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.
RényiCL uses Rényi divergence for robust contrastive learning with stronger data augmentations.
Contrastive Divergence (CD) and Persistent Contrastive Divergence (PCD) are popular methods for training the weights of Restricted Boltzmann Machines. However, both methods use an approximate method for sampling from the model distribution. As a side effect, these approximations yield significantly different biases and…
Theoretical proof shows COMs are a type of contrastive divergence model with improved sampling.
NCE and CD are shown to be equivalent ML methods.
Paper proposes f-EBM for training deep EBMs using various f-divergences.
This paper proposes a more efficient training method for energy-based models.
CD algorithm achieves near-optimal convergence rate for unnormalized models.
We develop a method to combine Markov chain Monte Carlo (MCMC) and variational inference (VI), leveraging the advantages of both inference approaches. Specifically, we improve the variational distribution by running a few MCMC steps. To make inference tractable, we introduce the variational contrastive divergence (VCD)…
New statistical theory explains contrastive learning effectiveness.
VCL adds uncertainty to contrastive learning models.
Self-supervised and supervised methods learn similar intermediate visual representations but diverge in final layers.
Continuous-time PCD for MLE with explicit error bounds.
New theory explains GAN's high quality but low diversity.
Disagreement between two classifiers regarding the class membership of an observation in pattern recognition can be indicative of an anomaly and its nuance. As in general classifiers base their decision on class aposteriori probabilities, the most natural approach to detecting classifier incongruence is to use divergen…
Contrastive divergence (CD) is a promising method of inference in high dimensional distributions with intractable normalizing constants, however, the theoretical foundations justifying its use are somewhat shaky. This document proposes a framework for understanding CD inference, how/when it works, and provides multiple…
Estimating the log-likelihood gradient with respect to the parameters of a Restricted Boltzmann Machine (RBM) typically requires sampling using Markov Chain Monte Carlo (MCMC) techniques. To save computation time, the Markov chains are only run for a small number of steps, which leads to a biased estimate. This bias ca…
This paper proposes the divergence triangle as a framework for joint training of generator model, energy-based model and inference model. The divergence triangle is a compact and symmetric (anti-symmetric) objective function that seamlessly integrates variational learning, adversarial learning, wake-sleep algorithm, an…
Parametric adversarial divergences, which are a generalization of the losses used to train generative adversarial networks (GANs), have often been described as being approximations of their nonparametric counterparts, such as the Jensen-Shannon divergence, which can be derived under the so-called optimal discriminator …
Fisher auto-encoders use Fisher divergence for more robust generative modeling.
By exploiting the property that the RBM log-likelihood function is the difference of convex functions, we formulate a stochastic variant of the difference of convex functions (DC) programming to minimize the negative log-likelihood. Interestingly, the traditional contrastive divergence algorithm is a special case of th…
CD learning is shown to be an adversarial game for fitting models.
We show that the Bregman divergence provides a rich framework to estimate unnormalized statistical models for continuous or discrete random variables, that is, models which do not integrate or sum to one, respectively. We prove that recent estimation methods such as noise-contrastive estimation, ratio matching, and sco…
Paper introduces a new method to improve GANs by leveraging the discriminator's energy.
Paper connects rejection learning to Bhattacharyya divergence.
RLMH improves adaptive MCMC by optimizing contrastive divergence reward.
Replicated Softmax model, a well-known undirected topic model, is powerful in extracting semantic representations of documents. Traditional learning strategies such as Contrastive Divergence are very inefficient. This paper provides a novel estimator to speed up the learning based on Noise Contrastive Estimate, extende…
New variational formula for Rényi divergences improves neural network estimation in high dimensions.
In this letter, we generalize the convolutional NMF by taking the -divergence as the contrast function and present the correct multiplicative updates for its factors in closed form. The new updates unify the -NMF and the convolutional NMF. We state why almost all of the existing updates are inexact and approximat…
Restricted Boltzmann machines are undirected neural networks which have been shown to be effective in many applications, including serving as initializations for training deep multi-layer neural networks. One of the main reasons for their success is the existence of efficient and practical stochastic algorithms, such a…
Improved training of GRBMs for image generation.
EBMs improve continual learning without external memory or regularization.
Learning algorithms for energy based Boltzmann architectures that rely on gradient descent are in general computationally prohibitive, typically due to the exponential number of terms involved in computing the partition function. In this way one has to resort to approximation schemes for the evaluation of the gradient.…
New method tackles incomplete data in RBM inverse Ising problems.
New algorithm speeds up NMF with -divergence.
DM framework improves robustness and efficiency in latent-mixture models.
We propose a Laplace approximation that creates a stochastic unit from any smooth monotonic activation function, using only Gaussian noise. This paper investigates the application of this stochastic approximation in training a family of Restricted Boltzmann Machines (RBM) that are closely linked to Bregman divergences.…
Recognizing subtle historical patterns is central to modeling and forecasting problems in time series analysis. Here we introduce and develop a new approach to quantify deviations in the underlying hidden generators of observed data streams, resulting in a new efficiently computable universal metric for time series. Th…
Paper develops tighter risk certificates for contrastive learning models.
EM algorithm converges in KL divergence for exponential families via mirror descent.
A theoretical framework for non-negative matrix factorization based on generalized dual Kullback-Leibler divergence, which includes members of the exponential family of models, is proposed. A family of algorithms is developed using this framework and its convergence proven using the Expectation-Maximization algorithm. …
GRPO optimizes LLMs with verifiable rewards, amplifying policy success.
New measure quantifies contrastive self-supervised learning's generalization ability.
We introduce a simple analysis of the structural complexity of infinite-memory processes built from random samples of stationary, ergodic finite-memory component processes. Such processes are familiar from the well known multi-arm Bandit problem. We contrast our analysis with computation-theoretic and statistical infer…
We propose a number of new algorithms for learning deep energy models and demonstrate their properties. We show that our SteinCD performs well in term of test likelihood, while SteinGAN performs well in terms of generating realistic looking images. Our results suggest promising directions for learning better models by …
Conditional Restricted Boltzmann Machines (CRBMs) are rich probabilistic models that have recently been applied to a wide range of problems, including collaborative filtering, classification, and modeling motion capture data. While much progress has been made in training non-conditional RBMs, these algorithms are not a…
Study convergence and approximations of entropic regularized Wasserstein distances for Gaussian and RKHS measures.
Revisits stress-energy tensor in Finsler spacetimes, showing it's anisotropic.
PROTOCOL tackles imbalanced multi-view clustering by enhancing contrastive learning.