Imagen de Portada

Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Harel, Itamar, Wolanowsky, Yonathan, Vardi, Gal, Srebro, Nathan, Soudry, Daniel
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

Provable Tempered Overfitting of Minimal Nets and Typical Nets
por: Harel, Itamar, et al.
Publicado: (2024)

How Uniform Random Weights Induce Non-uniform Bias: Typical Interpolating Neural Networks Generalize with Narrow Teachers
por: Buzaglo, Gon, et al.
Publicado: (2024)

Noisy Interpolation Learning with Shallow Univariate ReLU Networks
por: Joshi, Nirmit, et al.
Publicado: (2023)

Overfitting Behaviour of Gaussian Kernel Ridgeless Regression: Varying Bandwidth or Dimensionality
por: Medvedev, Marko, et al.
Publicado: (2024)

On the Hardness of Learning Regular Expressions
por: Attias, Idan, et al.
Publicado: (2025)

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
por: Zhou, Lijia, et al.
Publicado: (2023)

Learning to Think from Multiple Thinkers
por: Joshi, Nirmit, et al.
Publicado: (2026)

Positive Distribution Shift as a Framework for Understanding Tractable Learning
por: Medvedev, Marko, et al.
Publicado: (2026)

The Implicit Bias of Gradient Descent on Separable Data
por: Soudry, Daniel, et al.
Publicado: (2017)

Trained Transformer Classifiers Generalize and Exhibit Benign Overfitting In-Context
por: Frei, Spencer, et al.
Publicado: (2024)

A Theory of Learning with Autoregressive Chain of Thought
por: Joshi, Nirmit, et al.
Publicado: (2025)

From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
por: Evron, Itay, et al.
Publicado: (2025)

Transformers are almost optimal metalearners for linear classification
por: Magen, Roey, et al.
Publicado: (2025)

The Implicit Bias of Adam and Muon on Smooth Homogeneous Neural Networks
por: Gronich, Eitan, et al.
Publicado: (2026)

Quantifying Overfitting along the Regularization Path for Two-Part-Code MDL in Supervised Classification
por: Zhu, Xiaohan, et al.
Publicado: (2025)

Cross-Entropy Is All You Need To Invert the Data Generating Process
por: Reizinger, Patrik, et al.
Publicado: (2024)

Overfitting and Generalizing with (PAC) Bayesian Prediction in Noisy Binary Classification
por: Zhu, Xiaohan, et al.
Publicado: (2026)

Research Program: Theory of Learning in Dynamical Systems
por: Hazan, Elad, et al.
Publicado: (2025)

Accuracy is Not All You Need
por: Dutta, Abhinav, et al.
Publicado: (2024)

The Price of Implicit Bias in Adversarially Robust Generalization
por: Tsilivis, Nikolaos, et al.
Publicado: (2024)

Implicit Regularization Towards Rank Minimization in ReLU Networks
por: Timor, Nadav, et al.
Publicado: (2022)

To Grok Grokking: Provable Grokking in Ridge Regression
por: Xu, Mingyue, et al.
Publicado: (2026)

Realizable Learning is All You Need
por: Hopkins, Max, et al.
Publicado: (2021)

Attention is All You Need Until You Need Retention
por: Yaslioglu, M. Murat
Publicado: (2025)

Standard Gaussian Process is All You Need for High-Dimensional Bayesian Optimization
por: Xu, Zhitong, et al.
Publicado: (2024)

Data is All You Need: Markov Chain Car-Following (MC-CF) Model
por: Chung, Sungyong, et al.
Publicado: (2026)

Context is All You Need
por: Delanois, Jean Erik, et al.
Publicado: (2026)

Attention Is All You Need But You Don't Need All Of It For Inference of Large Language Models
por: Tyukin, Georgy, et al.
Publicado: (2024)

Provable Privacy Attacks on Trained Shallow Neural Networks
por: Smorodinsky, Guy, et al.
Publicado: (2024)

FP4 All the Way: Fully Quantized Training of LLMs
por: Chmiel, Brian, et al.
Publicado: (2025)

PLUMAGE: Probabilistic Low rank Unbiased Min Variance Gradient Estimator for Efficient Large Model Training
por: Haroush, Matan, et al.
Publicado: (2025)

Recursive Models for Long-Horizon Reasoning
por: Yang, Chenxiao, et al.
Publicado: (2026)

Some Attention is All You Need for Retrieval
por: Michalak, Felix, et al.
Publicado: (2025)

Half Search Space is All You Need
por: Rumiantsev, Pavel, et al.
Publicado: (2025)

Top-$nσ$: Not All Logits Are You Need
por: Tang, Chenxia, et al.
Publicado: (2024)

Isoperimetry is All We Need: Langevin Posterior Sampling for RL with Sublinear Regret
por: Jorge, Emilio, et al.
Publicado: (2024)

Workspace Optimization: How to Train Your Agent
por: Sarafian, Elad, et al.
Publicado: (2026)

Exploitation Is All You Need... for Exploration
por: Rentschler, Micah, et al.
Publicado: (2025)

Multistep Inverse Is Not All You Need
por: Levine, Alexander, et al.
Publicado: (2024)

On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
por: Joshi, Nirmit, et al.
Publicado: (2024)