arXiv research

Improved reSGLD accelerates convergence in non-convex learning problems.

Extends denoising and score estimation to energy models via Tweedie's formula.

New method improves sampling from noisy energy models.

Noise-resilient method improves Hurst exponent estimation accuracy in noisy data.

Continuous phase transitions identified in Doi-Onsager, noisy transformer, and Hegselmann-Krause models.

SBO uses dual voting to build consensus in noisy feedback settings.

A new method trains and samples from energy-based models using diffusion recovery likelihood.

Gaussian process model learns Hamiltonian systems from noisy data.

The heuristic identification of peaks from noisy complex spectra often leads to misunderstanding of the physical and chemical properties of matter. In this paper, we propose a framework based on Bayesian inference, which enables us to separate multipeak spectra into single peaks statistically and consists of two steps.…

Unified empirical and variational Bayes for unnormalized densities.

Study phase transitions in noisy transformer dynamics on spheres.

Optimizes noisy IS with better proposal densities.

Dual-T method improves transition matrix estimation in noisy label learning.

We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connection between the misclassification rate and the notion of minimum energy on the local neighborhood of the SBM. We develop an optimally weighte…

Estimates linear model from noisy covariates and instruments using spectral regularization.

Method estimates noise transition matrix from noisy labels without relying on unreliable class-posterior estimation.

We investigate the problem of estimating a given real symmetric signal matrix $\textbf{C}$ from a noisy observation matrix $\textbf{M}$ in the limit of large dimension. We consider the case where the noisy measurement $\textbf{M}$ comes either from an arbitrary additive or multiplicative rotational invariant perturbati…

FEAT estimates free energy using adaptive transports.

Optimizes private statistics with noisy methods.

Paper proposes an alternative to anchor points for learning with noisy labels.

Spectral estimation (SE) aims to identify how the energy of a signal (e.g., a time series) is distributed across different frequencies. This can become particularly challenging when only partial and noisy observations of the signal are available, where current methods fail to handle uncertainty appropriately. In this c…

A new method relaxes molecules without needing non-equilibrium data.

Develops a method to estimate treatment effects using noisy proxies over time.

Paper tackles noisy bandit feedback for multiclass classification.

EB-RANSAC uses energy-based model for robust estimation without complex sampling.

New estimates for Hitchin's equations at high energy.

Optimization with noisy gradients has become ubiquitous in statistics and machine learning. Reparameterization gradients, or gradient estimates computed via the "reparameterization trick," represent a class of noisy gradients often used in Monte Carlo variational inference (MCVI). However, when these gradient estimator…

Deep learning with noisy gradient descent outperforms linear estimators in high dimensions.

Neural density estimators are flexible families of parametric models which have seen widespread use in unsupervised machine learning in recent years. Maximum-likelihood training typically dictates that these models be constrained to specify an explicit density. However, this limitation can be overcome by instead using …

Preconditioned non-convex gradient descent improves noisy matrix estimation.

Proposes CDRL to improve EBM training and generation quality.

We address the problem of estimating the parameters of a time-homogeneous Markov chain given only noisy, aggregate data. This arises when a population of individuals behave independently according to a Markov chain, but individual sample paths cannot be observed due to limitations of the observation process or the need…

Accelerometer measurements are the prime type of sensor information most think of when seeking to measure physical activity. On the market, there are many fitness measuring devices which aim to track calories burned and steps counted through the use of accelerometers. These measurements, though good enough for the aver…

New method uses neural networks to improve free energy estimation.

Paper proposes a new model for noisy tensor completion.

We derive gradient and energy estimates for critical points of the full supersymmetric sigma model and discuss several applications.

A physics-based method improves data interpolators and regression tasks.

This paper generalizes neural transport learning for free energy estimation in arbitrary state spaces.

The paper improves boundary detection and density estimation on noisy data.

MSLG generates soft labels to improve DNN performance on noisy datasets.

Estimates for Schrödinger operators on manifolds with bounded Ricci curvature.

Study of charged scalar fields on Reissner-Nordström spacetimes via energy estimates.

Gradient estimation techniques applied to programs with randomness in high energy physics.

New model estimates Gibbs free energies using machine learning and isobaric-isothermal flows.

Training energy-based probabilistic models is confronted with apparently intractable sums, whose Monte Carlo estimation requires sampling from the estimated probability distribution in the inner loop of training. This can be approximately achieved by Markov chain Monte Carlo methods, but may still face a formidable obs…

Study recovers spike order in noisy tensor estimation without SNR assumptions.

The paper improves energy decay estimates for Dir-stationary Q-valued functions and applies them to Liouville-type theorems and continuity.

Researchers establish bounds and continuity of decomposed Möbius energies using cosine formula.