Imagen de Portada

When does Metropolized Hamiltonian Monte Carlo provably outperform Metropolis-adjusted Langevin algorithm?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Yuansi, Gatmiry, Khashayar, Jiang, Minhui
Formato:	Preprint
Publicado:	2023
Materias:	Computation Computational Complexity Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Regularized Dikin Walks for Sampling Truncated Logconcave Measures, Mixed Isoperimetry and Beyond Worst-Case Analysis
por: Jiang, Minhui, et al.
Publicado: (2024)

Entanglement-induced provable and robust quantum learning advantages
por: Zhao, Haimeng, et al.
Publicado: (2024)

What does guidance do? A fine-grained analysis in a simple setting
por: Chidambaram, Muthu, et al.
Publicado: (2024)

Diffusion Language Models are Provably Optimal Parallel Samplers
por: Jiang, Haozhe, et al.
Publicado: (2025)

Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm
por: Srinivasan, Vishwak, et al.
Publicado: (2023)

Simple algorithms to test and learn local Hamiltonians
por: Gutiérrez, Francisco Escudero
Publicado: (2024)

Polyhedral Instability Governs Regret in Online Learning
por: Li, Yuetai, et al.
Publicado: (2026)

High-accuracy sampling from constrained spaces with the Metropolis-adjusted Preconditioned Langevin Algorithm
por: Srinivasan, Vishwak, et al.
Publicado: (2024)

Data Debugging is NP-hard for Classifiers Trained with SGD
por: Guo, Zizheng, et al.
Publicado: (2024)

When Can We Solve the Weighted Low Rank Approximation Problem in Truly Subquadratic Time?
por: Li, Chenyang, et al.
Publicado: (2025)

Computing Optimal Regularizers for Online Linear Optimization
por: Gatmiry, Khashayar, et al.
Publicado: (2024)

Adversarial Online Learning with Temporal Feedback Graphs
por: Gatmiry, Khashayar, et al.
Publicado: (2024)

Rate-optimal community detection near the KS threshold via node-robust algorithms
por: Ding, Jingqiu, et al.
Publicado: (2025)

Proximity to Losslessly Compressible Parameters
por: Farrugia-Roberts, Matthew
Publicado: (2023)

From Pseudorandomness to Multi-Group Fairness and Back
por: Dwork, Cynthia, et al.
Publicado: (2023)

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

Learnability of Parameter-Bounded Bayes Nets
por: Bhattacharyya, Arnab, et al.
Publicado: (2024)

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
por: Merrill, William, et al.
Publicado: (2025)

How Hard Is Continuous Clustering? Lower Bounds from the Existential Theory of the Reals
por: Majumdar, Angshul
Publicado: (2026)

Spiky Rank and Its Applications to Rigidity and Circuits
por: Hambardzumyan, Lianna, et al.
Publicado: (2026)

Rethinking the Role of Positional Encoding: Sliding-Window Transformers without PE Remain Turing Complete
por: Li, Qian, et al.
Publicado: (2026)

Low-Rank Matrix Approximation for Neural Network Compression
por: Cherukuri, Kalyan, et al.
Publicado: (2025)

Decision Tree Learning on Product Spaces
por: Moakahr, Arshia Soltani, et al.
Publicado: (2026)

Lower Bounds for Chain-of-Thought Reasoning in Hard-Attention Transformers
por: Amiri, Alireza, et al.
Publicado: (2025)

Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances
por: Wang, Jie, et al.
Publicado: (2024)

Fundamental Limits of Crystalline Equivariant Graph Neural Networks: A Circuit Complexity Perspective
por: Cao, Yang, et al.
Publicado: (2025)

A Logic for Expressing Log-Precision Transformers
por: Merrill, William, et al.
Publicado: (2022)

Smoothed Analysis for Learning Concepts with Low Intrinsic Dimension
por: Chandrasekaran, Gautam, et al.
Publicado: (2024)

Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation
por: Jacobs, Peter Matthew, et al.
Publicado: (2026)

Distribution-Specific Agnostic Conditional Classification With Halfspaces
por: Huang, Jizhou, et al.
Publicado: (2025)

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
por: Li, Zhiyuan, et al.
Publicado: (2024)

Ask, and it shall be given: On the Turing completeness of prompting
por: Qiu, Ruizhong, et al.
Publicado: (2024)

Necessary and Sufficient Oracles: Toward a Computational Taxonomy For Reinforcement Learning
por: Rohatgi, Dhruv, et al.
Publicado: (2025)

How Global Calibration Strengthens Multiaccuracy
por: Casacuberta, Sílvia, et al.
Publicado: (2025)

On the Computational Hardness of Transformers
por: Saha, Barna, et al.
Publicado: (2026)

Additive Models Explained: A Computational Complexity Approach
por: Bassan, Shahaf, et al.
Publicado: (2025)

Certifiable Boolean Reasoning Is Universal
por: Li, Wenhao, et al.
Publicado: (2026)

Large Language Models on Small Resource-Constrained Systems: Performance Characterization, Analysis and Trade-offs
por: Seymour, Liam, et al.
Publicado: (2024)

Constant Bit-size Transformers Are Turing Complete
por: Li, Qian, et al.
Publicado: (2025)

New Hardness Results for Low-Rank Matrix Completion
por: Chawin, Dror, et al.
Publicado: (2025)