arXiv Machine Learning August 26, 2026 By Erin Carson, Xinye Chen, Fei He, Cheng Kang

QABBA: Error-Guaranteed Symbolic Time-Series Compression via Integer-Quantized Aggregation

Read the original on arXiv Machine Learning →

QABBA is a quantized variant of the Adaptive Brownian Bridge-based Aggregation (ABBA) method that compresses long numerical time‑series into short symbolic sequences using integer‑quantized symbolic centers. It reduces parameter storage and enables integer arithmetic while providing rigorous error bounds—including a dimension‑free segment error, a time‑domain reconstruction error, a stability condition for symbolic assignment, and a bit‑allocation rule. The resulting symbolic strings can be fed directly into pretrained large language models, and experiments on several benchmark archives show a practical trade‑off among storage, reconstruction accuracy, and downstream predictive performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Sep 2

QABBA: Symbolic Time-Series Compression via Integer-Quantized Aggregation

arXiv:2411.15209v4 Announce Type: replace Abstract: The expansion of time-series data from sensors and monitoring systems has made compact representations increasingly important. Such representations...

By Erin Carson, Xinye Chen, Fei He, Cheng Kang

llms rag efficiency

arXiv AI

Jul 7

QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting

arXiv:2607. 02632v1 Announce Type: cross Abstract: Time-series forecasting supports decisions in finance, en-ergy, transportation, public health, and industrial monitoring.

By Shah Nawaz Haider, Steve Austin, Arnab Barua, Sarowar Morshed Shawon, Hadaate Ullah

llms rag safety

arXiv Machine Learning

Aug 31

DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization

The paper introduces DAMP, a decay‑aware mixed‑precision quantization scheme for recurrent‑state representations in GDN and KDA language models. By identifying high‑risk channels through quantization‑error energy and decay persistence, DAMP stores these channels at higher precision while compressing the rest to INT8, achieving a 9.9‑bit average precision. Experiments on Qwen3.6‑35B and Kimi‑Linear‑48B show a 69.1% reduction in recurrent‑state storage, up to 2.01× faster state‑update kernels, and up to 10.9% lower full‑model TPOT while preserving accuracy close to the FP32 baseline.

By Tao Zhang, Jianchao Tan, Pingwei Sun, Yanqi Yu, Zixu Jiang, Yuchen Xie, Xunliang Cai, Ziqian Zeng

llms efficiency benchmarks

arXiv AI

Aug 6

Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs

arXiv:2608. 04048v1 Announce Type: cross Abstract: Serving large language models (LLMs) under diverse deployment constraints requires flexible trade-offs between accuracy, memory footprint, and throughput.

By Yu Luo, Bo Dong, Wenhua Cheng, Haihao Shen

llms efficiency

arXiv AI

Aug 17

OTIS: Learning High-Quality Time Series Features With Tiny Encoders

arXiv:2410. 07299v3 Announce Type: replace-cross Abstract: We introduce OTIS, an open time series encoder that yields high-quality time series features for downstream deployment on any system, including resource-constrained wearables and industrial sensors.

By \"Ozg\"un Turgut, Philip M\"uller, Martin J. Menten, Daniel Rueckert

benchmarks

arXiv AI

Sep 10

All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs

arXiv:2609.06161v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable progress, yet their massive storage and memory-bandwidth demands still hinder efficient deploym...

By Zhixiong Zhao, Zukang Xu, Guangyu Sun, Lifeng Liu, Dawei Yang

llms efficiency

One email a morning, machine-written

Related stories

QABBA: Symbolic Time-Series Compression via Integer-Quantized Aggregation

QuantFlow: A Federated Mamba-Based Post-Transformer Foundation Model for Time-Series Forecasting

DAMP: Decay-Aware Mixed-Precision Recurrent-State Quantization

Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs

OTIS: Learning High-Quality Time Series Features With Tiny Encoders

All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs