arXiv research

Proximal online gradient minimizes dynamic regret in evolving environments.

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

Two new methods solve nonsmooth optimization on Riemannian Stiefel manifold.

New method solves convex optimization faster than NAG.

APO optimizes neural network parameters by amortizing proximal point methods.

Online algorithm identifies PDEs from noisy data snapshots.

New method optimizes hyperparameters for non-smooth problems efficiently.

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…

A new method for RLHF using proximal point Nash learning.

Improved bounds for proximal gradient algorithms with computational errors.

This paper explores a new framework for reinforcement learning based on online convex optimization, in particular mirror descent and related algorithms. Mirror descent can be viewed as an enhanced gradient method, particularly suited to minimization of convex functions in highdimensional spaces. Unlike traditional grad…

Innovative method solves nonconvex optimization on manifolds.

Adaptive methods improve gradient descent and proximal gradient for convex optimization.

Unified analysis of EG and OGDA for saddle point problems using proximal point method.

Proposes a probabilistic optimization method for large-scale problems.

We consider the problem of minimizing the sum of two convex functions: one is the average of a large number of smooth component functions, and the other is a general convex function that admits a simple proximal mapping. We assume the whole objective function is strongly convex. Such problems often arise in machine lea…

Optimizes decisions in time-varying distributions using online stochastic methods and Wasserstein distance.

New PnP algorithm converges with relaxed proximal gradient descent.

Unified framework for training neural networks with non-smooth, non-convex regularizers.

This paper converts ADMM to proximal gradient for efficient sparse estimation.

A new method solves convex optimization problems on manifolds efficiently.

Paper analyzes convergence of proximal algorithm in metric spaces without geodesic convexity.

Gradient boosting is a prediction method that iteratively combines weak learners to produce a complex and accurate model. From an optimization point of view, the learning procedure of gradient boosting mimics a gradient descent on a functional variable. This paper proposes to build upon the proximal point algorithm, wh…

In this paper, we investigate the attractive properties of the proximal gradient algorithm with inertia. Notably, we show that using alternated inertia yields monotonically decreasing functional values, which contrasts with usual accelerated proximal gradient methods. We also provide convergence rates for the algorithm…

This work optimizes bid strategies for online auctions using measure-valued optimization.

New methods improve convergence rate of zeroth-order proximal stochastic algorithms.

A regularized optimization problem over a large unstructured graph is studied, where the regularization term is tied to the graph geometry. Typical regularization examples include the total variation and the Laplacian regularizations over the graph. When applying the proximal gradient algorithm to solve this problem, t…

Develops minibatch stochastic proximal gradient for large-scale learning models.

LPOM approximates neural nets with proximal operators for efficient training.

Paper improves convergence rates and step sizes for gradient algorithms.

Deriving and applying Proximal Policy Optimization to GFlowNets for efficient training of discrete sampling policies

New method finds linear relationships across multiple data blocks using proximal gradient descent with $\ell_1$ constraint.

Optimal scaling for proximal MALA in high dimensions confirmed.

This paper accelerates TV regularization algorithms by unrolling proximal gradient descent.

We study a hybrid conditional gradient - smoothing algorithm (HCGS) for solving composite convex optimization problems which contain several terms over a bounded set. Examples of these include regularization problems with several norms as penalties and a norm constraint. HCGS extends conditional gradient methods to cas…

Paper introduces a new reinforcement learning method with improved performance.

DE-PSGLD samples from constrained distributions in a decentralized manner.

AsyB-ProxSGD parallelizes model updates and stochastic gradient descent for large models and data.

NASP uses proximal gradient descent to speed up neural architecture search.

Improved shuffling gradient methods converge faster for nonsmooth convex optimization.

New algorithm speeds up sampling from complex distributions.

We analyze Riemannian accelerated methods using a new framework.

New method improves structure learning on sparse graphs.

In this paper, we propose a new algorithm to speed-up the convergence of accelerated proximal gradient (APG) methods. In order to minimize a convex function $f(\mathbf{x})$, our algorithm introduces a simple line search step after each proximal gradient step in APG so that a biconvex function $f(θ\mathbf{x})$ is minimi…

We analyze stochastic gradient algorithms for optimizing nonconvex, nonsmooth finite-sum problems. In particular, the objective function is given by the summation of a differentiable (possibly nonconvex) component, together with a possibly non-differentiable but convex component. We propose a proximal stochastic gradie…

Stochastic proximal point algorithm with momentum converges faster and is more stable than standard methods.

A scalable system detects price anomalies in online marketplaces to improve customer experience.

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 …