paper-with-me

Papers

Learning Fast-Mixing Models for Structured Prediction

2015-02-24 · Jacob Steinhardt, Percy Liang

Markov Chain Monte Carlo (MCMC) algorithms are often used for approximate inference inside learning, but their slow mixing can be difficult to diagnose and the approximations can seriously degrade learning. To alleviate these issues, we define a new model family using strong Doeblin Markov chains, whose mixing times can be precisely controlled by a parameter. We also develop an algorithm to learn such models, which involves maximizing the data likelihood under the induced stationary distribution of these chains. We show empirical improvements on two challenging inference tasks.

📄 PDF Abstract BibTeX arXiv:1502.06668

Code (1)

https://worksheets.codalab.org/worksheets/0xc6edf0c9bec643ac9e74418bd6ad4136 공식 구현

Tasks

PredictionStructured Prediction

Similar Papers 제목 키워드 기반

Iterative Thresholding for Demixing Structured Superpositions in High Dimensions

2017-01-23 · Mohammadreza Soltani, Chinmay Hegde

We consider the demixing problem of two (or more) high-dimensional vectors from nonlinear observations when the number of such observations is far less than the ambient dimension of the underlying vectors. Specifically, …

Vocal Bursts Intensity Prediction

A deep learning modeling framework to capture mixing patterns in reactive-transport systems

2021-01-11 · N. V. Jagtap, M. K. Mudunuru, K. B. Nakshatrala

Prediction and control of chemical mixing are vital for many scientific areas such as subsurface reactive transport, climate modeling, combustion, epidemiology, and pharmacology. Due to the complex nature of mixing in he…

EpidemiologyFuture prediction

Maximum Likelihood Learning With Arbitrary Treewidth via Fast-Mixing Parameter Sets

2015-09-30 · NeurIPS 2015 12 · Justin Domke

Inference is typically intractable in high-treewidth undirected graphical models, making maximum likelihood learning a challenge. One way to overcome this is to restrict parameters to a tractable set, most typically the …

A Geometry-Aware Triplane Field Network for Vehicle Aerodynamic Prediction

2026-06-05 · Kangkang Qi, Huiyu Yang, Keqi Ding, Yunpeng Wang 외 arxiv

High-fidelity computational fluid dynamics (CFD) is crucial to vehicle aerodynamic analysis, but its cost still constrains early-stage design exploration. Machine-learning-based surface-field prediction offers a faster a…

Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training

2018-06-01 · Maohua Zhu, Jason Clemons, Jeff Pool, Minsoo Rhu 외

Exploiting sparsity enables hardware systems to run neural networks faster and more energy-efficiently. However, most prior sparsity-centric optimization techniques only accelerate the forward pass of neural networks and…