Imagen de Portada

Linear Gradient Prediction with Control Variates

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ciosek, Kamil, Felicioni, Nicolò, Litwin, Juan Elenter
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Fast Adversarial Attacks with Gradient Prediction
por: Ciosek, Kamil, et al.
Publicado: (2026)

Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy
por: Ciosek, Kamil, et al.
Publicado: (2025)

A Bayesian Information-Theoretic Approach to Data Attribution
por: Tailor, Dharmesh, et al.
Publicado: (2026)

The Minimax Rate of Second-Order Calibration
por: Ciosek, Kamil, et al.
Publicado: (2026)

On the Importance of Uncertainty in Decision-Making with Large Language Models
por: Felicioni, Nicolò, et al.
Publicado: (2024)

Measuring Uncertainty Calibration
por: Ciosek, Kamil, et al.
Publicado: (2025)

Epistemic Uncertainty and Observation Noise with the Neural Tangent Kernel
por: Calvo-Ordoñez, Sergio, et al.
Publicado: (2024)

Automated Off-Policy Estimator Selection via Supervised Learning
por: Felicioni, Nicolò, et al.
Publicado: (2024)

Gradient-Variation Regret Bounds for Unconstrained Online Learning
por: Zhao, Yuheng, et al.
Publicado: (2026)

Impatient Bandits: Optimizing for the Long-Term Without Delay
por: Zhang, Kelly W., et al.
Publicado: (2025)

When Embedding Models Meet: Procrustes Bounds and Applications
por: Maystre, Lucas, et al.
Publicado: (2025)

The Neural Tangent Kernel for Classification
por: Plenk, Jonathan, et al.
Publicado: (2026)

LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning
por: Peng, Liangzu, et al.
Publicado: (2024)

Near-Optimal Solutions of Constrained Learning Problems
por: Elenter, Juan, et al.
Publicado: (2024)

A Gaussian Process View on Observation Noise and Initialization in Wide Neural Networks
por: Calvo-Ordoñez, Sergio, et al.
Publicado: (2025)

Richer Bayesian Last Layers with Subsampled NTK Features
por: Calvo-Ordoñez, Sergio, et al.
Publicado: (2026)

Primal Dual Continual Learning: Balancing Stability and Plasticity through Adaptive Memory Allocation
por: Elenter, Juan, et al.
Publicado: (2023)

Pathwise Gradient Variance Reduction with Control Variates in Variational Inference
por: Ng, Kenyon, et al.
Publicado: (2024)

Overcoming Brittleness in Pareto-Optimal Learning-Augmented Algorithms
por: Angelopoulos, Spyros, et al.
Publicado: (2024)

Non-Coherent Over-the-Air Decentralized Gradient Descent
por: Michelusi, Nicolo'
Publicado: (2022)

Conformal Load Prediction with Transductive Graph Autoencoders
por: Luo, Rui, et al.
Publicado: (2024)

Online Linear Regression with Paid Stochastic Features
por: Merlis, Nadav, et al.
Publicado: (2025)

Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
por: Jin, Tianyuan, et al.
Publicado: (2024)

Linear Preference Optimization: Decoupled Gradient Control via Absolute Regularization
por: Wang, Rui, et al.
Publicado: (2025)

Zero-Variance Gradients for Variational Autoencoders
por: Shao, Zilei, et al.
Publicado: (2025)

Feasible Learning
por: Ramirez, Juan, et al.
Publicado: (2025)

A Perturbation Approach to Unconstrained Linear Bandits
por: Jacobsen, Andrew, et al.
Publicado: (2026)

Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring
por: Di Gennaro, Federico, et al.
Publicado: (2025)

Wasserstein Gradient Flow over Variational Parameter Space for Variational Inference
por: Nguyen, Dai Hai, et al.
Publicado: (2023)

Parametric PDE Control with Deep Reinforcement Learning and Differentiable L0-Sparse Polynomial Policies
por: Botteghi, Nicolò, et al.
Publicado: (2024)

Parameter-Free Dynamic Regret for Unconstrained Linear Bandits
por: Rumi, Alberto, et al.
Publicado: (2026)

Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning
por: Bozkurt, Alper Kamil, et al.
Publicado: (2019)

Accelerated Learning with Linear Temporal Logic using Differentiable Simulation
por: Bozkurt, Alper Kamil, et al.
Publicado: (2025)

Understanding Stochastic Natural Gradient Variational Inference
por: Wu, Kaiwen, et al.
Publicado: (2024)

A Multi-Fidelity Control Variate Approach for Policy Gradient Estimation
por: Liu, Xinjie, et al.
Publicado: (2025)

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
por: Kuroki, Yuko, et al.
Publicado: (2023)

Adaptive Kernel Selection for Stein Variational Gradient Descent
por: Melcher, Moritz, et al.
Publicado: (2025)

Variational Stochastic Gradient Descent for Deep Neural Networks
por: Chen, Haotian, et al.
Publicado: (2024)

Gradient-Based Non-Linear Inverse Learning
por: Abhishake, et al.
Publicado: (2024)

Linear Discriminant Analysis with Gradient Optimization
por: Shen, Cencheng, et al.
Publicado: (2025)