English
Related papers

Related papers: Empirical Gaussian priors for cross-lingual transf…

200 papers

Large pretrained language models (LMs) have become the central building block of many NLP applications. Training these models requires ever more computational resources and most of the existing models are trained on English text only. It is…

Computation and Language · Computer Science 2022-09-13 Benjamin Minixhofer , Fabian Paischer , Navid Rekabsaz

Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits. Often, performance gains and improved generalization can be…

Computation and Language · Computer Science 2021-07-27 Sougata Saha , Souvik Das , Rohini Srihari

As data sets grow in size, the ability of learning methods to find structure in them is increasingly hampered by the time needed to search the large spaces of possibilities and generate a score for each that takes all of the observed data…

Machine Learning · Computer Science 2012-07-03 Benjamin Yackley , Terran Lane

We consider a Gaussian process formulation of the multiple kernel learning problem. The goal is to select the convex combination of kernel matrices that best explains the data and by doing so improve the generalisation on unseen data.…

Machine Learning · Statistics 2011-10-25 Cedric Archambeau , Francis Bach

Gaussian processes are probabilistic models that are commonly used as functional priors in machine learning. Due to their probabilistic nature, they can be used to capture the prior information on the statistics of noise, smoothness of the…

Computation · Statistics 2024-02-02 Ahmad Farooq , Cristian A. Galvis-Florez , Simo Särkkä

This paper describes an expectation propagation (EP) method for multi-class classification with Gaussian processes that scales well to very large datasets. In such a method the estimate of the log-marginal-likelihood involves a sum across…

Machine Learning · Statistics 2017-06-23 Carlos Villacampa-Calvo , Daniel Hernández-Lobato

Compression is at the heart of effective representation learning. However, lossy compression is typically achieved through simple parametric models like Gaussian noise to preserve analytic tractability, and the limitations this imposes on…

Machine Learning · Computer Science 2019-11-15 Rob Brekelmans , Daniel Moyer , Aram Galstyan , Greg Ver Steeg

What is the best way to exploit extra data -- be it unlabeled data from the same task, or labeled data from a related task -- to learn a given task? This paper formalizes the question using the theory of reference priors. Reference priors…

Machine Learning · Statistics 2022-06-17 Yansong Gao , Rahul Ramesh , Pratik Chaudhari

We study the use of Gaussian process emulators to approximate the parameter-to-observation map or the negative log-likelihood in Bayesian inverse problems. We prove error bounds on the Hellinger distance between the true posterior…

Numerical Analysis · Mathematics 2024-10-01 Andrew M. Stuart , Aretha L. Teckentrup

We develop a computational procedure to estimate the covariance hyperparameters for semiparametric Gaussian process regression models with additive noise. Namely, the presented method can be used to efficiently estimate the variance of the…

Machine Learning · Computer Science 2022-06-22 Siavash Ameli , Shawn C. Shadden

We study the problem of PAC learning halfspaces in the reliable agnostic model of Kalai et al. (2012). The reliable PAC model captures learning scenarios where one type of error is costlier than the others. Our main positive result is a new…

Machine Learning · Computer Science 2024-11-19 Ilias Diakonikolas , Lisheng Ren , Nikos Zarifis

Safety-critical technical systems operating in unknown environments require the ability to quickly adapt their behavior, which can be achieved in control by inferring a model online from the data stream generated during operation. Gaussian…

Systems and Control · Electrical Eng. & Systems 2022-02-24 Armin Lederer , Mingmin Zhang , Samuel Tesfazgi , Sandra Hirche

While end-to-end neural machine translation (NMT) has achieved impressive progress, noisy input usually leads models to become fragile and unstable. Generating adversarial examples as the augmented data has been proved to be useful to…

Computation and Language · Computer Science 2022-10-25 Juncheng Wan , Jian Yang , Shuming Ma , Dongdong Zhang , Weinan Zhang , Yong Yu , Zhoujun Li

Either human annotation or rule based automatic labeling is an effective method to augment data for relation extraction. However, the inevitable wrong labeling problem for example by distant supervision may deteriorate the performance of…

Computation and Language · Computer Science 2020-04-30 Shanchan Wu , Kai Fan

We explore unsupervised speech enhancement using diffusion models as expressive generative priors for clean speech. Existing approaches guide the reverse diffusion process using noisy speech through an approximate, noise-perturbed…

Sound · Computer Science 2025-07-04 Mostafa Sadeghi , Jean-Eudes Ayilo , Romain Serizel , Xavier Alameda-Pineda

We prove that the empirical risk of most well-known loss functions factors into a linear term aggregating all labels with a term that is label free, and can further be expressed by sums of the loss. This holds true even for non-smooth,…

Machine Learning · Computer Science 2016-02-11 Giorgio Patrini , Frank Nielsen , Richard Nock , Marcello Carioni

Previous studies show that intermediate supervision signals benefit various Natural Language Processing tasks. However, it is not clear whether there exist intermediate signals that benefit Neural Machine Translation (NMT). Borrowing…

Computation and Language · Computer Science 2023-05-17 Chaojun Wang , Yang Liu , Wai Lam

We introduce a novel Bayesian estimator for the class proportion in an unlabeled dataset, based on the targeted learning framework. Our procedure requires the specification of a prior (and outputs a posterior) only for the target of…

Methodology · Statistics 2019-11-26 Iván Díaz , Oleksander Savenkov , Hooman Kamel

We show how to predict the basic word-order facts of a novel language given only a corpus of part-of-speech (POS) sequences. We predict how often direct objects follow their verbs, how often adjectives follow their nouns, and in general the…

Computation and Language · Computer Science 2017-10-12 Dingquan Wang , Jason Eisner

Maximizing the likelihood of the next token is an established, statistically sound objective for pre-training language models. In this paper we show that we can train better models faster by pre-aggregating the corpus with a collapsed…

Computation and Language · Computer Science 2024-07-04 Ashutosh Sathe , Sunita Sarawagi