paper-with-me

홈 › Papers

UnHiPPO: Uncertainty-aware Initialization for State Space Models

2025-06-05 · Marten Lienen, Abdullah Saydemir, Stephan Günnemann

State space models are emerging as a dominant model class for sequence problems with many relying on the HiPPO framework to initialize their dynamics. However, HiPPO fundamentally assumes data to be noise-free; an assumption often violated in practice. We extend the HiPPO theory with measurement noise and derive an uncertainty-aware initialization for state space model dynamics. In our analysis, we interpret HiPPO as a linear stochastic control problem where the data enters as a noise-free control signal. We then reformulate the problem so that the data become noisy outputs of a latent system and arrive at an alternative dynamics initialization that infers the posterior of this latent system from the data without increasing runtime. Our experiments show that our initialization improves the resistance of state-space models to noise both at training and inference time. Find our implementation at https://cs.cit.tum.de/daml/unhippo.

📄 PDF Abstract BibTeX arXiv:2506.05065

Code (0)

등록된 구현이 없습니다.

Tasks

State Space Models

Similar Papers 제목 키워드 기반

Convolution Aware Initialization

2017-02-21 · Armen Aghajanyan

Initialization of parameters in deep neural networks has been shown to have a big impact on the performance of the networks (Mishkin & Matas, 2015). The initialization scheme devised by He et al, allowed convolution acti…

Meta-Learned Adaptive Optimization for Robust Human Mesh Recovery with Uncertainty-Aware Parameter Updates

2026-03-27 · Shaurjya Mandal, Nutan Sharma, John Galeotti arxiv

Human mesh recovery from single images remains challenging due to inherent depth ambiguity and limited generalization across domains. While recent methods combine regression and optimization approaches, they struggle wit…

Human Mesh RecoveryDomain Adaptation

Learning in the Fisher Subspace: A Guided Initialization for LoRA Fine-Tuning

2026-05-01 · Zhi-Quan Feng, Ying-Jia Lin, Hung-Yu Kao arxiv

LoRA adapts large language models (LLMs) by restricting updates to low-rank subspaces of pre-trained weights. While this substantially reduces training cost, the effectiveness of adaptation critically depends on which su…

Adaptive Overclocking: Dynamic Control of Thinking Path Length via Real-Time Reasoning Signals

2025-09-21 · Shuhao Jiang, Songbo Wang, Yang Qiao, Chun Xu 외 arxiv

Large Reasoning Models (LRMs) often suffer from computational inefficiency due to overthinking, where a fixed reasoning budget fails to match the varying complexity of tasks. To address this issue, we propose Adaptive Ov…

LoRA-DA: Data-Aware Initialization for Low-Rank Adaptation via Asymptotic Analysis

2025-10-28 · Qingyue Zhang, Chang Chu, Tianren Peng, Qi Li 외 arxiv

LoRA has become a widely adopted method for PEFT, and its initialization methods have attracted increasing attention. However, existing methods have notable limitations: many methods do not incorporate target-domain data…