中文
相关论文

相关论文: Train and Test Tightness of LP Relaxations in Stru…

200 篇论文

Conformal prediction has recently emerged as a promising strategy for quantifying the uncertainty of a predictive model; these algorithms modify the model to output sets of labels that are guaranteed to contain the true label with high…

机器学习 · 计算机科学 2025-03-11 Botong Zhang , Shuo Li , Osbert Bastani

Learning structured models using maximum margin techniques has become an indispensable tool for com- puter vision researchers, as many computer vision applications can be cast naturally as an image labeling problem. Pixel-based or…

机器学习 · 计算机科学 2013-09-17 Andreas Christian Mueller , Sven Behnke

Besides training, mathematical optimization is also used in deep learning to model and solve formulations over trained neural networks for purposes such as verification, compression, and optimization with learned constraints. However,…

最优化与控制 · 数学 2024-01-30 Jiatai Tong , Junyang Cai , Thiago Serra

Structured prediction energy networks (SPENs; Belanger & McCallum 2016) use neural network architectures to define energy functions that can capture arbitrary dependencies among parts of structured outputs. Prior work used gradient descent…

计算与语言 · 计算机科学 2018-03-12 Lifu Tu , Kevin Gimpel

In structured output prediction tasks, labeling ground-truth training output is often expensive. However, for many tasks, even when the true output is unknown, we can evaluate predictions using a scalar reward function, which may be easily…

机器学习 · 计算机科学 2021-10-19 Amirmohammad Rooshenas , Dongxu Zhang , Gopal Sharma , Andrew McCallum

Deep structured models are widely used for tasks like semantic segmentation, where explicit correlations between variables provide important prior information which generally helps to reduce the data needs of deep nets. However, current…

机器学习 · 计算机科学 2018-11-02 Colin Graber , Ofer Meshi , Alexander Schwing

Structured prediction in natural language processing (NLP) has a long history. The complex models of structured application come at the difficulty of learning and inference. These difficulties lead researchers to focus more on models with…

计算与语言 · 计算机科学 2021-08-31 Lifu Tu

Reinforcement learning has been successfully applied to the problem of tuning PID controllers in several applications. The existing methods often utilize function approximation, such as neural networks, to update the controller parameters…

Modern applications require methods that are computationally feasible on large datasets but also preserve statistical efficiency. Frequently, these two concerns are seen as contradictory: approximation methods that enable computation are…

统计方法学 · 统计学 2021-06-11 Darren Homrighausen , Daniel J. McDonald

Recent advances in large language models (LLMs) have shown that test-time scaling can substantially improve model performance on complex tasks, particularly in the coding domain. Under this paradigm, models use a larger token budget during…

人工智能 · 计算机科学 2026-04-21 Jiaxin Fang , Runyuan He , Sahil Bhatia , Neel Gajare , Alvin Cheung

Predicting structured outputs can be computationally onerous due to the combinatorially large output spaces. In this paper, we focus on reducing the prediction time of a trained black-box structured classifier without losing accuracy. To do…

机器学习 · 计算机科学 2018-06-13 Xingyuan Pan , Vivek Srikumar

Generating semantically coherent text requires a robust internal representation of linguistic structures, which traditional embedding techniques often fail to capture adequately. A novel approach, Latent Lexical Projection (LLP), is…

计算与语言 · 计算机科学 2025-03-26 Ziad Shaker , Brendan Ashdown , Hugo Fitzalan , Alistair Heathcote , Jocasta Huntington

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these…

机器学习 · 计算机科学 2018-06-01 Hongyu Ren , Russell Stewart , Jiaming Song , Volodymyr Kuleshov , Stefano Ermon

Deep learning harnesses massive parallel floating-point processing to train and evaluate large neural networks. Trends indicate that deeper and larger neural networks with an increasing number of parameters achieve higher accuracy than…

计算机视觉与模式识别 · 计算机科学 2023-08-29 Brad Larson , Bishal Upadhyaya , Luke McDermott , Siddha Ganju

A successful approach to structured learning is to write the learning objective as a joint function of linear parameters and inference messages, and iterate between updates to each. This paper observes that if the inference problem is…

机器学习 · 计算机科学 2014-07-04 Justin Domke

Distilling data into compact and interpretable analytic equations is one of the goals of science. Instead, contemporary supervised machine learning methods mostly produce unstructured and dense maps from input to output. Particularly in…

机器学习 · 计算机科学 2021-05-14 Matthias Werner , Andrej Junginger , Philipp Hennig , Georg Martius

We describe a method for utilizing the known structure of input data to make learning more efficient. Our work is in the domain of programming languages, and we use deep neural networks to do program analysis. Computer programs include a…

神经与进化计算 · 计算机科学 2019-04-01 Zehra Sura , Tong Chen , Hyojin Sung

Large Language Models (LLMs) are unable to reliably reason about specific physical systems. Attempts to imbue LLMs with knowledge of the necessary physics concepts have shown great promise, but explainability and validation remain open…

人工智能 · 计算机科学 2026-05-22 Sean Memery , Kartic Subr

We propose and analyze a regularization approach for structured prediction problems. We characterize a large class of loss functions that allows to naturally embed structured outputs in a linear space. We exploit this fact to design…

机器学习 · 计算机科学 2017-07-31 Carlo Ciliberto , Alessandro Rudi , Lorenzo Rosasco

Regression methods are fundamental for scientific and technological applications. However, fitted models can be highly unreliable outside of their training domain, and hence the quantification of their uncertainty is crucial in many of…

机器学习 · 统计学 2024-03-05 Filippo Bigi , Sanggyu Chong , Michele Ceriotti , Federico Grasselli