4 papers
Curvature-Guided LoRA: Matching Full Fine-Tuning in Function Space
Frédéric Zheng, Alexandre Proutière
Parameter-efficient fine-tuning methods such as LoRA enable efficient adaptation of large pretrained models, but often lag behind full fine-tuning in both convergence speed and fin…
Near-optimal Rank Adaptive Inference of High Dimensional Matrices
Frédéric Zheng, Yassir Jedra, Alexandre Proutiere
We address the problem of estimating a high-dimensional matrix from linear measurements, with a focus on designing optimal rank-adaptive algorithms. These algorithms infer the matr…
Minimal Order Recovery through Rank-adaptive Identification
Frédéric Zheng, Yassir Jedra, Alexandre Proutière
This paper addresses the problem of identifying linear systems from noisy input-output trajectories. We introduce Thresholded Ho-Kalman, an algorithm that leverages a rank-adaptive…
Conformal Predictions under Markovian Data
Frédéric Zheng, Alexandre Proutiere
We study the split Conformal Prediction method when applied to Markovian data. We quantify the gap in terms of coverage induced by the correlations in the data (compared to exchang…