Imagen de Portada

Stress-Aware Learning under KL Drift via Trust-Decayed Mirror Descent

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Raj, Gabriel Nixon
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Statistics Theory
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A connection between Tempering and Entropic Mirror Descent
por: Chopin, Nicolas, et al.
Publicado: (2023)

A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
por: Alfano, Carlo, et al.
Publicado: (2023)

Interactive Learning of Single-Index Models via Stochastic Gradient Descent
por: Rajaraman, Nived, et al.
Publicado: (2026)

KL Convergence Guarantees for Score diffusion models under minimal data assumptions
por: Conforti, Giovanni, et al.
Publicado: (2023)

Double Descent and Overfitting under Noisy Inputs and Distribution Shift for Linear Denoisers
por: Kausik, Chinmaya, et al.
Publicado: (2023)

Generalization Error Curves for Analytic Spectral Algorithms under Power-law Decay
por: Li, Yicheng, et al.
Publicado: (2024)

Transfer Learning for Classification under Decision Rule Drift with Application to Optimal Individualized Treatment Rule Estimation
por: Wang, Xiaohan, et al.
Publicado: (2025)

Wasserstein KL-divergence for Gaussian distributions
por: Datar, Adwait, et al.
Publicado: (2025)

Dropout Drops Double Descent
por: Yang, Tian-Le, et al.
Publicado: (2023)

An Asymptotic Law of the Iterated Logarithm for $\mathrm{KL}_{\inf}$
por: Ram, Ashwin, et al.
Publicado: (2026)

MoMA: Model-based Mirror Ascent for Offline Reinforcement Learning
por: Hong, Mao, et al.
Publicado: (2024)

A Sharp KL-Convergence Analysis for Diffusion Models under Minimal Assumptions
por: Jain, Nishant, et al.
Publicado: (2025)

kTULA: A Langevin sampling algorithm with improved KL bounds under super-linear log-gradients
por: Lytras, Iosif, et al.
Publicado: (2025)

Variational Approach for Efficient KL Divergence Estimation in Dirichlet Mixture Models
por: Pal, Samyajoy, et al.
Publicado: (2024)

Double Robust Semi-Supervised Inference for the Mean: Selection Bias under MAR Labeling with Decaying Overlap
por: Zhang, Yuqian, et al.
Publicado: (2021)

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

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

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

Conformal Prediction Under Generalized Covariate Shift with Posterior Drift
por: Wang, Baozhen, et al.
Publicado: (2025)

Identifying Drift, Diffusion, and Causal Structure from Temporal Snapshots
por: Guan, Vincent, et al.
Publicado: (2024)

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
por: Zhao, Qingyue, et al.
Publicado: (2026)

Convergence of the Inexact Langevin Algorithm in KL Divergence with Application to Score-based Generative Models
por: Yang, Kaylee Yingxi, et al.
Publicado: (2022)

Training Diagonal Linear Networks with Stochastic Sharpness-Aware Minimization
por: Clara, Gabriel, et al.
Publicado: (2025)

Learning from Samples: Inverse Problems over measures via Sharpened Fenchel-Young Losses
por: Andrade, Francisco, et al.
Publicado: (2025)

Least Squares Regression Can Exhibit Under-Parameterized Double Descent
por: Li, Xinyue, et al.
Publicado: (2023)

Gradient Descent with Projection Finds Over-Parameterized Neural Networks for Learning Low-Degree Polynomials with Nearly Minimax Optimal Rate
por: Yang, Yingzhen, et al.
Publicado: (2026)

Implicit Regularization for Tubal Tensor Factorizations via Gradient Descent
por: Karnik, Santhosh, et al.
Publicado: (2024)

Plug-In Classification of Drift Functions in Diffusion Processes Using Neural Networks
por: Zhao, Yuzhen, et al.
Publicado: (2026)

Learning Operators with Stochastic Gradient Descent in General Hilbert Spaces
por: Shi, Lei, et al.
Publicado: (2024)

Neural Drift Estimation for Ergodic Diffusions: Non-parametric Analysis and Numerical Exploration
por: Di Gregorio, Simone, et al.
Publicado: (2025)

Double Descent: Understanding Linear Model Estimation of Nonidentifiable Parameters and a Model for Overfitting
por: Christensen, Ronald
Publicado: (2024)

Learning Operators by Regularized Stochastic Gradient Descent with Operator-valued Kernels
por: Yang, Jia-Qi, et al.
Publicado: (2025)

Learning under Latent Group Sparsity via Diffusion on Networks
por: Ghosh, Subhroshekhar, et al.
Publicado: (2025)

Stopping Rules for Stochastic Gradient Descent via Anytime-Valid Confidence Sequences
por: Aolaritei, Liviu, et al.
Publicado: (2025)

Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
por: Lovig, Max
Publicado: (2026)

Benign Overfitting without Linearity: Neural Network Classifiers Trained by Gradient Descent for Noisy Linear Data
por: Frei, Spencer, et al.
Publicado: (2022)

Tail-Sensitive KL and Rényi Convergence of Unadjusted Hamiltonian Monte Carlo via One-Shot Couplings
por: Bou-Rabee, Nawaf, et al.
Publicado: (2026)

Robust Predictive Uncertainty and Double Descent in Contaminated Bayesian Random Features
por: Caprio, Michele, et al.
Publicado: (2026)

Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent
por: Banerjee, Sayan, et al.
Publicado: (2024)

Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean-Field Games
por: Ocello, Antonio, et al.
Publicado: (2025)