DeciMamba: Exploring the Length Extrapolation Potential of Mamba
- URL: http://arxiv.org/abs/2406.14528v1
- Date: Thu, 20 Jun 2024 17:40:18 GMT
- Title: DeciMamba: Exploring the Length Extrapolation Potential of Mamba
- Authors: Assaf Ben-Kish, Itamar Zimerman, Shady Abu-Hussein, Nadav Cohen, Amir Globerson, Lior Wolf, Raja Giryes,
- Abstract summary: We introduce DeciMamba, a context-extension method specifically designed for Mamba.
We show that DeciMamba can extrapolate context lengths 25x longer than the ones seen during training, and does so without utilizing additional computational resources.
- Score: 89.07242846058023
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length. A promising alternative is Mamba, which demonstrates high performance and achieves Transformer-level capabilities while requiring substantially fewer computational resources. In this paper we explore the length-generalization capabilities of Mamba, which we find to be relatively limited. Through a series of visualizations and analyses we identify that the limitations arise from a restricted effective receptive field, dictated by the sequence length used during training. To address this constraint, we introduce DeciMamba, a context-extension method specifically designed for Mamba. This mechanism, built on top of a hidden filtering mechanism embedded within the S6 layer, enables the trained model to extrapolate well even without additional training. Empirical experiments over real-world long-range NLP tasks show that DeciMamba can extrapolate to context lengths that are 25x times longer than the ones seen during training, and does so without utilizing additional computational resources. We will release our code and models.
Related papers
- An Empirical Study of Mamba-based Language Models [69.74383762508805]
Selective state-space models (SSMs) like Mamba overcome some shortcomings of Transformers.
We present a direct comparison between 8B-context Mamba, Mamba-2, and Transformer models trained on the same datasets.
We find that the 8B Mamba-2-Hybrid exceeds the 8B Transformer on all 12 standard tasks.
arXiv Detail & Related papers (2024-06-12T05:25:15Z) - MambaTS: Improved Selective State Space Models for Long-term Time Series Forecasting [12.08746904573603]
Mamba, based on selective state space models (SSMs), has emerged as a competitive alternative to Transformer.
We propose four targeted improvements, leading to MambaTS.
Experiments conducted on eight public datasets demonstrate that MambaTS achieves new state-of-the-art performance.
arXiv Detail & Related papers (2024-05-26T05:50:17Z) - Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting [5.166854384000439]
Long-term time series forecasting (LTSF) provides longer insights into future trends and patterns.
Recently, a new state space model (SSM) named Mamba is proposed.
With the selective capability on input data and the hardware-aware parallel computing algorithm, Mamba has shown great potential in balancing predicting performance and computational efficiency.
arXiv Detail & Related papers (2024-04-24T09:45:48Z) - Integrating Mamba and Transformer for Long-Short Range Time Series Forecasting [14.476978391383405]
Time series forecasting is an important problem and plays a key role in a variety of applications including weather forecasting, stock market, and scientific simulations.
Recent progress on state space models (SSMs) have shown impressive performance on modeling long range dependency.
We propose to leverage a hybrid framework Mambaformer that internally combines Mamba for long-range dependency, and Transformer for short range dependency.
arXiv Detail & Related papers (2024-04-23T05:43:44Z) - Is Mamba Effective for Time Series Forecasting? [30.85990093479062]
We propose a Mamba-based model named Simple-Mamba (S-Mamba) for time series forecasting.
Specifically, we tokenize the time points of each variate autonomously via a linear layer.
Experiments on thirteen public datasets prove that S-Mamba maintains low computational overhead and achieves leading performance.
arXiv Detail & Related papers (2024-03-17T08:50:44Z) - MiM-ISTD: Mamba-in-Mamba for Efficient Infrared Small Target Detection [72.46396769642787]
We develop a nested structure, Mamba-in-Mamba (MiM-ISTD), for efficient infrared small target detection.
MiM-ISTD is $8 times$ faster than the SOTA method and reduces GPU memory usage by 62.2$%$ when testing on $2048 times 2048$ images.
arXiv Detail & Related papers (2024-03-04T15:57:29Z) - PointMamba: A Simple State Space Model for Point Cloud Analysis [65.59944745840866]
We propose PointMamba, transferring the success of Mamba, a recent representative state space model (SSM), from NLP to point cloud analysis tasks.
Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs.
arXiv Detail & Related papers (2024-02-16T14:56:13Z) - Is Mamba Capable of In-Context Learning? [63.682741783013306]
State of the art foundation models such as GPT-4 perform surprisingly well at in-context learning (ICL)
This work provides empirical evidence that Mamba, a newly proposed state space model, has similar ICL capabilities.
arXiv Detail & Related papers (2024-02-05T16:39:12Z) - CLEX: Continuous Length Extrapolation for Large Language Models [68.43814043853347]
We propose Continuous Length EXtrapolation (CLEX) for Large Language Models (LLMs)
CLEX extends the context window to over 4x or almost 8x training length, with no deterioration in performance.
Our model trained on a 4k length exhibits competitive performance against state-of-the-art open-source models trained on context lengths up to 32k.
arXiv Detail & Related papers (2023-10-25T08:13:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.