Imagen de Portada

Closed-Form Last Layer Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Galashov, Alexandre, Da Costa, Nathaël, Xu, Liyuan, Hennig, Philipp, Gretton, Arthur
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

Rethinking Approximate Gaussian Inference in Classification
por: Mucsányi, Bálint, et al.
Publicado: (2025)

Deep MMD Gradient Flow without adversarial training
por: Galashov, Alexandre, et al.
Publicado: (2024)

Geometric Gaussian Approximations of Probability Distributions
por: Da Costa, Nathaël, et al.
Publicado: (2025)

Accelerated Diffusion Models via Speculative Sampling
por: De Bortoli, Valentin, et al.
Publicado: (2025)

Kernel Single Proxy Control for Deterministic Confounding
por: Xu, Liyuan, et al.
Publicado: (2023)

Sample Path Regularity of Gaussian Processes from the Covariance Kernel
por: Da Costa, Nathaël, et al.
Publicado: (2023)

Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation
por: Xu, Liyuan, et al.
Publicado: (2021)

Doubly Robust Proxy Causal Learning with Neural Mean Embeddings
por: Bozkurt, Bariscan, et al.
Publicado: (2026)

Sequential Kernel Embedding for Mediated and Time-Varying Dose Response Curves
por: Singh, Rahul, et al.
Publicado: (2021)

Learn to Guide Your Diffusion Model
por: Galashov, Alexandre, et al.
Publicado: (2025)

On the Wasserstein Gradient Flow Interpretation of Drifting Models
por: Gretton, Arthur, et al.
Publicado: (2026)

Distributional Diffusion Models with Scoring Rules
por: De Bortoli, Valentin, et al.
Publicado: (2025)

Density Ratio-Free Doubly Robust Proxy Causal Learning
por: Bozkurt, Bariscan, et al.
Publicado: (2025)

Density Ratio-based Proxy Causal Learning Without Density Ratios
por: Bozkurt, Bariscan, et al.
Publicado: (2025)

Constructive Disintegration and Conditional Modes
por: Da Costa, Nathaël, et al.
Publicado: (2025)

Perturbative methods for non-parametric instrumental variable
por: Bu, Wei, et al.
Publicado: (2026)

Semiparametric Efficient Test for Interpretable Distributional Treatment Effects
por: Zenati, Houssam, et al.
Publicado: (2026)

Towards a Unified Analysis of Neural Networks in Nonparametric Instrumental Variable Regression: Optimization and Generalization
por: Chen, Zonghao, et al.
Publicado: (2025)

Geometric Learning with Positively Decomposable Kernels
por: Da Costa, Nathael, et al.
Publicado: (2023)

Doubly-Robust Estimation of Counterfactual Policy Mean Embeddings
por: Zenati, Houssam, et al.
Publicado: (2025)

Regularized $f$-Divergence Kernel Tests
por: Ribero, Mónica, et al.
Publicado: (2026)

Differential geometry with extreme eigenvalues in the positive semidefinite cone
por: Mostajeran, Cyrus, et al.
Publicado: (2023)

Muon is Not That Special: Random or Inverted Spectra Work Just as Well
por: Shumaylov, Zakhar, et al.
Publicado: (2026)

Kernel Treatment Effects with Adaptively Collected Data
por: Zenati, Houssam, et al.
Publicado: (2025)

Interventional Processes for Causal Uncertainty Quantification
por: Dance, Hugh, et al.
Publicado: (2024)

Near-Optimality of Contrastive Divergence Algorithms
por: Glaser, Pierre, et al.
Publicado: (2025)

Geometric statistics with subspace structure preservation for SPD matrices
por: Mostajeran, Cyrus, et al.
Publicado: (2024)

Bayesian Optimization via Continual Variational Last Layer Training
por: Brunzema, Paul, et al.
Publicado: (2024)

Fast and Scalable Score-Based Kernel Calibration Tests
por: Glaser, Pierre, et al.
Publicado: (2025)

Nonparametric Instrumental Regression via Kernel Methods is Minimax Optimal
por: Meunier, Dimitri, et al.
Publicado: (2024)

Semiparametrically Efficient Inference for Kernel Measures of Noise Heterogeneity
por: Wornbard, Jakub, et al.
Publicado: (2026)

Towards Optimal Sobolev Norm Rates for the Vector-Valued Regularized Least-Squares Algorithm
por: Li, Zhu, et al.
Publicado: (2023)

Controlling Moments with Kernel Stein Discrepancies
por: Kanagawa, Heishiro, et al.
Publicado: (2022)

Sobolev Regularized MMD Gradient Flow
por: Tian, Chenyang, et al.
Publicado: (2026)

Nonlinear Meta-Learning Can Guarantee Faster Rates
por: Meunier, Dimitri, et al.
Publicado: (2023)

Foundations of Multivariate Distributional Reinforcement Learning
por: Wiltzer, Harley, et al.
Publicado: (2024)

Scalable Bayesian Inference for Nonlinear Conservation Laws
por: Weiland, Tim, et al.
Publicado: (2026)

Is the Last Layer Sufficient for Uncertainty Quantification?
por: Wilson, Joseph, et al.
Publicado: (2026)

Conditional Bayesian Quadrature
por: Chen, Zonghao, et al.
Publicado: (2024)

Composite Goodness-of-fit Tests with Kernels
por: Key, Oscar, et al.
Publicado: (2021)