Imagen de Portada

Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kaushik, Chiraag, Romberg, Justin, Muthukumar, Vidya
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A general technique for approximating high-dimensional empirical kernel matrices
por: Kaushik, Chiraag, et al.
Publicado: (2025)

The good, the bad and the ugly sides of data augmentation: An implicit spectral regularization perspective
por: Lin, Chi-Heng, et al.
Publicado: (2022)

New Equivalences Between Interpolation and SVMs: Kernels and Structured Features
por: Kaushik, Chiraag, et al.
Publicado: (2023)

Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance
por: Kaushik, Chiraag, et al.
Publicado: (2024)

A least-square method for non-asymptotic identification in linear switching control
por: Sun, Haoyuan, et al.
Publicado: (2024)

Decomposing multimodal embedding spaces with group-sparse autoencoders
por: Kaushik, Chiraag, et al.
Publicado: (2026)

Sharp analysis of out-of-distribution error for "importance-weighted" estimators in the overparameterized regime
por: Lai, Kuo-Wei, et al.
Publicado: (2024)

General Loss Functions Lead to (Approximate) Interpolation in High Dimensions
por: Lai, Kuo-Wei, et al.
Publicado: (2023)

Pointwise confidence estimation in the non-linear $\ell^2$-regularized least squares
por: Kuzborskij, Ilja, et al.
Publicado: (2025)

Improved and Oracle-Efficient Online $\ell_1$-Multicalibration
por: Ghuge, Rohan, et al.
Publicado: (2025)

Task Shift: From Classification to Regression in Overparameterized Linear Models
por: LaBonte, Tyler, et al.
Publicado: (2025)

Just Wing It: Near-Optimal Estimation of Missing Mass in a Markovian Sequence
por: Pananjady, Ashwin, et al.
Publicado: (2024)

Estimating stationary mass, frequency by frequency
por: Nakul, Milind, et al.
Publicado: (2025)

Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning
por: Zeng, Sihan, et al.
Publicado: (2024)

Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes
por: Zeng, Sihan, et al.
Publicado: (2021)

A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning
por: Zeng, Sihan, et al.
Publicado: (2021)

Anderson acceleration for iteratively reweighted $\ell_1$ algorithm
por: Li, Kexin
Publicado: (2024)

A constrained iteratively-reweighted least-squares framework for generalised linear models
por: Masselot, Pierre, et al.
Publicado: (2025)

Optimal sampling for least-squares approximation
por: Adcock, Ben
Publicado: (2024)

Leave-one-out least squares Monte Carlo algorithm for pricing Bermudan options
por: Woo, Jeechul, et al.
Publicado: (2018)

A general formulation of reweighted least squares fitting
por: Giannelli, Carlotta, et al.
Publicado: (2024)

Improved state mixing in higher-order and block diagonal linear recurrent networks
por: Dubinin, Igor, et al.
Publicado: (2026)

On the Unreasonable Effectiveness of Last-layer Retraining
por: Hill, John C., et al.
Publicado: (2025)

Faster Margin Maximization Rates for Generic and Adversarially Robust Optimization Methods
por: Wang, Guanghui, et al.
Publicado: (2023)

Pre-trained Tabular Foundation Models as Versatile Summary Networks for Neural Posterior Estimation
por: Pickens, Elliot, et al.
Publicado: (2026)

How Does the ReLU Activation Affect the Implicit Bias of Gradient Descent on High-dimensional Neural Network Regression?
por: Lai, Kuo-Wei, et al.
Publicado: (2026)

Non-asymptotic analysis of the performance of the penalized least trimmed squares in sparse models
por: Zuo, Yijun
Publicado: (2025)

Accelerating Multi-Task Temporal Difference Learning under Low-Rank Representation
por: Bai, Yitao, et al.
Publicado: (2025)

Double descent for least-squares interpolation on contaminated data: A simulation study
por: Werner, Tino
Publicado: (2026)

Finite-Time Analysis of Projected Two-Time-Scale Stochastic Approximation
por: Bai, Yitao, et al.
Publicado: (2026)

The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
por: LaBonte, Tyler, et al.
Publicado: (2024)

Hybrid least squares for learning functions from highly noisy data
por: Adcock, Ben, et al.
Publicado: (2025)

Compare different SG-Schemes based on large least square problems
por: Acharya, Ramkrishna
Publicado: (2025)

Structured and sparse partial least squares coherence for multivariate cortico-muscular analysis
por: Sun, Jingyao, et al.
Publicado: (2025)

Last-iterate Convergence for Symmetric, General-sum, $2 \times 2$ Games Under The Exponential Weights Dynamic
por: Wang, Guanghui, et al.
Publicado: (2025)

Concentration inequalities for semidefinite least squares based on data
por: Fabiani, Filippo, et al.
Publicado: (2025)

Flexi-Fuzz least squares SVM for Alzheimer's diagnosis: Tackling noise, outliers, and class imbalance
por: Akhtar, Mushir, et al.
Publicado: (2024)

ResQPASS: an algorithm for bounded variable linear least squares with asymptotic Krylov convergence
por: Symoens, Bas, et al.
Publicado: (2023)

Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning
por: Philippenko, Constantin, et al.
Publicado: (2023)

Closed-form $\ell_r$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $\ell_p$ bias
por: Zhang, Shuofeng, et al.
Publicado: (2025)