Continuized Nesterov acceleration accelerates stochastic gradient descent and gossip algorithms.
problem Improving the convergence rate of stochastic gradient descent and gossip algorithms.
method Introducing a continuized variant of Nesterov acceleration, which mixes variables continuously and takes gradient steps at random times.
result The continuized Nesterov acceleration achieves convergence rates similar to Nesterov's original acceleration but with random parameters.
AGNES accelerates gradient descent with noisy gradients.
problem Minimizing smooth convex and strongly convex functions with noisy gradients.
method Generalization of Nesterov's accelerated gradient descent algorithm for noisy conditions.
result AGNES achieves acceleration for noisy gradients with a constant of proportionality up to 1.
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 …
Accelerated gradient method's stability deteriorates exponentially with steps.
problem Algorithmic stability of Nesterov's accelerated gradient method.
method Analysis of two notions of algorithmic stability for Nesterov's accelerated gradient method.
result Stability of Nesterov's accelerated method deteriorates exponentially with the number of gradient steps.
New method accelerates gradient descent on curved spaces.
problem Optimizing functions on curved Riemannian manifolds.
method Developed a novel geometric inequality to control metric distortion, enabling a Riemannian accelerated gradient method.
result Proposed the first global accelerated gradient method for Riemannian manifolds.
Accelerates MMLE using SVGD with Nesterov acceleration.
problem Maximum Marginal Likelihood Estimation optimization.
method Stein variational gradient descent with Nesterov acceleration.
result Consistently accelerates convergence across various tasks.
Stacking improves deep neural network training efficiency.
problem Improving the efficiency of training deep neural networks.
method Proposes stacking as a form of accelerated gradient descent.
result Proves stacking provides accelerated training for certain deep linear residual networks.
There is widespread sentiment that it is not possible to effectively utilize fast gradient methods (e.g. Nesterov's acceleration, conjugate gradient, heavy ball) for the purposes of stochastic optimization due to their instability and error accumulation, a notion made precise in d'Aspremont 2008 and Devolder, Glineur, …
Super-acceleration of gradient descent with momentum improves loss function minimization.
problem Minimizing loss functions in machine learning.
method Extending Nesterov acceleration by using gradients at multiple steps ahead.
result Super-acceleration of the momentum algorithm is beneficial for various loss landscapes and tasks.
Accelerates coordinate descent methods for machine learning problems.
problem Slowness of coordinate descent methods in machine learning.
method Extrapolation-based accelerated coordinate descent.
result Significant speed-up in practice compared to existing methods.
First-order methods play a central role in large-scale machine learning. Even though many variations exist, each suited to a particular problem, almost all such methods fundamentally rely on two types of algorithmic steps: gradient descent, which yields primal progress, and mirror descent, which yields dual progress. W…
Accelerates Riemannian gradient methods with extrapolation.
problem Optimizing functions on manifolds efficiently.
method Extrapolating iterates in Riemannian gradient descent.
result Achieves optimal convergence rate and computational advantage.
Two new differentially private optimization algorithms derived from accelerated methods.
problem Improving privacy in optimization algorithms while maintaining convergence rates.
method Polyak's heavy ball method and Nesterov's accelerated gradient method with differential privacy.
result The proposed algorithms outperform existing differentially private optimization methods.
A new transformer model accelerates training with optimization techniques.
problem Training deep neural networks efficiently and effectively.
method Interprets transformer layers as optimization steps, applying Nesterov acceleration.
result The new model outperforms existing models on benchmark datasets.
Proposes momentum methods for Lie groups, improving on classical algorithms.
problem Optimization on nonlinear spaces, especially Lie groups.
method Generalizes Nesterov's Accelerated Gradient method to Lie groups.
result Demonstrates faster convergence for NAG-like methods on Lie groups.
Improved optimization guarantees for deep learning models with Nesterov acceleration.
problem Optimization in non-convex deep learning landscapes.
method Analysis of Nesterov acceleration in benignly non-convex landscapes.
result Identical guarantees can be obtained in optimization problems with weak geometric assumptions, especially in overparametrized deep learning.
FedNAG improves federated learning accuracy and reduces training time.
problem Efficiency of federated learning with gradient descent.
method Nesterov Accelerated Gradient (NAG) applied to federated learning (FL) with additional momentum and model aggregation.
result FedNAG increases learning accuracy by 3-24% and reduces training time by 11-70%.
Poor (even random) starting points for learning/training/optimization are common in machine learning. In many settings, the method of Robbins and Monro (online stochastic gradient descent) is known to be optimal for good starting points, but may not be optimal for poor starting points -- indeed, for poor starting point…
We study learning properties of accelerated gradient descent methods for linear least-squares in Hilbert spaces. We analyze the implicit regularization properties of Nesterov acceleration and a variant of heavy-ball in terms of corresponding learning error bounds. Our results show that acceleration can provides faster …
Develops accelerated methods for optimization using low-dimensional projected-gradient information.
problem Optimization with low-dimensional projected-gradient information and Nesterov acceleration.
method Randomized-subspace Nesterov accelerated gradient methods for smooth convex and strongly convex optimization.
result Established accelerated oracle-complexity guarantees and unified basis for comparing sketch families.
A fast method for training linear classifiers maximizes margins.
problem Training linear classifiers with maximum margins.
method Momentum-based gradient method derived from convex dual with Nesterov acceleration.
result Exponentially faster convergence rate compared to standard methods.
Nesterov's momentum trick is famously known for accelerating gradient descent, and has been proven useful in building fast iterative algorithms. However, in the stochastic setting, counterexamples exist and prevent Nesterov's momentum from providing similar acceleration, even if the underlying problem is convex and fin…
Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceleration method have been proposed, it is not yet clear what is the natural scope of the acceleration concept. In this paper, we study accelera…
Nesterov SGD is widely used for training modern neural networks and other machine learning models. Yet, its advantages over SGD have not been theoretically clarified. Indeed, as we show in our paper, both theoretically and empirically, Nesterov SGD with any parameter selection does not in general provide acceleration o…
Optimizes deep learning pipelines with novel algorithms for smooth and non-smooth functions.
problem Optimizing deep learning pipelines for smooth and non-smooth functions.
method Provided matching lower and upper bounds for smooth convex and non-convex functions, and developed PPRS for non-smooth convex functions.
result PPRS achieves near-linear speed-up and convergence time for non-smooth non-convex problems.
Study accelerates optimization methods in non-convex problems, but doesn't improve the algorithm's performance.
problem Understanding the behavior of momentum-based acceleration methods in non-convex, high-dimensional landscapes.
method Used dynamical mean field theory to describe the average dynamics of heavy-ball momentum and Nesterov acceleration in a non-convex model.
result Accelerated dynamics but did not improve the algorithm's performance with respect to gradient descent.
HF-opt uses Hamiltonian dynamics to optimize functions, achieving accelerated rates with randomized integration time.
problem Optimizing functions efficiently and accelerating convergence rates.
method Randomized Hamiltonian flow (RHF) with accelerated convergence rates.
result RHGD achieves accelerated convergence rates similar to Nesterov's AGD.
Study on Nesterov's method in stochastic settings, revealing divergence under certain conditions.
problem Understanding Nesterov's method in stochastic settings, especially finite-sum.
method Analysis of Nesterov's accelerated gradient method in stochastic and finite-sum settings.
result Nesterov's method may diverge in finite-sum settings without additional conditions.
Momentum based stochastic gradient methods such as heavy ball (HB) and Nesterov's accelerated gradient descent (NAG) method are widely used in practice for training deep networks and other supervised learning models, as they often provide significant improvements over stochastic gradient descent (SGD). Rigorously speak…
New methods accelerate gradient descent for convex and strongly convex functions.
problem Improving convergence rates of gradient-based optimization methods.
method Formulated two classes of first-order algorithms with Lyapunov analyses and Hamiltonian assisted gradient method.
result Achieved accelerated convergence rates matching Nesterov's methods in strongly and general convex settings.
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 …
We formulate gradient-based Markov chain Monte Carlo (MCMC) sampling as optimization on the space of probability measures, with Kullback-Leibler (KL) divergence as the objective functional. We show that an underdamped form of the Langevin algorithm performs accelerated gradient descent in this metric. To characterize t…
Gradient tree boosting is a prediction algorithm that sequentially produces a model in the form of linear combinations of decision trees, by solving an infinite-dimensional optimization problem. We combine gradient boosting and Nesterov's accelerated descent to design a new algorithm, which we call AGB (for Accelerated…
ASVGD accelerates SVGD for efficient sampling.
problem Slow SVGD in high-dimensional sampling.
method Accelerated gradient flow in a metric space of probability densities, using Nesterov's method and momentum-based updates.
result ASVGD outperforms SVGD and other methods in sampling efficiency.
Accelerated gradient (AG) methods are breakthroughs in convex optimization, improving the convergence rate of the gradient descent method for optimization with smooth functions. However, the analysis of AG methods for non-convex optimization is still limited. It remains an open question whether AG methods from convex o…
A new algorithm improves convergence rates for convex optimization problems.
problem Convex optimization problems with finite-sum structure.
method Nesterov Accelerated Shuffling Gradient (NASG) integrating Nesterov's acceleration with different shuffling schemes.
result Improved convergence rate of O(1/T) for unified shuffling schemes.
New algorithm AG-OG optimizes separable convex-concave problems efficiently.
problem Efficiently solving separable convex-concave minimax optimization problems.
method Leverages Nesterov acceleration and optimistic gradient on component and coupling parts of the problem.
result Achieves optimal convergence rate for various settings including bilinearly coupled problems.
Accelerated optimization methods improve robustness and privacy in estimation.
problem Improving robustness and privacy in estimation methods.
method Accelerated gradient methods based on Frank-Wolfe and projected gradient descent, with tailored learning rates and Nesterov's momentum.
result Reduction in iteration complexity, leading to stronger statistical guarantees.
Nesterov's extrapolation improves convergence in nonsmooth optimization.
problem Improving convergence rate in nonsmooth convex optimization.
method Nesterov's extrapolation applied to projected subgradient methods.
result Nesterov's extrapolation optimizes individual convergence for nonsmooth problems.
In this paper, we study the stochastic gradient descent (SGD) method for the nonconvex nonsmooth optimization, and propose an accelerated SGD method by combining the variance reduction technique with Nesterov's extrapolation technique. Moreover, based on the local error bound condition, we establish the linear converge…
We derive a second-order ordinary differential equation (ODE) which is the limit of Nesterov's accelerated gradient method. This ODE exhibits approximate equivalence to Nesterov's scheme and thus can serve as a tool for analysis. We show that the continuous time ODE allows for a better understanding of Nesterov's schem…
Adapts SGD to noise and problem specifics for faster convergence.
problem Minimizing smooth, strongly-convex functions with varying noise and problem constants.
method Adaptive SGD with exponentially decreasing step-sizes, Nesterov acceleration, and stochastic line-search.
result Achieves near-optimal convergence rates without knowing noise or problem specifics.
The development of machine learning is promoting the search for fast and stable minimization algorithms. To this end, we suggest a change in the current gradient descent methods that should speed up the motion in flat regions and slow it down in steep directions of the function to minimize. It is based on a "power grad…
This research accelerates sampling methods using Nesterov's Acceleration.
problem Improving sampling efficiency in MCMC methods.
method Developed a Hessian-Free High-Resolution ODE reformulation of NAG-SC, injected noise, and discretized the diffusion process.
result Quantified acceleration beyond underdamped Langevin in W2 distance for log-strongly-concave targets. This paper improves NAQ method for faster convergence on Tensorflow.
problem Non-convex optimization problems.
method Modified Nesterov's Accelerated Quasi-Newton (NAQ) method on Tensorflow.
result mNAQ converges better and faster than first and second order optimizers.
Improved training of large-scale neural networks with reduced variance noise.
problem Training large-scale neural networks with high variance noise.
method Stochastic variance reduced Nesterov's Accelerated Quasi-Newton method (SVR-NAQ).
result Improved performance compared to conventional methods on benchmark problems.
New algorithms optimize decentralized convex optimization with near optimal communication and computation.
problem Decentralized convex optimization in large-scale machine learning and sensor networks.
method Novel algorithms combining Nesterov's acceleration, multi-consensus, and gradient-tracking.
result Achieves optimal computation and near optimal communication complexity, matching lower bounds.
Derives new optimization methods using variational integrators.
problem Optimization methods in machine learning.
method Variational integrators and principles of Hamilton and Lagrange-d'Alembert.
result Derives two families of optimization methods, including Nesterov's accelerated gradient method.