NCE and CD are shown to be equivalent ML methods.
problem Estimating unnormalised models without normalisation constant.
method NCE uses proxy criterion, CD uses importance sampling.
result NCE and CD are equivalent ML methods.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,878 papers · 148 categories
Trend · papers per month
32 results for “NCE”
Researchers improve NCE by addressing its flat loss landscape issues.
problem NCE's poor performance due to an ill-behaved loss landscape.
method Introduced eNCE with an exponential loss and normalized gradient descent.
result Proven that landscape issues arise from inappropriate noise distribution.
There are many models, often called unnormalized models, whose normalizing constants are not calculated in closed form. Maximum likelihood estimation is not directly applicable to unnormalized models. Score matching, contrastive divergence method, pseudo-likelihood, Monte Carlo maximum likelihood, and noise contrastive…
Gaussians as noise in NCE lead to exponentially bad conditioning, hindering its efficiency.
problem Exponential conditioning of Hessian in NCE with Gaussian noise.
method Using Gaussian as the noise distribution in NCE.
result Gaussian noise in NCE leads to exponentially bad conditioning of the loss Hessian.
Unified view on learning unnormalized distributions using NCE.
problem Learning unnormalized distributions across different communities.
method Noise-Contrastive Estimation (NCE) for a unified perspective.
result Established finite-sample convergence rates for exponential families.
Many parametric statistical models are not properly normalised and only specified up to an intractable partition function, which renders parameter estimation difficult. Examples of unnormalised models are Gibbs distributions, Markov random fields, and neural network models in unsupervised deep learning. In previous wor…
A new whole-sentence language model - neural trans-dimensional random field language model (neural TRF LM), where sentences are modeled as a collection of random fields, and the potential function is defined by a neural network, has been introduced and successfully trained by noise-contrastive estimation (NCE). In this…
Two recently introduced criteria for estimation of generative models are both based on a reduction to binary classification. Noise-contrastive estimation (NCE) is an estimation procedure in which a generative model is trained to be able to distinguish data samples from noise samples. Generative adversarial networks (GA…
Improved visual representation learning with conditional negative sampling.
problem Learning strong unsupervised visual representations using contrastive learning.
method Introduce a family of mutual information estimators that sample negatives conditionally.
result Improves accuracy by 2-5% points on four standard image datasets.
We develop a general method for estimating a finite mixture of non-normalized models. Here, a non-normalized model is defined to be a parametric distribution with an intractable normalization constant. Existing methods for estimating non-normalized models without computing the normalization constant are not applicable …
Paper improves video feature learning for better downstream tasks.
problem Improving video feature learning for better performance on downstream tasks.
method Self-supervised learning approach using contrastive bidirectional transformer, extending BERT for real-valued feature vectors.
result Significantly improved performance on video classification, captioning, and segmentation tasks.
Unified framework connects NCE, MIS, RLR, and bridge sampling for EBMs.
problem Challenges in parameter estimation for intractable likelihood EBMs.
method Unified framework connecting NCE, RLR, MIS, and bridge sampling.
result Unified perspective clarifies relationships among existing methods.
Many statistical models are given in the form of non-normalized densities with an intractable normalization constant. Since maximum likelihood estimation is computationally intensive for these models, several estimation methods have been developed which do not require explicit computation of the normalization constant,…
Calibration of simplified vine copulas using noise contrastive estimation
problem Modeling complex multivariate dependence structures
method Noise contrastive estimation for calibration
result Improved model accuracy when simplifying assumption is violated
Unnormalised latent variable models are a broad and flexible class of statistical models. However, learning their parameters from data is intractable, and few estimation techniques are currently available for such models. To increase the number of techniques in our arsenal, we propose variational noise-contrastive esti…
Several dihedral angles prediction methods were developed for protein structure prediction and their other applications. However, distribution of predicted angles would not be similar to that of real angles. To address this we employed generative adversarial networks (GAN). Generative adversarial networks are composed …
Adaptive multi-stage density ratio estimation improves learning of latent space EBM.
problem Learning energy-based models in latent space is computationally expensive and challenging.
method Adaptive multi-stage density ratio estimation using NCE to bridge the gap between prior and posterior densities.
result The method enables more expressive prior models and sharpens the latent space EBM.
Genealogy research is the study of family history using available resources such as historical records. Ancestry provides its customers with one of the world's largest online genealogical index with billions of records from a wide range of sources, including vital records such as birth and death certificates, census re…
New methods improve Monte Carlo estimation of partition functions.
problem Estimating the normalization constant of complex distributions.
method Annealing through paths of distributions to estimate partition functions.
result Optimal path for estimation is arithmetic, improving efficiency.
New insights into noise distribution for self-supervised learning.
problem Challenges the assumption that optimal noise should match data distribution.
method Turns to Noise-Contrastive Estimation (NCE) to define optimality of noise distribution.
result Optimal noise distribution is different from data distribution, challenging GANs assumption.
This paper broadens contrastive learning for disentangled representations without strict data distribution assumptions.
problem Learning disentangled representations from data with specific assumptions.
method Extends theoretical guarantees for disentanglement to a broader family of contrastive methods, relaxing data distribution assumptions.
result Identifiability of true latents for four contrastive losses proved without common independence assumptions.
We present NN-grams, a novel, hybrid language model integrating n-grams and neural networks (NN) for speech recognition. The model takes as input both word histories as well as n-gram counts. Thus, it combines the memorization capacity and scalability of an n-gram model with the generalization ability of neural network…
This paper proposes a method for multi-class classification problems, where the number of classes K is large. The method, referred to as Candidates vs. Noises Estimation (CANE), selects a small subset of candidate classes and samples the remaining classes. We show that CANE is always consistent and computationally effi…
EBMs are flexible but hard to train; this paper explains methods.
problem Training Energy-Based Models is difficult due to the unknown normalizing constant.
method Explains MCMC, SM, and NCE for training EBMs, highlighting connections.
result Provides a friendly introduction to modern EBM training methods.
COBRA reduces modality gap in cross-modal tasks.
problem Joint embedding spaces fail to sufficiently reduce modality gap in multi-modal tasks.
method COBRA trains image and text modalities in a joint fashion using Contrastive Predictive Coding and Noise Contrastive Estimation.
result COBRA significantly reduces the modality gap and generates robust joint-embedding space.
New findings show optimal noise in contrastive learning is not the same as data distribution.
problem The optimal noise distribution in contrastive learning is not the same as the data distribution.
method Empirical and theoretical analysis of contrastive learning methods.
result Deviation from the assumption of equal noise and data distribution leads to better statistical estimators.
Learning neural trans-dimensional random field language models with noise-contrastive estimationcs.CL
Trans-dimensional random field language models (TRF LMs) where sentences are modeled as a collection of random fields, have shown close performance with LSTM LMs in speech recognition and are computationally more efficient in inference. However, the training efficiency of neural TRF LMs is not satisfactory, which limit…
We propose BlackOut, an approximation algorithm to efficiently train massive recurrent neural network language models (RNNLMs) with million word vocabularies. BlackOut is motivated by using a discriminative loss, and we describe a new sampling strategy which significantly reduces computation while improving stability, …
Paper refines InfoNCE for accurate mutual information estimation.
problem Indirect connection of InfoNCE to mutual information estimation.
method Introduces InfoNCE-anchor with an auxiliary anchor class for consistent density ratio estimation.
result InfoNCE-anchor yields a plug-in MI estimator with significantly reduced bias.
Paper tackles multi-task learning for molecular property prediction with limited data.
problem Limited labeled data for each molecular property task in drug discovery.
method Proposes SGNN-EBM method to utilize relation graph between tasks and improve multi-task learning performance.
result Empirical results show the effectiveness of SGNN-EBM.
New method identifies causal relationships using proxy variables in the presence of unmeasured confounders.
problem Challenges in inferring causal relationships due to unmeasured confounding.
method Develops a general nonparametric approach using a single negative control outcome (NCO) and negative control exposure (NCE).
result Establishes a new identification result and proposes a kernel-based testing procedure.
Bayesian Causal Forests model assesses part-time work's impact on student growth.
problem Estimating causal effects of part-time work on student growth in mathematics achievement.
method Longitudinal Bayesian Causal Forests model combining non-parametric and difference-in-differences methods.
result Negative impact of part-time work for most students, potential benefits for those with low school belonging, widening achievement gap identified.