality: A Rate-Distortion Theorem for Membership Testing
par: Guo, Anxin, et autres
Publié: (2026)

High-Rate Nested-Lattice Quantized Matrix Multiplication with Small Lookup Tables
par: Kaplan, Iris, et autres
Publié: (2025)

How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?
par: Garg, Nikhil, et autres
Publié: (2026)

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory
par: Zuo, Fei, et autres
Publié: (2026)

Semantic Faithfulness and Entropy Production Measures to Tame Your LLM Demons and Manage Hallucinations
par: Halperin, Igor
Publié: (2025)

Optimal Scalar Quantization for Matrix Multiplication: Closed-Form Density and Phase Transition
par: Ang, Calvin, et autres
Publié: (2026)

Learning to Bid Optimally and Efficiently in Adversarial First-price Auctions
par: Han, Yanjun, et autres
Publié: (2020)

OD-Stega: LLM-Based Relatively Secure Steganography via Optimized Distributions
par: Huang, Yu-Shin, et autres
Publié: (2024)

MOTIF: Modular Thinking via Reinforcement Fine-tuning in LLMs
par: Mitra, Purbesh, et autres
Publié: (2025)

Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning
par: Mitra, Purbesh, et autres
Publié: (2025)

The Shape of Learning: Anisotropy and Intrinsic Dimensions in Transformer-Based Models
par: Razzhigaev, Anton, et autres
Publié: (2023)

Retrieval-Augmented Generation as Noisy In-Context Learning: A Unified Theory and Risk Bounds
par: Guo, Yang, et autres
Publié: (2025)

Forgetting-MarI: LLM Unlearning via Marginal Information Regularization
par: Xu, Shizhou, et autres
Publié: (2025)