English
Related papers

Related papers: NF4 Isn't Information Theoretically Optimal (and t…

200 papers

In this work we analyze the mean-square performance of different strategies for distributed estimation over least-mean-squares (LMS) adaptive networks. The results highlight some useful properties for distributed adaptation in comparison to…

Information Theory · Computer Science 2015-06-05 Xiaochuan Zhao , Ali H. Sayed

The inference of Large language models (LLMs) requires immense computation and memory resources. To curtail these costs, quantisation has merged as a promising solution, but existing LLM quantisation mainly focuses on 8-bit. In this work,…

Machine Learning · Computer Science 2024-03-15 Cheng Zhang , Jianyi Cheng , Ilia Shumailov , George A. Constantinides , Yiren Zhao

Quantizing LLM weights and activations is a standard approach for efficient deployment, but a few extreme outliers can stretch the dynamic range and amplify low-bit quantization errors. Prior transform-based mitigations (e.g., Hadamard…

Machine Learning · Computer Science 2026-02-03 Jiale Chen , Vage Egiazarian , Roberto L. Castro , Torsten Hoefler , Dan Alistarh

Complex networks are mapped to a model of boxes and balls where the balls are distinguishable. It is shown that the scale-free size distribution of boxes maximizes the information associated with the boxes provided configurations including…

Statistical Mechanics · Physics 2007-12-17 Petter Minnhagen , Sebastian Bernhardsson

The problem of lossless data compression with side information available to both the encoder and the decoder is considered. The finite-blocklength fundamental limits of the best achievable performance are defined, in two different versions…

Information Theory · Computer Science 2021-02-23 Lampros Gavalakis , Ioannis Kontoyiannis

This paper is concerned with nonparametric estimation of the weighted stochastic block model. We first show that the model implies a set of multilinear restrictions on the joint distribution of edge weights of certain subgraphs involving…

Statistics Theory · Mathematics 2022-03-10 Koen Jochmans

We demonstrate, for the first time, fully quantized training (FQT) of large language models (LLMs) using predominantly 4-bit floating-point (FP4) precision for weights, activations, and gradients on datasets up to 200 billion tokens. We…

Machine Learning · Computer Science 2025-08-12 Brian Chmiel , Maxim Fishman , Ron Banner , Daniel Soudry

This technical report explains how optimal size-aware dispatching policies can be determined numerically using value iteration. It also contains some numerical examples that shed light to the nature of the optimal policies itself. The…

Optimization and Control · Mathematics 2024-02-14 Esa Hyytiä , Rhonda Righter

Motivated by economic dispatch and linearly-constrained resource allocation problems, this paper proposes a novel Distributed Approx-Newton algorithm that approximates the standard Newton optimization method. A main property of this…

Numerical Analysis · Computer Science 2017-03-24 Tor Anderson , Chin-Yao Chang , Sonia Martinez

The growing computational demands of training large language models (LLMs) necessitate more efficient methods. Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce these costs. While FP8…

Machine Learning · Computer Science 2026-05-18 Ruizhe Wang , Yeyun Gong , Xiao Liu , Guoshuai Zhao , Ziyue Yang , Baining Guo , Zhengjun Zha , Peng Cheng

We consider the design of distributed scheduling algorithms that minimize age of information in single-hop wireless networks. The centralized max-weight policy is known to be nearly optimal in this setting; hence, our goal is to design a…

Networking and Internet Architecture · Computer Science 2023-07-13 Vishrant Tripathi , Nicholas Jones , Eytan Modiano

In this work we consider data-driven optimization problems where one must maximize a function given only queries at a fixed set of points. This problem setting emerges in many domains where function evaluation is a complex and expensive…

Machine Learning · Computer Science 2021-02-17 Justin Fu , Sergey Levine

We investigate the upper and lower bounds on the quantization distortions for independent and identically distributed sources in the finite block-length regime. Based on the convex optimization framework of the rate-distortion theory, we…

Information Theory · Computer Science 2013-06-21 Chen Gong , Xiaodong Wang

Block maxima methods constitute a fundamental part of the statistical toolbox in extreme value analysis. However, most of the corresponding theory is derived under the simplifying assumption that block maxima are independent observations…

Statistics Theory · Mathematics 2019-07-24 Nan Zou , Stanislav Volgushev , Axel Bücher

The amounts of data that need to be transmitted, processed, and stored by the modern deep neural networks have reached truly enormous volumes in the last few years calling for the invention of new paradigms both in hardware and software…

Machine Learning · Computer Science 2022-11-08 Ilya Soloveychik , Ilya Lyubomirsky , Xin Wang , Sudeep Bhoja

In this paper we consider the estimation problem for high quantiles of a heavy-tailed distribution from block data when only a few largest values are observed within blocks. We propose estimators for high quantiles and prove that these…

Statistics Theory · Mathematics 2023-06-27 Yongcheng Qi , Mengzi Xie , Jingping Yang

For large language models (LLMs), post-training quantization (PTQ) can significantly reduce memory footprint and computational overhead. Model quantization is rapidly evolving. Though many papers report breakthrough results, they are often…

Machine Learning · Computer Science 2026-01-30 Yutong Liu , Cairong Zhao , Guosheng Hu

Distributed functional scalar quantization (DFSQ) theory provides optimality conditions and predicts performance of data acquisition systems in which a computation on acquired data is desired. We address two limitations of previous works:…

Information Theory · Computer Science 2015-03-24 John Z. Sun , Vinith Misra , Vivek K Goyal

Weight-sharing quantization has emerged as a technique to reduce energy expenditure during inference in large neural networks by constraining their weights to a limited set of values. However, existing methods for weight-sharing…

Machine Learning · Computer Science 2023-10-05 Christopher Subia-Waud , Srinandan Dasmahapatra

Efficient deployment of large language models (LLMs) necessitates low-bit quantization to minimize model size and inference cost. While low-bit integer formats (e.g., INT8/INT4) have been the conventional choice, emerging low-bit…

Machine Learning · Computer Science 2023-05-23 Yijia Zhang , Lingran Zhao , Shijie Cao , Wenqiang Wang , Ting Cao , Fan Yang , Mao Yang , Shanghang Zhang , Ningyi Xu