Unbiased methods for alpha-divergence minimization struggle in high dimensions.
problem The difficulty of unbiased alpha-divergence minimization in high dimensions.
method Signal-to-Noise Ratio (SNR) analysis of gradient estimators.
result The SNR of the gradient estimator worsens exponentially with dimensionality.
Proposes unbiased estimators for training mixture of experts models.
problem Efficiently training large-scale mixture of experts models on modern hardware.
method Two unbiased estimators based on principled stochastic assignment procedures.
result Both estimators are more effective and robust than biased alternatives.
Unbiased wealth exchanges always lead to inequality.
problem Understanding wealth distribution in unbiased binary exchange systems.
method Analytical demonstration of unbiased binary exchanges leading to perfect inequality.
result Any system driven by unbiased binary exchanges will reach perfect inequality and zero mobility.
Computing partition functions, the normalizing constants of probability distributions, is often hard. Variants of importance sampling give unbiased estimates of a normalizer Z, however, unbiased estimates of the reciprocal 1/Z are harder to obtain. Unbiased estimates of 1/Z allow Markov chain Monte Carlo sampling of "d…
Develops unbiased averaging methods for second order optimization in distributed systems.
problem Computing the Hessian is challenging and communication is a bottleneck in distributed optimization.
method Unbiased parameter averaging methods using sampling and sketching of the Hessian.
result Provably minimizes bias for sketched Newton directions.
A new method speeds up sampling of Boltzmann distribution in high-dimensional systems.
problem High computational cost of obtaining Jacobian of flow-based models in high dimensions.
method Flow perturbation method that incorporates stochastic perturbations and reweighting.
result Achieves unbiased sampling of Boltzmann distribution with orders of magnitude speedup.
A new method improves communication efficiency in distributed learning.
problem Reducing communication overhead in distributed machine learning.
method Transforming contractive compressors into induced unbiased compressors.
result Significant improvements in memory requirements and communication complexity.
Paper develops an unbiased risk estimator for learning with augmented classes.
problem Learning with augmented classes where unseen classes might appear in testing.
method Uses unlabeled training data to approximate potential distribution of augmented classes.
result Establishes an unbiased risk estimator for the testing distribution under mild assumptions.
Improved GANs model geological facies with diversity and unbiased distribution.
problem Generating unbiased and representative geological models from training images.
method Info-WGAN combining InfoGAN, Wasserstein distance, and Gradient Penalty.
result Generated samples have equal probability distribution as training data.
New method makes machine learning approximations unbiased and efficient.
problem Efficient sampling of complex probability distributions.
method Uses autoregressive neural networks with cluster updates and physical symmetries.
result Shows unbiased and low-variance approximations for phase transitions.
Improved learning theory for kernel distribution regression with two-stage sampling.
problem Distribution regression problem and two-stage sampling setting.
method Kernel methods, near-unbiased condition, new error bounds, convergence rates.
result Strictly improved convergence rates for three important classes of kernels.
We consider the approximation of expectations with respect to the distribution of a latent Markov process given noisy measurements. This is known as the smoothing problem and is often approached with particle and Markov chain Monte Carlo (MCMC) methods. These methods provide consistent but biased estimators when run fo…
Recent neural network and language models rely on softmax distributions with an extremely large number of categories. Since calculating the softmax normalizing constant in this context is prohibitively expensive, there is a growing literature of efficiently computable but biased estimates of the softmax. In this paper …
In applications of Gaussian processes where quantification of uncertainty is of primary interest, it is necessary to accurately characterize the posterior distribution over covariance parameters. This paper proposes an adaptation of the Stochastic Gradient Langevin Dynamics algorithm to draw samples from the posterior …
Improved UIVI method shows better performance than state-of-the-art SIVI methods.
problem Estimating the likelihood of samples from complex distributions in high dimensions.
method Replaced the inner MCMC loop of UIVI with importance sampling and learned the optimal proposal distribution.
result The refined UIVI approach demonstrates superior performance or parity with state-of-the-art methods.
In linear regression we wish to estimate the optimum linear least squares predictor for a distribution over d-dimensional input points and real-valued responses, based on a small sample. Under standard random design analysis, where the sample is drawn i.i.d. from the input distribution, the least squares solution for…
We develop unbiased implicit variational inference (UIVI), a method that expands the applicability of variational inference by defining an expressive variational family. UIVI considers an implicit variational distribution obtained in a hierarchical manner using a simple reparameterizable distribution whose variational …
Paper introduces a new sampling method combining Consistency Models with importance sampling.
problem Inherent errors in samples and high NFEs for high-quality samples in Boltzmann distributions.
method Combines Consistency Models with importance sampling to produce unbiased samples with minimal NFEs.
result Produces unbiased samples using only 6-25 NFEs, comparable to 100 NFEs for DDPMs.
The Barankin bound is generalized to the vector case in the mean square error sense. Necessary and sufficient conditions are obtained to achieve the lower bound. To obtain the result, a simple finite dimensional real vector valued generalization of the Riesz representation theorem for Hilbert spaces is given. The bound…
New theory of sensitivity for unbiased estimators using Wasserstein geometry.
problem Estimating the instability of estimators under small perturbations.
method Developed a new theory based on Wasserstein geometry, analogous to classical Cramér-Rao theory.
result Wasserstein-Cramér-Rao lower bound for sensitivity of unbiased estimators.
New methods improve distributed optimization on non-iid data.
problem Communication bottleneck in distributed machine learning models.
method Two types of distributed gradient compression methods (D-QSGD and D-EF-SGD) analyzed for non-iid data.
result D-EF-SGD performs better than D-QSGD on non-iid data but can still slow down with high data skewness.
Clapping reduces memory usage in distributed optimization by reusing data samples.
problem Significant communication overhead and impractical memory overhead in pipeline-parallel distributed optimization.
method Lazy sampling strategy to reuse data samples across steps, supporting convergence without unbiased gradient assumptions.
result Clapping achieves convergence in few-epoch or online training regimes without sample-size memory overhead.
Unbiased method for Bayesian posterior means using kinetic Langevin dynamics.
problem Estimating Bayesian posterior means efficiently and accurately.
method Combines advanced splitting methods with enhanced gradient approximations in a multilevel Monte Carlo approach.
result The method achieves unbiased estimates with finite variance and central limit theorem properties.
We propose and analyze a new stochastic gradient method, which we call Stochastic Unbiased Curvature-aided Gradient (SUCAG), for finite sum optimization problems. SUCAG constitutes an unbiased total gradient tracking technique that uses Hessian information to accelerate con- vergence. We analyze our method under the ge…
New method learns from noisy data without knowing noise level.
problem Learning from noisy data without knowing noise level.
method Uses Stein's Unbiased Risk Estimate (SURE) without noise level knowledge.
result Outperforms other self-supervised methods on imaging problems.
A promising class of generative models maps points from a simple distribution to a complex distribution through an invertible neural network. Likelihood-based training of these models requires restricting their architectures to allow cheap computation of Jacobian determinants. Alternatively, the Jacobian trace can be u…
A large class of machine learning techniques requires the solution of optimization problems involving spectral functions of parametric matrices, e.g. log-determinant and nuclear norm. Unfortunately, computing the gradient of a spectral function is generally of cubic complexity, as such gradient descent methods are rath…
New method finds unbiased subnetworks in biased models for better OOD performance.
problem How to improve out-of-distribution generalization in deep models.
method Functional modular probing method and Modular Risk Minimization.
result Even in biased models, there are unbiased subnetworks that can achieve better OOD performance.
Paper proposes an unbiased risk estimator for PLLAC, handling unseen classes.
problem Handling unseen classes in PLLAC where some classes are not present in the training set.
method Proposes an unbiased risk estimator that estimates the distribution of augmented classes by differentiating known classes from unlabeled data.
result The estimator provides theoretical guarantees and converges to true risk minimizer as data increases.
Linear-cost unbiased estimates for complex models via couplings.
problem High-dimensional Bayesian models with crossed effects and matrix factorization.
method Coupled Gibbs samplers for linear computational cost.
result Unbiased posterior estimates at linear cost.
This work improves texture segmentation by automatically tuning hyperparameters for Total-Variation.
problem The challenge is to automatically select hyperparameters for Total-Variation texture segmentation.
method The approach involves extending Stein's unbiased gradient estimator to handle correlated Gaussian noise, leading to an automatic tuning method.
result The method provides an automatic way to select hyperparameters for Total-Variation texture segmentation.
Federated learning improves by unbiased gradient aggregation and controllable meta updating.
problem Gradient biases and inconsistency between target and optimization objectives in federated averaging.
method Unbiased gradient aggregation with keep-trace gradient descent and gradient evaluation strategy, controllable meta updating with small data samples.
result Faster convergence and higher accuracy with different network architectures in various FL settings.
Synthetic construction of 3D complex bases.
problem Creating a complete set of unbiased bases in 3D complex space.
method Synthetic construction using complex projective trigonometry.
result Synthetic construction of mutually unbiased bases in C^3.
Consider a process, stochastic or deterministic, obtained by using a numerical integration scheme, or from Monte-Carlo methods involving an approximation to an integral, or a Newton-Raphson iteration to approximate the root of an equation. We will assume that we can sample from the distribution of the process from time…
Estimates CDF over complex regions using normalizing flows.
problem Challenges in estimating CDF over complex regions using traditional methods.
method Leverages diffeomorphic properties of normalizing flows and divergence theorem.
result Improves sample efficiency in estimating CDF over complex regions.
A key quantity of interest in Bayesian inference are expectations of functions with respect to a posterior distribution. Markov Chain Monte Carlo is a fundamental tool to consistently compute these expectations via averaging samples drawn from an approximate posterior. However, its feasibility is being challenged in th…
Bayesian method improves extreme quantile estimation with zero coverage error.
problem Estimating extreme quantiles with zero coverage error in small samples.
method Bayesian quantile estimation using Jeffreys prior.
result Bayesian method results in zero coverage error, unlike maximum likelihood.
VT-DIS improves sampling from Boltzmann distributions with minimal overhead.
problem Bias in Monte Carlo estimates from score-based diffusion models.
method Variance-Tuned Diffusion Importance Sampling (VT-DIS) adapts noise covariance to correct bias.
result VT-DIS achieves effective sample sizes of 80%, 35%, and 3.5% on benchmarks, using less computational budget.
A key element in transfer learning is representation learning; if representations can be developed that expose the relevant factors underlying the data, then new tasks and domains can be learned readily based on mappings of these salient factors. We propose that an important aim for these representations are to be unbi…
The paper generalizes Bayesian Cramér-Rao inequality using information geometry of relative α-entropy.
problem Establishing a lower bound for the variance of an unbiased estimator for the α-escort distribution.
method Proposes a general Riemannian metric based on relative α-entropy to derive a generalized Bayesian Cramér-Rao inequality.
result Establishes a lower bound for the variance of an unbiased estimator for the α-escort distribution.
The problem of determining the joint probability distributions for correlated random variables with pre-specified marginals is considered. When the joint distribution satisfying all the required conditions is not unique, the "most unbiased" choice corresponds to the distribution of maximum entropy. The calculation of t…
UREs lead to overfitting in complex models, especially in complementary label learning.
problem Overfitting in weakly supervised learning with complementary labels.
method Proposed a surrogate complementary loss (SCL) framework to reduce gradient variance.
result SCL mitigates overfitting and improves URE-based methods.
Neural network predicts short rate model steps accurately.
problem Predicting intractable short rate model steps.
method Proposes an algorithm using neural networks.
result Achieves superior outcomes compared to unbiased estimate.
New unbiased methods for generating stochastic bridges with given extrema.
problem Generating unbiased stochastic bridges with a specified extremum.
method Comparison and generalization of two algorithms for Brownian bridges to other diffusions, and application to Ornstein-Uhlenbeck and unconstrained processes.
result Generalization of unbiased generation methods to other diffusions and application to various processes.
MUSE provides unbiased stopping estimates for optimal problems.
problem Estimating the utility of optimal stopping problems.
method Backward recursive construction of the Multilevel Unbiased Stopping Estimator (MUSE).
result MUSE achieves ε-accuracy with O(1/ε^2) computational cost.
Randomized trials, also known as A/B tests, are used to select between two policies: a control and a treatment. Given a corresponding set of features, we can ideally learn an optimized policy P that maps the A/B test data features to action space and optimizes reward. However, although A/B testing provides an unbiased …
End-to-end training of DBMs with improved gradient estimation.
problem Biased gradient estimation in DBMs, especially with high-dimensional states.
method Unbiased contrastive divergence using MH coupling and local mode initialization.
result End-to-end training of DBMs without greedy pretraining, achieving FID score of 10.33 for MNIST.
Private statistics estimation faces a bias, accuracy, and privacy trilemma.
problem Balancing privacy, accuracy, and bias in statistical estimation.
method Use differential privacy (DP) for private statistics, but clip samples to control sensitivity and add noise for privacy, introducing bias.
result No algorithm can simultaneously have low bias, low error, and low privacy loss for arbitrary distributions.