Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

4387130173 · Jun 202019922001200920172026
48 results for constant acceleration

New algorithms accelerate model-based optimization for stochastic problems.

problem Optimizing model-based stochastic optimization problems efficiently.
method Proposed new model-based algorithms with acceleration and minibatch techniques.
result Non-asymptotic convergence guarantees with linear speedup in minibatch size.

We show that accelerated gradient descent, averaged gradient descent and the heavy-ball method for non-strongly-convex problems may be reformulated as constant parameter second-order difference equation algorithms, where stability of the system is equivalent to convergence at rate O(1/n 2), where n is the number of ite…

2015-04-07abs ↗pdf ↗

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.

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.

Stochastic gradient decent~(SGD) and its variants, including some accelerated variants, have become popular for training in machine learning. However, in all existing SGD and its variants, the sample size in each iteration~(epoch) of training is the same as the size of the full training set. In this paper, we propose a…

2019-06-11abs ↗pdf ↗

Large stepsizes can accelerate gradient descent for logistic regression.

problem Optimizing logistic regression with large stepsizes.
method Gradient descent with large stepsize for 2\ell_2-regularized logistic regression.
result Large stepsizes can achieve O~(κ)\widetilde{\mathcal{O}}(\sqrtκ) convergence, improving over O~(κ)\widetilde{\mathcal{O}}(\sqrtκ) from classical theory.

LightOn OPUs accelerate randomized numerical linear algebra, reducing computational costs.

problem Computational bottleneck in randomization step for large-scale linear algebra.
method Near constant-time linear random projections from LightOn OPUs.
result Significant acceleration of RandNLA algorithms with negligible precision loss.

ASVGD accelerates SVGD for efficient sampling from Gaussian targets.

problem Efficient sampling from Gaussian distributions using SVGD.
method Accelerated gradient flow in a metric space of probability densities, including momentum and Wasserstein regularization.
result ASVGD achieves optimal convergence rate for Gaussian targets, independent of covariance.

New method accelerates optimization in fixed time, improving convergence rates.

problem Optimization in large-scale data-driven problems.
method Gradient-based optimization framework with fixed-time stable dynamical systems.
result Achieves convergence to the optimizer in a fixed number of iterations, independent of initialization.

Seesaw optimizes training by balancing learning rate and batch size, accelerating model pretraining.

problem Optimizing training efficiency for large language models with adaptive optimizers.
method Develops a principled framework for batch-size scheduling, introducing Seesaw which multiplies learning rate by 1/√2 and doubles batch size.
result Empirically, Seesaw reduces wall-clock time by approximately 36% compared to cosine decay, matching theoretical limits.

New algorithms solve monotone inclusions and convex-concave minimax problems.

problem Solving maximally monotone equations and inclusions.
method Developed new accelerated algorithms based on Halpern-type fixed-point iteration and Popov's past extra-gradient method.
result Achieved O(1/k)\mathcal{O}(1/k) convergence rates for various problems.

New algorithms find near-stationary points in convex optimization.

problem Finding near-stationary points in convex optimization.
method Memory-saving variant of OGM-G, accelerated SVRG, adaptively regularized accelerated SVRG.
result Schemes achieve fast rates for minimizing gradient norm and function value.

Boosted Frank-Wolfe accelerates optimization for nonconvex problems.

problem Optimizing nonconvex and quasar-convex objectives efficiently.
method Developed a novel step size strategy for stochastic Frank-Wolfe, extending it to various gradient estimators.
result Boosted Frank-Wolfe achieves faster convergence rates than non-boosted Frank-Wolfe.

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

problem Improving convergence and stability of stochastic optimization methods.
method Developed and analyzed the convergence and stability of the stochastic proximal point algorithm with momentum (SPPAM).
result SPPAM converges faster and is more stable than standard stochastic proximal point algorithm (SPPA) and stochastic gradient descent with momentum (SGDM).

We study the Bondi-Sachs rockets with nonzero cosmological constant. We observe that the acceleration of the systems arises naturally in the asymptotic symmetries of (anti-) de Sitter spacetimes. Assuming the validity of the concepts of energy and mass previously introduced in asymptotically flat spacetimes, we find th…

2011-05-17abs ↗pdf ↗

A new algorithm solves nonnegative least squares faster with nonnegative data.

problem Nonnegative least squares problems with nonnegative data.
method Primal-dual perspective accelerated algorithm with adaptive restart.
result Oracle complexity independent of matrix constants, solvable to multiplicative error.

We propose a new stochastic coordinate descent method for minimizing the sum of convex functions each of which depends on a small number of coordinates only. Our method (APPROX) is simultaneously Accelerated, Parallel and PROXimal; this is the first time such a method is proposed. In the special case when the number of…

2013-12-20abs ↗pdf ↗

Improved sampling guarantees for underdamped Langevin Monte Carlo without restrictive assumptions.

problem Sampling from unnormalized densities with improved guarantees and acceleration.
method Novel analysis relaxing assumptions on log-Sobolev inequality and Hessian smoothness, using Rényi discretization bounds.
result First KL divergence guarantees for ULMC without Hessian smoothness under strong log-concavity.

We introduce a generic scheme to solve nonconvex optimization problems using gradient-based algorithms originally designed for minimizing convex functions. Even though these methods may originally require convexity to operate, the proposed approach allows one to use them on weakly convex objectives, which covers a larg…

2017-03-31abs ↗pdf ↗

In this paper, we provide near-optimal accelerated first-order methods for minimizing a broad class of smooth nonconvex functions that are strictly unimodal on all lines through a minimizer. This function class, which we call the class of smooth quasar-convex functions, is parameterized by a constant γ(0,1]γ\in (0,1], wher…

2019-06-27abs ↗pdf ↗

HALO uses local Lipschitz constants to optimize functions efficiently.

problem Efficiently solving global optimization problems with complex objective functions.
method Hybrid Adaptive Lipschizian Optimization (HALO) algorithm that estimates local Lipschitz constants and balances global and local information.
result HALO outperforms other global optimization algorithms on numerous test functions.

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.

Consistency models accelerate generation with theoretical guarantees.

problem Empirical success of consistency models without theoretical justification.
method Theoretical analysis of consistency models mapping inputs to arbitrary points.
result Achieve KL divergence of order O(ε2) O(\varepsilon^2) with $ O\left(\log\left(\frac{d}{\varepsilon} ight) ight) $ iterations.

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.

PF-LaCG removes the need for knowing smoothness and strong convexity parameters for locally accelerated CG.

problem Locally accelerated CG requires knowledge of smoothness and strong convexity parameters.
method Parameter-Free Locally Accelerated CG (PF-LaCG) algorithm.
result PF-LaCG achieves local acceleration without requiring knowledge of smoothness and strong convexity parameters.