← Back to all news
arXiv Machine Learning By Wenbin Wan

LoRA-RC: Reservoir Computing with Low-Rank Adaptation

Read the original on arXiv Machine Learning →

LoRA-RC introduces a low‑rank adaptation scheme for reservoir computing that updates the recurrent matrix using streaming prediction errors while keeping the base reservoir and adaptation bases fixed offline. The method projects a small core matrix onto a spectral‑norm ball and applies low‑pass filtering at each step, ensuring every recurrent matrix stays within a certified contraction set. Experiments on a Lorenz system with abrupt parameter drift show that LoRA‑RC reduces post‑drift prediction error by 56% compared to a fixed RC and 51% compared to readout‑only adaptation, and that removing the projection increases error by more than a factor of 40.

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.

Related stories

arXiv AI
Sep 10

Adaptive Nonlinear Vector Autoregression: Robust Forecasting for Noisy Chaotic Time Series

The paper introduces a data‑adaptive nonlinear vector autoregression (NVAR) model that replaces fixed polynomial or random feature maps with a shallow, trainable multilayer perceptron (MLP). By jointly training the MLP and a linear readout via gradient‑based optimization, the model learns data‑driven nonlinearities while maintaining a simple readout structure, improving scalability in high‑dimensional settings. Experiments on several chaotic systems, both noise‑free and synthetically noisy, show that this adaptive NVAR outperforms standard NVAR, a leaky echo state network (ESN), and a hybrid ESN in predictive accuracy, demonstrating robust forecasting under noisy conditions.

By Sherkhon Azimov, Susana Lopez-Moreno, Eric Dolores-Cuenca, Sieun Lee, Jae-Il Kwon, Sangil Kim
More like this →
Hugging Face Trending Papers
Sep 2

LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates

Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that treats every LoRA step as a tangent vector of the fixed-rank matrix manifold and takes the spectral-norm steepest-descent step of Muon inside that tangent space, mapping the result back to the factors through a retraction native to the LoRA parametrization.

llmsfine-tuningbenchmarks
More like this →
arXiv Machine Learning
Aug 6

Echo Flow Networks

arXiv:2509. 24122v3 Announce Type: replace Abstract: At the heart of time-series forecasting (TSF) lies a fundamental challenge: how can models efficiently and effectively capture long-range temporal dependencies across ever-growing sequences?

By Hongbo Liu, Jia Xu
benchmarks
More like this →
arXiv Machine Learning
Jun 11

PCA-Enhanced Adaptive NVAR Framework for High-Resolution Sea Surface Temperature Forecasting in the East Sea

arXiv:2606. 12141v1 Announce Type: new Abstract: Accurate forecasting of sea surface temperature (SST) in regional seas such as the East Sea is crucial for monitoring marine ecosystems, assessing climate risks, managing fisheries, and conducting naval operations.

By Sherkhon Azimov, Susana L\'opez-Moreno, Eric Dolores-Cuenca, JinYong Choi, Sangil Kim
More like this →