Cover Image

WaterSIC: information-theoretically (near) optimal linear layer quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lifar, Egor, Savkin, Semyon, Ordentlich, Or, Polyanskiy, Yury
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Information Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

NestQuant: Nested Lattice Quantization for Matrix Products and LLMs
by: Savkin, Semyon, et al.
Published: (2025)

Price of universality in vector quantization is at most 0.11 bit
by: Harbuzova, Alina, et al.
Published: (2026)

High-Rate Quantized Matrix Multiplication II
by: Ordentlich, Or, et al.
Published: (2026)

Optimal Quantization for Matrix Multiplication
by: Ordentlich, Or, et al.
Published: (2024)

The Radio-Frequency Transformer for Signal Separation
by: Lifar, Egor, et al.
Published: (2026)

High-Rate Quantized Matrix Multiplication I
by: Ordentlich, Or, et al.
Published: (2026)

Diffusion Domain Expansion: Learning to Coordinate Pre-trained Diffusion Models
by: Lifar, Egor, et al.
Published: (2026)

On the Minimax Regret of Sequential Probability Assignment via Square-Root Entropy
by: Jia, Zeyu, et al.
Published: (2025)

Statistical Inference with Limited Memory: A Survey
by: Berg, Tomer, et al.
Published: (2023)

Optimal Online Bookmaking for Binary Games
by: Bhatt, Alankrita, et al.
Published: (2025)

Nonparametric MLE for Gaussian Location Mixtures: Certified Computation and Generic Behavior
by: Polyanskiy, Yury, et al.
Published: (2025)

Learning to Bid Optimally and Efficiently in Adversarial First-price Auctions
by: Han, Yanjun, et al.
Published: (2020)

The Voronoi Spherical CDF for Lattices and Linear Codes: New Bounds for Quantization and Coding
by: Ordentlich, Or
Published: (2025)

Testing and estimation in orthosymmetric Gaussian sequence model
by: Jia, Zeyu, et al.
Published: (2025)

LZ Penalty: An information-theoretic repetition penalty for autoregressive language models
by: Ginart, Antonio A., et al.
Published: (2025)

Unsourced Multiple Access: A Coding Paradigm for Massive Random Access
by: Liva, Gianluigi, et al.
Published: (2024)

A Gapped Scale-Sensitive Dimension and Lower Bounds for Offset Rademacher Complexity
by: Jia, Zeyu, et al.
Published: (2025)

The importance of feature preprocessing for differentially private linear optimization
by: Sun, Ziteng, et al.
Published: (2023)

Likelihood-free hypothesis testing
by: Gerber, Patrik Róbert, et al.
Published: (2022)

Is Dimensionality a Barrier for Retrieval Models?
by: Bangachev, Kiril, et al.
Published: (2026)

Information theoretic underpinning of self-supervised learning by clustering
by: Kittler, Josef, et al.
Published: (2026)

Fast Rate Information-theoretic Bounds on Generalization Errors
by: Wu, Xuetong, et al.
Published: (2023)

Information-theoretic signatures of causality in Bayesian networks and hypergraphs
by: Chiang, Sung En, et al.
Published: (2025)

Federated learning over physical channels: adaptive algorithms with near-optimal guarantees
by: Zhang, Rui, et al.
Published: (2025)

Some theoretical improvements on the tightness of PAC-Bayes risk certificates for neural networks
by: García-Pérez, Diego, et al.
Published: (2025)

Partial information decomposition: redundancy as information bottleneck
by: Kolchinsky, Artemy
Published: (2024)

Cyclic Group Projection for Enumerating Quasi-Cyclic Codes Trapping Sets
by: Usatyuk, Vasiliy, et al.
Published: (2024)

High-Rate Nested-Lattice Quantized Matrix Multiplication with Small Lookup Tables
by: Kaplan, Iris, et al.
Published: (2025)

Machine-learning optimized measurements of chaotic dynamical systems via the information bottleneck
by: Murphy, Kieran A., et al.
Published: (2023)

FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information
by: Hwang, Dongseong
Published: (2024)

Thresholds for Reconstruction of Random Hypergraphs From Graph Projections
by: Bresler, Guy, et al.
Published: (2025)

Information-theoretic Bayesian Optimization: Survey and Tutorial
by: Garrido-Merchán, Eduardo C.
Published: (2025)

Information-theoretic reduction of deep neural networks to linear models in the overparametrized proportional regime
by: Camilli, Francesco, et al.
Published: (2025)

Providing Differential Privacy for Federated Learning Over Wireless: A Cross-layer Framework
by: Mao, Jiayu, et al.
Published: (2024)

Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces
by: Tran-The, Hung, et al.
Published: (2020)

Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits
by: Rajaraman, Nived, et al.
Published: (2023)

Near-optimal Rank Adaptive Inference of High Dimensional Matrices
by: Zheng, Frédéric, et al.
Published: (2025)

A unified framework for learning with nonlinear model classes from arbitrary linear samples
by: Adcock, Ben, et al.
Published: (2023)

On optimal solutions of classical and sliced Wasserstein GANs with non-Gaussian data
by: Huang, Yu-Jui, et al.
Published: (2025)

An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding
by: Hu, Dou, et al.
Published: (2025)