Cover Image

Gradient dynamics for low-rank fine-tuning beyond kernels

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Dayi, Arif Kerem, Chen, Sitan
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Statistics Theory
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

High-accuracy and dimension-free sampling with diffusions
by: Gatmiry, Khashayar, et al.
Published: (2026)

Entrywise error bounds for low-rank approximations of kernel matrices
by: Modell, Alexander
Published: (2024)

Efficient Pauli channel estimation with logarithmic quantum memory
by: Chen, Sitan, et al.
Published: (2023)

Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
by: Gupta, Shivam, et al.
Published: (2024)

When few labeled target data suffice: a theory of semi-supervised domain adaptation via fine-tuning from multiple adaptive starts
by: Ha, Wooseok, et al.
Published: (2025)

Sublinear iterations can suffice even for DDPMs
by: Zhang, Matthew S., et al.
Published: (2025)

Average Gradient Outer Product in kernel regression provably recovers the central subspace for multi-index models
by: Zhu, Libin, et al.
Published: (2026)

Physics-informed kernel learning
by: Doumèche, Nathan, et al.
Published: (2024)

The phase diagram of kernel interpolation in large dimensions
by: Zhang, Haobo, et al.
Published: (2024)

On the number of modes of Gaussian kernel density estimators
by: Geshkovski, Borjan, et al.
Published: (2024)

Top-$K$ ranking with a monotone adversary
by: Yang, Yuepeng, et al.
Published: (2024)

Early stopping and polynomial smoothing in regression with reproducing kernels
by: Averyanov, Yaroslav, et al.
Published: (2020)

Scalable and adaptive prediction bands with kernel sum-of-squares
by: Allain, Louis, et al.
Published: (2025)

Statistical and computational challenges in ranking
by: Carpentier, Alexandra, et al.
Published: (2025)

Is RL fine-tuning harder than regression? A PDE learning approach for diffusion models
by: Mou, Wenlong
Published: (2025)

Gradient-flow SDEs have unique transient population dynamics
by: Guan, Vincent, et al.
Published: (2025)

Consistent estimation of generative model representations in the data kernel perspective space
by: Acharyya, Aranyak, et al.
Published: (2024)

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension
by: Haas, Moritz, et al.
Published: (2023)

Eigen-convergence of Gaussian kernelized graph Laplacian by manifold heat interpolation
by: Cheng, Xiuyuan, et al.
Published: (2021)

Effective regions and kernels in continuous sparse regularisation, with application to sketched mixtures
by: De Castro, Yohann, et al.
Published: (2025)

Improved learning theory for kernel distribution regression with two-stage sampling
by: Bachoc, François, et al.
Published: (2023)

Mean Testing under Truncation beyond Gaussian
by: Wang, Yuhao, et al.
Published: (2026)

Optimal Confidence Band for Kernel Gradient Flow Estimator
by: Cheng, Yuqian, et al.
Published: (2026)

Low-rank matrix completion and denoising under Poisson noise
by: McRae, Andrew D., et al.
Published: (2019)

Asymptotically free sketched ridge ensembles: Risks, cross-validation, and tuning
by: Patil, Pratik, et al.
Published: (2023)

Derivatives and residual distribution of regularized M-estimators with application to adaptive tuning
by: Bellec, Pierre C, et al.
Published: (2021)

Vector-valued self-normalized concentration inequalities beyond sub-Gaussianity
by: Martinez-Taboada, Diego, et al.
Published: (2025)

Fast kernel methods: Sobolev, physics-informed, and additive models
by: Doumèche, Nathan, et al.
Published: (2025)

Limit theorems of Chatterjee's rank correlation
by: Lin, Zhexiao, et al.
Published: (2022)

Assumption-free stability for ranking problems
by: Liang, Ruiting, et al.
Published: (2025)

Improved convergence rate of kNN graph Laplacians: differentiable self-tuned affinity
by: Cheng, Xiuyuan, et al.
Published: (2024)

Federated Causal Inference: Multi-Study ATE Estimation beyond Meta-Analysis
by: Khellaf, Rémi, et al.
Published: (2024)

On the Natural Gradient of the Evidence Lower Bound
by: Ay, Nihat, et al.
Published: (2023)

Gradient descent for deep equilibrium single-index models
by: Dandapanthula, Sanjit, et al.
Published: (2025)

GIST: Gibbs self-tuning for locally adaptive Hamiltonian Monte Carlo
by: Bou-Rabee, Nawaf, et al.
Published: (2024)

A Stein Gradient Descent Approach for Doubly Intractable Distributions
by: Lee, Heesang, et al.
Published: (2024)

Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent
by: Patil, Pratik, et al.
Published: (2024)

Finite-Particle Rates for Regularized Stein Variational Gradient Descent
by: He, Ye, et al.
Published: (2026)

Computational and statistical lower bounds for low-rank estimation under general inhomogeneous noise
by: De, Debsurya, et al.
Published: (2025)

Gradient-enhanced global sensitivity analysis with Poincar{é} chaos expansions
by: Roustant, O, et al.
Published: (2025)