arXiv research

A new method improves stochastic gradient descent for faster and more efficient estimation.

We generalize stochastic smoothing for gradient estimation of non-differentiable functions.

Stochastic gradient descent procedures have gained popularity for parameter estimation from large data sets. However, their statistical properties are not well understood, in theory. And in practice, avoiding numerical instability requires careful tuning of key parameters. Here, we introduce implicit stochastic gradien…

A method for estimating the median of gradients in stochastic optimization.

Improved stochastic gradient estimation for deep learning in high dimensions.

FGD reduces noisy gradient variance in SGD for neural networks.

Paper develops unbiased gradient estimator for continuous-time models.

Storchastic improves stochastic AD for complex models in RL and VI.

New unbiased gradient estimators for complex optimization problems.

A new hybrid algorithm reduces stochastic gradient evaluations for nonconvex optimization.

New estimator for SDEs is shown to be an adjoint state method.

New method improves parameter estimation in complex stochastic models.

Error estimates found between SGD with momentum and Langevin diffusion.

A new algorithm SRG-DQN reduces variance in deep Q-learning.

A number of optimization approaches have been proposed for optimizing nonconvex objectives (e.g. deep learning models), such as batch gradient descent, stochastic gradient descent and stochastic variance reduced gradient descent. Theory shows these optimization methods can converge by using an unbiased gradient estimat…

New method for estimating gradients in stochastic binary networks.

A new method reduces variance in SGMCMC by preferentially subsampling data.

New oracles improve stochastic optimization with noisy or biased measurements.

New method controls gradient error for sparse MRFs.

In this paper we introduce a family of stochastic gradient estimation techniques based of the perturbative expansion around the mean of the sampling distribution. We characterize the bias and variance of the resulting Taylor-corrected estimators using the Lagrange error formula. Furthermore, we introduce a family of va…

Riemannian stochastic gradient descent approximates a diffusion process called Riemannian stochastic modified flow.

Scout-Nd optimizes parameters of stochastic simulators efficiently.

Paper proposes a new estimator for generic discrete distributions.

New method for zeroth-order stochastic gradient algorithms provides confidence intervals.

New approach improves model generalization through distributionally robust learning.

New algorithm improves heavy-tailed statistical estimation in streaming data.

FSGLD improves federated data sampling by correcting noisy gradients.

Stochastic gradient algorithms have been the main focus of large-scale learning problems and they led to important successes in machine learning. The convergence of SGD depends on the careful choice of learning rate and the amount of the noise in stochastic estimates of the gradients. In this paper, we propose a new ad…

Unified framework for gradient estimation in combinatorial spaces.

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…

New method improves online covariance estimation for SGD.

The paper analyzes the efficiency of gradient estimation methods in noisy function evaluations.

Variational inference approximates the posterior distribution of a probabilistic model with a parameterized density by maximizing a lower bound for the model evidence. Modern solutions fit a flexible approximation with stochastic gradient descent, using Monte Carlo approximation for the gradients. This enables variatio…

Stochastic gradient MCMC (SG-MCMC) has played an important role in large-scale Bayesian learning, with well-developed theoretical convergence properties. In such applications of SG-MCMC, it is becoming increasingly popular to employ distributed systems, where stochastic gradients are computed based on some outdated par…

An algorithm is proposed for solving stochastic and finite sum minimization problems. Based on a trust region methodology, the algorithm employs normalized steps, at least as long as the norms of the stochastic gradient estimates are within a specified interval. The complete algorithm---which dynamically chooses whethe…

Estimates log-likelihood of interacting particle systems using virtual particles.

Optimizes shortfall risk using gradient-based methods.

Framework improves gradient estimation for faster training convergence.

Paper develops methods for statistical inference in SGD with infinite variance.

State space models (SSMs) provide a flexible framework for modeling complex time series via a latent stochastic process. Inference for nonlinear, non-Gaussian SSMs is often tackled with particle methods that do not scale well to long time series. The challenge is two-fold: not only do computations scale linearly with t…

We consider nonconvex-concave minimax optimization problems of the form $\min_{\bf x}\max_{\bf y\in{\mathcal Y}} f({\bf x},{\bf y})$, where $f$ is strongly-concave in $\bf y$ but possibly nonconvex in $\bf x$ and ${\mathcal Y}$ is a convex and compact set. We focus on the stochastic setting, where we can only access an…

It is well known that Markov chain Monte Carlo (MCMC) methods scale poorly with dataset size. A popular class of methods for solving this issue is stochastic gradient MCMC. These methods use a noisy estimate of the gradient of the log posterior, which reduces the per iteration computational cost of the algorithm. Despi…

Paper approximates risk measures using SGD with Langevin dynamics.

New method optimizes hyperparameters in deep learning models efficiently.

New method estimates SDE parameters efficiently using WCE and SGD.

Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is often excessive, leading to poor sample efficiency. In this paper, we apply the stoc…

Stochastic Gradient Descent or SGD is the most popular optimization algorithm for large-scale problems. SGD estimates the gradient by uniform sampling with sample size one. There have been several other works that suggest faster epoch-wise convergence by using weighted non-uniform sampling for better gradient estimates…

ICSGLD improves efficiency in posterior sampling for big data.