English
Related papers

Related papers: Rate-Distortion Optimization for Transformer Infer…

200 papers

Transformers have achieved remarkable success in sequence modeling and beyond but suffer from quadratic computational and memory complexities with respect to the length of the input sequence. Leveraging techniques include sparse and linear…

Machine Learning · Computer Science 2022-08-02 Tan Nguyen , Richard G. Baraniuk , Robert M. Kirby , Stanley J. Osher , Bao Wang

In this paper, we study the computation of the rate-distortion-perception function (RDPF) for discrete memoryless sources subject to a single-letter average distortion constraint and a perception constraint that belongs to the family of…

Information Theory · Computer Science 2023-05-09 Giuseppe Serra , Photios A. Stavrou , Marios Kountouris

By extracting task-relevant information while maximally compressing the input, the information bottleneck (IB) principle has provided a guideline for learning effective and robust representations of the target inference. However, extending…

Information Theory · Computer Science 2025-01-22 Yuhan Wang , Youlong Wu , Shuai Ma , Ying-Jun Angela Zhang

Optical networks are vulnerable to physical layer attacks; wiretappers can improperly receive messages intended for legitimate recipients. Our work considers an aspect of this security problem within the domain of multimode fiber (MMF)…

Cryptography and Security · Computer Science 2016-11-17 Eva C. Song , Emina Soljanin , Paul Cuff , H. Vincent Poor , Kyle Guan

In successive refinement of information, the decoder refines its representation of the source progressively as it receives more encoded bits. The rate-distortion region of successive refinement describes the minimum rates required to attain…

Information Theory · Computer Science 2018-11-22 Victoria Kostina , Ertem Tuncel

Transformer-based language models have become the standard approach to solving natural language processing tasks. However, industry adoption usually requires the maximum throughput to comply with certain latency constraints that prevents…

Computation and Language · Computer Science 2022-12-08 Haihao Shen , Ofir Zafrir , Bo Dong , Hengyu Meng , Xinyu Ye , Zhe Wang , Yi Ding , Hanwen Chang , Guy Boudoukh , Moshe Wasserblat

This paper describes a memory-efficient transformer model designed to drive a reduction in memory usage and execution time by substantial orders of magnitude without impairing the model's performance near that of the original model.…

Machine Learning · Computer Science 2025-01-03 Krisvarish V , Priyadarshini T , K P Abhishek Sri Saai , Vaidehi Vijayakumar

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

Understanding how information propagates through Transformer models is a key challenge for interpretability. In this work, we study the effects of minimal token perturbations on the embedding space. In our experiments, we analyze the…

Machine Learning · Computer Science 2025-06-24 Eddie Conti , Alejandro Astruc , Alvaro Parafita , Axel Brando

Many common types of data can be represented as functions that map coordinates to signal values, such as pixel locations to RGB values in the case of an image. Based on this view, data can be compressed by overfitting a compact neural…

Machine Learning · Computer Science 2023-10-31 Zongyu Guo , Gergely Flamich , Jiajun He , Zhibo Chen , José Miguel Hernández-Lobato

Despite recent advances in architectures for mobile devices, deep learning computational requirements remains prohibitive for most embedded devices. To address that issue, we envision sharing the computational costs of inference between…

Machine Learning · Computer Science 2019-11-26 Juliano S. Assine , Alan Godoy , Eduardo Valle

Transformers allow attention between all pairs of tokens, but there is reason to believe that most of these connections - and their quadratic time and memory - may not be necessary. But which ones? We evaluate the impact of sparsification…

Computation and Language · Computer Science 2022-10-11 Siddhartha Brahma , Polina Zablotskaia , David Mimno

Since Shannon's foundational work, rate-distortion theory has defined the fundamental limits of lossy compression. Classical results, derived for memoryless and stationary ergodic sources in the asymptotic regime, have shaped both transform…

Information Theory · Computer Science 2026-03-11 Sujata Sinha , Vishwas Rao , Robert Underwood , David Lenz , Sheng Di , Franck Cappello , Lingjia Liu

Large Transformer models routinely achieve state-of-the-art results on a number of tasks but training these models can be prohibitively costly, especially on long sequences. We introduce two techniques to improve the efficiency of…

Machine Learning · Computer Science 2020-02-19 Nikita Kitaev , Łukasz Kaiser , Anselm Levskaya

This paper presents a novel algorithm that aims at minimizing the required decoding energy by exploiting a general energy model for HEVC-decoder solutions. We incorporate the energy model into the HEVC encoder such that it is capable of…

Image and Video Processing · Electrical Eng. & Systems 2022-03-04 Christian Herglotz , André Kaup

Dithering is a technique that can improve human perception of low-resolution data by reducing quantization artifacts. In this work we formalize and analytically justify two metrics for quantization artifact prominence, using them to design…

Signal Processing · Electrical Eng. & Systems 2024-02-27 Morriel Kasher , Michael Tinston , Predrag Spasojevic

The ubiquitous Variable-Byte encoding is one of the fastest compressed representation for integer sequences. However, its compression ratio is usually not competitive with other more sophisticated encoders, especially when the integers to…

Information Retrieval · Computer Science 2022-02-08 Giulio Ermanno Pibiri , Rossano Venturini

This paper considers lossy source coding of $n$-dimensional memoryless sources and shows an explicit approximation to the minimum source coding rate required to sustain the probability of exceeding distortion $d$ no greater than $\epsilon$,…

Information Theory · Computer Science 2017-02-28 Victoria Kostina

Consider a pair of correlated Gaussian sources (X1,X2). Two separate encoders observe the two components and communicate compressed versions of their observations to a common decoder. The decoder is interested in reconstructing a linear…

Information Theory · Computer Science 2007-07-25 D. Krithivasan , S. S. Pradhan

General-purpose pretrained sentence encoders such as BERT are not ideal for real-world conversational AI applications; they are computationally heavy, slow, and expensive to train. We propose ConveRT (Conversational Representations from…

Computation and Language · Computer Science 2020-04-30 Matthew Henderson , Iñigo Casanueva , Nikola Mrkšić , Pei-Hao Su , Tsung-Hsien Wen , Ivan Vulić
‹ Prev 1 8 9 10 Next ›