English
Related papers

Related papers: Polynomial Context-Truncation Sensitivity in Autor…

200 papers

Policy gradient (PG) gives rise to a rich class of reinforcement learning (RL) methods. Recently, there has been an emerging trend to accelerate the existing PG methods such as REINFORCE by the \emph{variance reduction} techniques. However,…

Machine Learning · Computer Science 2021-05-31 Junyu Zhang , Chengzhuo Ni , Zheng Yu , Csaba Szepesvari , Mengdi Wang

Visual Autoregressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction approach, which yields substantial improvements in efficiency, scalability, and zero-shot generalization. Nevertheless, the…

Machine Learning · Computer Science 2025-05-27 Kunjun Li , Zigeng Chen , Cheng-Yen Yang , Jenq-Neng Hwang

We study sequential coding of Markov sources under an error propagation constraint. An encoder sequentially compresses a sequence of vector-sources that are spatially i.i.d. but temporally correlated according to a first-order Markov…

Information Theory · Computer Science 2012-02-24 Farrokh Etezadi , Ashish Khisti , Mitchell Trott

The Key-Value (KV) cache is central to the efficiency of transformer-based large language models (LLMs), storing previously computed vectors to accelerate inference. Yet, as sequence length and batch size grow, the cache becomes a major…

Machine Learning · Computer Science 2025-12-08 Damien Lesens , Beheshteh T. Rakhshan , Guillaume Rabusseau

Variable-length Markov chains on finite quivers provide a natural framework for context-dependent stochastic growth under incidence constraints. I study quiver-valued variable-length Markov chains observed through finite boundary windows…

Probability · Mathematics 2026-04-14 Oleg Kiriukhin

In recent years, learned image compression (LIC) technologies have surpassed conventional methods notably in terms of rate-distortion (RD) performance. Most present learned techniques are VAE-based with an autoregressive entropy model,…

Image and Video Processing · Electrical Eng. & Systems 2024-10-08 Minghao Han , Shiyin Jiang , Shengxi Li , Xin Deng , Mai Xu , Ce Zhu , Shuhang Gu

We consider lossy compression of an information source when the decoder has lossless access to a correlated one. This setup, also known as the Wyner-Ziv problem, is a special case of distributed source coding. To this day, practical…

Information Theory · Computer Science 2024-05-22 Ezgi Ozyilkan , Johannes Ballé , Elza Erkip

The KV cache used in large language models has linearly growing time complexity, so LLMs face memory blow-up and reduced decoding efficiency when they process long contexts. Current KV Cache eviction has become an important research…

Artificial Intelligence · Computer Science 2026-05-26 Wei Luo , Yi Huang , Songchen Ma , Huanyu Qu , Jiang Cai , Mingkun Xu

With the growing demand for long-context LLMs across a wide range of applications, the key-value (KV) cache has become a critical bottleneck for both latency and memory usage. Recently, KV-cache offloading has emerged as a promising…

Machine Learning · Computer Science 2026-05-18 Andrey Bocharnikov , Ivan Ermakov , Denis Kuznedelev , Vyacheslav Zhdanovskiy , Yegor Yershov

Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the trained network to platforms with memory and processing…

Machine Learning · Computer Science 2019-10-15 Andréa B. Duque , Luã Lázaro J. Santos , David Macêdo , Cleber Zanchettin

We study a controlled partial-KV decoding setting in which exact unnormalized softmax contributions are computed for sink/tail anchors and a retrieved token set, while the remaining prefill tokens are represented by a residual estimate. We…

Machine Learning · Computer Science 2026-05-08 Yasuto Hoshi , Daisuke Miyashita , Jun Deguchi

Decoding strategies largely determine the quality of Large Language Model (LLM) outputs, yet widely used heuristics such as greedy or fixed temperature/top-p decoding are static and often task-agnostic, leading to suboptimal or inconsistent…

Computation and Language · Computer Science 2026-03-20 Asmita Bhardwaj , Yuya Jeremy Ong , Eelaaf Zahid , Basel Shbita

In this paper, a novel learning-based Wyner-Ziv coding framework is considered under a distributed image transmission scenario, where the correlated source is only available at the receiver. Unlike other learnable frameworks, our approach…

Information Theory · Computer Science 2025-02-06 Yuxuan Shi , Shuo Shao , Yongpeng Wu , Wenjun Zhang , Merouane Debbah

The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…

Machine Learning · Computer Science 2025-07-25 Manlai Liang , JiaMing Zhang , Xiong Li , Jinlong Li

In this paper, we study whether an off-the-shelf LLM can be adapted into a discrete, variable-length token compressor and decompressor for long-context processing. To this end, we design a self-expressive autoencoding framework that…

Computation and Language · Computer Science 2026-05-14 Wenbing Li , Yiran Wang , Zikai Song , Jielei Zhang , Tianhao Zhao , Junkai Lin , Wei Yang

A likelihood encoder is studied in the context of lossy source compression. The analysis of the likelihood encoder is based on the soft-covering lemma. It is demonstrated that the use of a likelihood encoder together with the soft-covering…

Information Theory · Computer Science 2016-04-07 Eva C. Song , Paul Cuff , H. Vincent Poor

Transformer attention scales quadratically with sequence length O(n^2), limiting long-context use. We propose Adaptive Retention, a probabilistic, layer-wise token selection mechanism that learns which representations to keep under a strict…

Computation and Language · Computer Science 2025-10-13 S M Rafiuddin , Muntaha Nujat Khan

We study the computational complexity of approximating general constrained Markov decision processes. Our primary contribution is the design of a polynomial time $(0,\epsilon)$-additive bicriteria approximation algorithm for finding optimal…

Data Structures and Algorithms · Computer Science 2025-02-12 Jeremy McMahan

Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank tokens by one importance signal -- attention, recency, layer-wise allocation, or key…

Computation and Language · Computer Science 2026-05-27 Hong Chen , Xiang Liu , Yubo Gao , Yuxuan Fan , Bo Wang , Yuanlin Chu , Yuanguo Lin , Xuming Hu

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

Computation and Language · Computer Science 2024-10-31 Suyu Ge , Yunan Zhang , Liyuan Liu , Minjia Zhang , Jiawei Han , Jianfeng Gao