arXiv research

Paper introduces a new multi-kernel algorithm for better gradient approximation.

Reinforcement learning algorithms such as the deep deterministic policy gradient algorithm (DDPG) has been widely used in continuous control tasks. However, the model-free DDPG algorithm suffers from high sample complexity. In this paper we consider the deterministic value gradients to improve the sample efficiency of …

Gradient descent variants improve phase retrieval accuracy.

SGBD algorithm improves robustness in Bayesian sampling.

Paper proposes an $ε$-policy gradient for online pricing, reducing regret to $\mathcal{O}(\sqrt{T})$.

This paper analyzes adaptive gradient algorithms for better performance in ill-conditioned problems.

STORM-PG uses momentum for faster policy gradient updates.

Paper improves convergence rates and step sizes for gradient algorithms.

Gradient boosting method enforced with individual fairness.

Adaptive algorithm improves convergence rate of Langevin dynamics.

The paper analyzes SW-SGD for MSE in biased and variance-reduced gradient estimators.

SAGD uses Langevin algorithm for efficient gradient descent.

Gradient GA uses gradient information to improve molecular design.

In this paper, we study and analyze the mini-batch version of StochAstic Recursive grAdient algoritHm (SARAH), a method employing the stochastic recursive gradient, for solving empirical loss minimization for the case of nonconvex losses. We provide a sublinear convergence rate (to stationary points) for general noncon…

We present a unifying framework for adapting the update direction in gradient-based iterative optimization methods. As natural special cases we re-derive classical momentum and Nesterov's accelerated gradient method, lending a new intuitive interpretation to the latter algorithm. We show that a new algorithm, which we …

Blind Descent avoids gradient issues, using a different learning approach.

In machine learning research, the proximal gradient methods are popular for solving various optimization problems with non-smooth regularization. Inexact proximal gradient methods are extremely important when exactly solving the proximal operator is time-consuming, or the proximal operator does not have an analytic sol…

Overview of non-stochastic-gradient SA algorithms in signal processing and ML.

New algorithms for sampling and optimization without tuning.

Stochastic gradient algorithms estimate the gradient based on only one or a few samples and enjoy low computational cost per iteration. They have been widely used in large-scale optimization problems. However, stochastic gradient algorithms are usually slow to converge and achieve sub-linear convergence rates, due to t…

Review of gradient-based algorithms in statistical inference problems.

New algorithms ensure reproducibility and optimal convergence in convex optimization.

In this paper, we aim at providing an introduction to the gradient descent based optimization algorithms for learning deep neural network models. Deep learning models involving multiple nonlinear projection layers are very challenging to train. Nowadays, most of the deep learning model training still relies on the back…

We study finite-sum nonconvex optimization problems, where the objective function is an average of $n$ nonconvex functions. We propose a new stochastic gradient descent algorithm based on nested variance reduction. Compared with conventional stochastic variance reduced gradient (SVRG) algorithm that uses two reference …

Accelerated gradient method's stability deteriorates exponentially with steps.

We introduce a simple algorithm, True Asymptotic Natural Gradient Optimization (TANGO), that converges to a true natural gradient descent in the limit of small learning rates, without explicit Fisher matrix estimation. For quadratic models the algorithm is also an instance of averaged stochastic gradient, where the par…

Improved bounds for proximal gradient algorithms with computational errors.

Online learning with limited information feedback (bandit) tries to solve the problem where an online learner receives partial feedback information from the environment in the course of learning. Under this setting, Flaxman et al.[8] extended Zinkevich's classical Online Gradient Descent (OGD) algorithm [29] by proposi…

EGAB algorithms improve online portfolio selection.

New sparsity operator reduces variance reduction methods' computational cost.

This paper investigates asymptotic behaviors of gradient descent algorithms (particularly accelerated gradient descent and stochastic gradient descent) in the context of stochastic optimization arising in statistics and machine learning where objective functions are estimated from available data. We show that these alg…

Iterative algorithms, like gradient descent, are common tools for solving a variety of problems, such as model fitting. For this reason, there is interest in creating differentially private versions of them. However, their conversion to differentially private algorithms is often naive. For instance, a fixed number of i…

Study on privacy leakage in noisy gradient descent algorithms.

Paper introduces a new gradient estimator for SNNs.

We introduce Kalman Gradient Descent, a stochastic optimization algorithm that uses Kalman filtering to adaptively reduce gradient variance in stochastic gradient descent by filtering the gradient estimates. We present both a theoretical analysis of convergence in a non-convex setting and experimental results which dem…

Policy gradient algorithm with variable learning rates achieves near-optimal performance in multi-arm bandit problems.

A new gradient tree boosting framework reduces variance and accelerates performance.

In this paper, we propose an implicit gradient descent algorithm for the classic $k$-means problem. The implicit gradient step or backward Euler is solved via stochastic fixed-point iteration, in which we randomly sample a mini-batch gradient in every iteration. It is the average of the fixed-point trajectory that is c…

Paper analyzes inclusive KL inference using Wasserstein gradient flows.

New algorithms improve Langevin Monte Carlo efficiency.

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

Backpropagation and the chain rule of derivatives have been prominent; however, the total derivative rule has not enjoyed the same amount of attention. In this work we show how the total derivative rule leads to an intuitive visual framework for creating gradient estimators on graphical models. In particular, previous …

New algorithms reduce regret in online convex optimization with heavy-tailed gradients.

Gravilon improves gradient descent for neural networks.

Paper introduces a new gradient statistic to improve deep learning convergence.

We use differential equations based approaches to provide some {\it \textbf{physics}} insights into analyzing the dynamics of popular optimization algorithms in machine learning. In particular, we study gradient descent, proximal gradient descent, coordinate gradient descent, proximal coordinate gradient, and Newton's …

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

Bayesian learning rule unifies and generalizes various machine learning algorithms.