New method uses consistent gradient estimators for SGD in interconnected graphs.
problem Efficiently computing unbiased gradient estimators in interconnected graph scenarios.
method Uses consistent gradient estimators as an alternative to unbiased ones.
result Consistent estimators lead to the same convergence behavior as unbiased ones in various objective types.
Deep neural networks without regularization can achieve consistent estimates with good convergence rates.
problem The necessity of regularization in deep neural networks for consistent estimates.
method Gradient descent on an over-parametrized neural network without regularization, with specific initialization, step size, and number of steps.
result An estimate without regularization is universally consistent and achieves good convergence rates.
A new estimator improves training of probabilistic models with latent Gaussian variables.
problem Improving gradient estimation for models with latent Gaussian variables.
method Rao-Blackwellised Reparameterisation Gradients (R2-G2)
result R2-G2 consistently yields better performance in models with multiple applications of the reparameterisation trick.
DBQPG improves policy gradient estimation with fewer samples.
problem Accurate policy gradient estimation with limited samples.
method Deep Bayesian Quadrature Policy Gradient (DBQPG).
result DBQPG provides more accurate and less variable gradient estimates.
New estimator reduces variance in discrete random variables.
problem Estimating gradients for discrete random variables with reduced variance.
method Sampling without replacement and Rao-Blackwellization.
result Our estimator is the most consistent gradient estimator across different entropy settings.
Analysis of cross-validation for early-stopped gradient descent in high-dimensional regression.
problem Inconsistency of GCV for early-stopped GD in high-dimensional least squares regression.
method Theoretical analysis of GCV and LOOCV applied to early-stopped GD in high-dimensional least squares regression.
result LOOCV converges uniformly to the prediction risk of early-stopped GD, while GCV is generically inconsistent.
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…
The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy gradient estimates for reliable policy updates. In this paper, we combine the followi…
Improved stochastic gradient estimation for deep learning in high dimensions.
problem Inadmissibility of mini-batch gradients in high-dimensional settings.
method Stein-rule shrinkage applied to gradient computation.
result The proposed SR-Adam outperforms Adam in large-batch settings.
FGD reduces noisy gradient variance in SGD for neural networks.
problem Noisy and unreliable gradient estimation in SGD for deep learning.
method Solves an adaptive filtering problem to consistently estimate the local gradient.
result Significantly reduces gradient variance and accelerates convergence.
Averaged Gradient Descent improves performance in rough landscapes.
problem Minimizing strongly non-convex functions in high-dimensional estimation problems.
method Empirical average of gradients over random positions in parameter space.
result Averaged Gradient Descent outperforms existing methods in tensor PCA.
DGPs with variational inference suffer from SNR issues that degrade gradient estimates, leading to unreliable training.
problem SNR issues in gradient estimates for DGPs with variational inference.
method Adapted doubly reparameterized gradient estimators for DGP training.
result Fix improves predictive performance of DGP models.
TrIM improves gradient-based dimension reduction and regression.
problem Efficiently identifying relevant feature subspace for high-dimensional regression.
method Introduced TrIM forest, an iterative approach using Mondrian forest and EGOP estimate.
result Consistency guarantees and convergence rates for EGOP matrix and random forest estimator.
A new method for optimizing models with categorical variables using diffusion.
problem Optimizing models with categorical variables, especially in discrete distributions.
method Introducing ReDGE, a diffusion-based soft reparameterization method for categorical distributions.
result ReDGE consistently matches or outperforms existing gradient-based methods in experiments.
Paper proposes a new estimator for generic discrete distributions.
problem Estimating gradients for stochastic nodes in deep generative models.
method Generalized Gumbel-Softmax estimator using truncation, Gumbel-Softmax trick, and linear transformation.
result Efficacy and practical value demonstrated in synthetic examples and topic models.
GPG improves RL from feedback with less memory and compute.
problem Improving reinforcement learning from human feedback.
method Group-based Monte Carlo advantage estimator replacing learned value function.
result GPG matches or outperforms PPO on standard benchmarks.
Abstract reviews algorithms for multi-index models, focusing on polynomial-time methods and their limitations.
problem Estimating the index space in multi-index models efficiently and accurately.
method Polynomial-time algorithms in Gaussian space, nonparametric gradient estimation, and neural network fitting.
result A gap exists between computationally efficient methods and information-theoretical minimum.
The paper develops statistical inference for gradient flows in optimization.
problem Uncertainty quantification along the entire optimization path.
method Uniform central limit theorem and algorithm-aware covariance estimator.
result Asymptotically valid confidence intervals for target parameter.
Improves RL efficiency with nonparametric methods.
problem High sample complexity in policy gradient algorithms.
method Nonparametric regression and density estimation for value function estimation.
result Better sample efficiency compared to existing methods.
The paper proposes methods to estimate MCMC quality with couplings, bounding Wasserstein distance.
problem Improving MCMC efficiency without sacrificing asymptotic consistency.
method Estimators based on couplings of Markov chains to assess quality of asymptotically biased sampling methods.
result Empirical upper bounds of Wasserstein distance for assessing MCMC quality.
Given functional data from a survival process with time-dependent covariates, we derive a smooth convex representation for its nonparametric log-likelihood functional and obtain its functional gradient. From this, we devise a generic gradient boosting procedure for estimating the hazard function nonparametrically. An i…
Online SGD achieves consistent estimation in high-dimensional non-convex inference tasks.
problem Consistent estimation in high-dimensional non-convex optimization problems.
method Online stochastic gradient descent (SGD) on non-convex losses.
result Nearly sharp thresholds for sample complexity in high-dimensional settings.
A faster method for estimating effects in large data using fixed-point trees.
problem Estimating heterogeneous effects in large dimensions with computational efficiency.
method Fixed-point approximation to eliminate Jacobian estimation and speed up GRFs.
result Significant computational efficiency improvement without sacrificing statistical accuracy.
We prove the statistical consistency of kernel Partial Least Squares Regression applied to a bounded regression learning problem on a reproducing kernel Hilbert space. Partial Least Squares stands out of well-known classical approaches as e.g. Ridge Regression or Principal Components Regression, as it is not defined as…
Enhanced DFO using adaptive batch-based FD estimates.
problem Derivative-free optimization with imprecise gradient estimates.
method Adaptive batch-based finite difference estimation and dynamic sampling strategy.
result Algorithm achieves convergence rate similar to KW and SPSA methods.
Estimates log-likelihood of interacting particle systems using virtual particles.
problem Inconsistent estimation of finite-particle log-likelihood in large particle systems.
method Stochastic gradient estimate using continuous trajectory and virtual particle systems.
result Convergence to stationary points of limiting mean-field system's log-likelihood.
The paper analyzes stability and generalization of shallow neural networks using gradient methods.
problem Understanding the generalization of overparameterized shallow neural networks.
method The paper uses gradient descent and stochastic gradient descent to study shallow neural networks, developing consistent excess risk bounds.
result The analysis improves on existing methods by providing a refined estimation of iterates and Hessian eigenvalues, leading to better excess risk bounds.
A new boosting method corrects endogeneity bias in instrumental variable regression.
problem Endogeneity bias in instrumental variable regression.
method Causal Gradient Boosting (boostIV) that builds on gradient boosting algorithm.
result boostIV is consistent and performs well in finite samples compared to other methods.
Paper proposes an online estimator for covariance matrix of SGD iterates.
problem Quantifying variability and randomness of SGD-based estimates in online learning.
method Proposes a fully online estimator for covariance matrix of ASGD using SGD iterates.
result Establishes consistency of the online estimator and shows comparable convergence rate to offline methods.
Develop gradient boosting for estimating covariate-dependent GP distributions in insurance.
problem Estimating covariate-dependent Generalized Pareto distributions in insurance.
method Developing a statistical learning theory for gradient boosting.
result Deriving non-asymptotic error bounds for the boosting estimator.
New sparsity operator reduces variance reduction methods' computational cost.
problem Reduce computational cost of variance reduction methods.
method Introduce random-top-k operator to estimate gradient sparsity and reduce operations per update.
result Our algorithm consistently outperforms SpiderBoost in various tasks.
Unified perspective on score matching and new estimators designed.
problem Infeasibility of maximum likelihood estimation in complex models.
method Minimum Stein discrepancy estimators, diffusion kernel Stein discrepancy (DKSD), diffusion score matching (DSM).
result Consistency, asymptotic normality, and robustness of DKSD and DSM estimators.
DisARM improves gradient estimation for binary latent variables.
problem Challenges in training models with discrete latent variables.
method Uses antithetic sampling over continuous augmentation.
result DisARM consistently outperforms ARM and baseline methods in log-likelihood and variance.
New algorithm optimally minimizes convex functions with noisy gradients.
problem Minimizing strongly convex, smooth functions with noisy gradient estimates.
method A multistage accelerated stochastic gradient method with restarts.
result Achieves optimal convergence rate in deterministic and stochastic cases.
A new training method uses multilevel minimization for machine learning.
problem Training machine learning models with high variance and low efficiency.
method Constructs a multilevel hierarchy by reducing sample size and internally trains surrogate models with fewer samples.
result The multilevel method enhances model training efficiency compared to subsampled Newton's and variance reduction methods.
An online decision-making algorithm using stochastic gradient descent for big data.
problem Efficiently updating decision rules in online decision making with big data.
method Stochastic gradient descent for online updates, asymptotic normality of estimators.
result Asymptotic normality of parameter and value estimators, enabling statistical inference.
Proposes a method to stabilize Black Box Variational Inference using the James-Stein estimator.
problem Stability issues and fine-tuning required in basic Black Box Variational Inference.
method Reframe stochastic gradient ascent as multivariate estimation problem using James-Stein estimator.
result Provides a simpler method with consistent performance in terms of model fit and convergence time.
This text explores strategies for learning discrete latent structures in neural networks.
problem Learning discrete latent structures in neural networks is challenging.
method Continuous relaxation, surrogate gradients, and probabilistic estimation.
result Many latent structure learning strategies use the same fundamental building blocks but apply them differently.
Paper develops methods for statistical inference with SGD in nonconvex optimization.
problem Statistical inference for nonconvex optimization problems.
method Proposes two online inferential procedures combining SGD and bootstrap techniques.
result Establishes error convergence rates and asymptotically valid bootstrap confidence intervals.
New method improves off-policy critic evaluation in reinforcement learning.
problem High variance and instability in off-policy policy evaluation.
method Doubly robust estimators applied to actor-critic algorithms.
result Doubly robust estimation significantly improves performance in continuous control tasks.
ES-Single uses ES to estimate gradients in unrolled graphs, reducing variance and improving performance.
problem Estimating gradients in unrolled computation graphs with low variance and stability.
method Evolution strategies (ES) applied to unrolled graphs, with a single perturbation per particle.
result ES-Single reduces variance compared to PES, leading to better performance in various tasks.
New method estimates velocity fields for minimizing f-divergences without overfitting.
problem Minimizing statistical discrepancies between target and particle distributions.
method Directly estimate velocity fields using interpolation techniques, proving consistency under mild conditions.
result Consistent estimators of velocity fields improve accuracy in applications like domain adaptation and missing data imputation.
SVO improves particle diversity and variational bounds in filtering SMC.
problem Improving variational bounds in particle filtering with limited samples.
method Introduces Particle Smoothing Variational Objectives (SVO) for smoothed approximate posterior through subsampling.
result SVO outperforms filtered objectives with fewer Monte Carlo samples on nonlinear systems.
A new SGD framework reduces empirical risk by favoring higher loss observations.
problem Minimizing empirical risk in machine learning problems.
method Develops a biased gradient estimator for stochastic optimization.
result Minimizes an ordered modification of the empirical average loss.
Proposes SDRG to adjust missingness in machine learning models.
problem Systemic missingness in observational data leads to biased parameter estimation.
method Introduces SDRG using two models: weight-corrected gradients and per-covariate control variates.
result Empirically demonstrates convergence in training image classifiers with missing data.
Estimates generalization gap for overparameterized models using Langevin approximation.
problem Estimating the difference between training and generalization performance in overparameterized models.
method Functional variance and Langevin approximation of functional variance.
result Demonstrates efficient estimation of generalization gaps for overparameterized models.
DAIS improves AIS for differentiable marginal likelihood estimation.
problem Differentiable marginal likelihood estimation for complex models.
method Proposes Differentiable Annealed Importance Sampling (DAIS) to make AIS differentiable.
result DAIS achieves convergence and consistency in Bayesian linear regression.
A new algorithm for reinforcement learning using SVRPG.
problem Solving Markov Decision Processes (MDPs) with policy gradient methods.
method Stochastic variance-reduced policy gradient (SVRPG) algorithm.
result SVRPG achieves linear convergence under increasing batch sizes.