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.

168,786 papers · 148 categories

Trend · papers per month

7.6%15.2%22.9%30.5% · Jun 202019922001200920172026
48 results for stepsize optimization

Adaptive-stepsize MCMC sampling inspired by Adam optimizer.

problem Improving numerical stability and convergence speed in MCMC sampling.
method Time-rescaled Langevin dynamics with an auxiliary relaxation equation and adaptive stepsize control.
result Automatic stepsize control improves accuracy and stability in numerical experiments.

Enhanced ROOT-SGD optimizes stochastic optimization with diminishing stepsizes.

problem Improving statistical efficiency in stochastic optimization.
method Integrates a diminishing stepsize strategy into ROOT-SGD.
result Achieves optimal convergence rates with improved stability and precision.

This work accelerates gradient descent with anytime convergence guarantees.

problem Improving the convergence rate of gradient descent methods.
method Proposes a stepsize schedule for gradient descent that achieves anytime convergence rates.
result Gradient descent can achieve convergence rates of O(T1.119)O(T^{-1.119}) for any stopping time TT.

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.

Last SGD iterate bounds for overparameterized linear regression.

problem Analyzing the last iterate risk bounds of SGD with decaying stepsize for overparameterized linear regression.
method Problem-dependent analysis of last iterate risk bounds of SGD with geometrically decaying stepsize.
result Proved nearly matching upper and lower bounds on the excess risk for last iterate SGD with geometrically decaying stepsize.

Study Q-learning with constant stepsize, proving convergence and bias, and applying extrapolation.

problem Understanding and optimizing Q-learning with constant stepsize.
method Connecting Q-learning to a Markov chain, proving distributional convergence and bias, applying Richardson-Romberg extrapolation.
result Explicit expression for the linear coefficient of the asymptotic bias and improvement of RR extrapolation method.

Approximate dynamic programming (ADP) has proven itself in a wide range of applications spanning large-scale transportation problems, health care, revenue management, and energy systems. The design of effective ADP algorithms has many dimensions, but one crucial factor is the stepsize rule used to update a value functi…

2014-07-10abs ↗pdf ↗

This work analyzes QQ-learning with adaptive stepsizes for finite-time convergence.

problem Finite-time convergence analysis for average-reward QQ-learning with adaptive stepsizes.
method Adaptive stepsizes as local clocks, time-inhomogeneous Markovian reformulation, almost-sure time-varying bounds, conditioning arguments, and Markov chain concentration inequalities.
result Convergence rates of ildeO(1/k) ilde{\mathcal{O}}(1/k) for mean-square and pointwise mean-square convergence.

MARINA-P improves non-smooth federated optimization with adaptive stepsizes.

problem Non-smooth federated optimization in machine learning applications.
method Extends EF21-P and MARINA-P to non-smooth convex setting, proving optimal convergence rate and communication complexity bounds.
result MARINA-P achieves O(1/T)O(1/\sqrt{T}) convergence rate and communication complexity matching classical subgradient methods.

New adaptive stepsize method for stochastic approximation converges to target point.

problem Finding optimal step sizes for stochastic approximation algorithms.
method Adaptive block-coordinate stepsizes using online estimates of second moment.
result New method converges almost surely to a small neighborhood of the target point.

We propose a stepsize adaptation scheme for stochastic gradient descent. It operates directly with the loss function and rescales the gradient in order to make fixed predicted progress on the loss. We demonstrate its capabilities by conclusively improving the performance of Adam and Momentum optimizers. The enhanced op…

2018-02-14abs ↗pdf ↗

AdaSDBO solves decentralized bilevel optimization without problem parameters, achieving competitive performance.

problem Decentralized bilevel optimization problems without known parameters.
method AdaSDBO, a fully problem-parameter-free algorithm with adaptive stepsizes.
result AdaSDBO achieves a convergence rate of $\widetilde{\mathcal{O}}\left(\frac{1}{T} ight)$, matching state-of-the-art methods up to polylogarithmic factors.

Proposes a new metric selection for VM-PG with improved convergence.

problem Improves convergence of VM-PG methods for ill-conditioned problems.
method Diagonal Barzilai-Borwein stepsize for adaptive metric selection.
result Improved convergence results for ill-conditioned problems.

Cyclic and randomized stepsizes can lead to heavier tails in SGD, improving generalization.

problem Understanding when and why cyclic and randomized stepsizes outperform constant stepsize in SGD.
method Examined a general class of Markovian stepsizes, focusing on their tail-index behavior.
result Markovian stepsizes can achieve heavier tails, improving generalization over constant stepsize.

An algorithm is presented for momentum gradient descent optimization based on the first-order differential equation of the Newtonian dynamics. The fictitious mass is introduced to the dynamics of momentum for regularizing the adaptive stepsize of each individual parameter. The dynamic relaxation is adapted for stochast…

2018-05-13abs ↗pdf ↗

Improves posterior approximation speed for Dirichlet process mixture models.

problem Inefficiency of stochastic variational inference in large datasets.
method Uses stochastic gradient ascent with adaptive stepsize optimization.
result Adaptive stepsize improves speed and performance of posterior approximation.

Gradient descent converges with arbitrary stepsize for separable data under Fenchel-Young losses.

problem Understanding the conditions under which gradient descent converges with arbitrary stepsize.
method Using Fenchel-Young losses and leveraging the classical perceptron argument to derive convergence rates.
result GD converges with arbitrary stepsize for a majority of Fenchel-Young losses, with better rates for specific loss functions.

New PG methods tackle nonconvex optimization with auto-conditioned stepsizes.

problem Optimizing nonconvex functions over convex sets.
method Auto-conditioned projected gradient (AC-PG) methods and stochastic variants.
result Achieved optimal iteration complexity for finding approximate stationary points.

Large GD stepsizes improve margins and speed up training for non-homogeneous networks.

problem Training efficiency and margin improvement in non-homogeneous two-layer networks.
method Investigation of two distinct phases in GD training, showing margin growth and empirical risk decrease.
result Large GD stepsizes lead to faster convergence and improved margins in non-homogeneous networks.

New analysis reveals batch size effects on stochastic conditional gradient methods.

problem Understanding the role of batch size in stochastic conditional gradient methods.
method Deriving a new analysis focusing on momentum-based stochastic conditional gradient algorithms (e.g., Scion).
result Increasing batch size initially improves optimization accuracy but can degrade performance beyond a critical threshold.

New algorithm accelerates optimization on Riemannian manifolds, including Wasserstein space.

problem Accelerating optimization methods in Riemannian geometry.
method Dynamic stepsize algorithms on Riemannian manifolds with specific vector transport.
result First provable accelerated gradient method in Wasserstein space.

Study on GD and SGD over diagonal networks, focusing on stepsizes and regularisation.

problem Understanding the impact of stochasticity and large stepsizes on gradient descent and SGD solutions.
method Investigation of GD and SGD over diagonal linear networks with macroscopic stepsizes, proving convergence and characterizing solutions.
result Large stepsizes consistently benefit SGD for sparse regression problems, but can hinder GD recovery of sparse solutions, especially in the edge of stability regime.

Paper examines constant stepsize in LSA for Markovian data inference.

problem Improving statistical inference with constant stepsize in LSA for Markovian data.
method Established CLT, used averaged LSA iterates, applied Richardson-Romberg extrapolation.
result Constant stepsize leads to better CI coverage, especially with limited data.

Paper analyzes convergence of GDA for nonconvex-nonconcave minimax problems.

problem Understanding convergence of GDA for nonconvex-nonconcave minimax problems.
method Local convergence analysis of GDA with stepsize ratio Θ(κ).
result Stepsize ratio of Θ(κ) is necessary and sufficient for local convergence of GDA to a Stackelberg Equilibrium.

AdaGrad fails to adapt to Hölder-smoothness in composite optimization problems.

problem AdaGrad's convergence rate is suboptimal for composite objectives.
method Exhibited a simple one-dimensional convex problem to highlight AdaGrad's limitations.
result AdaGrad does not achieve the classical convergence rate for Hölder-smooth objectives.

NSGD-M optimizes machine learning models without hyperparameter tuning, even under relaxed smoothness.

problem Training machine learning models with optimal complexity under relaxed smoothness assumptions.
method Normalized Stochastic Gradient Descent with Momentum (NSGD-M) without stepsize tuning.
result NSGD-M achieves nearly optimal complexity without prior knowledge of problem parameters.

Improved SGD with AdaGrad stepsizes adapts to unknown parameters and unbounded gradients.

problem Adaptive optimization with unknown parameters and unbounded gradients.
method Stochastic Gradient Descent with AdaGrad stepsizes, without assuming problem parameters or strong global Lipschitz conditions.
result Sharp rates of convergence in both low-noise and high-noise regimes, supporting an affine variance noise model.

Study on nonsmooth contractive SA with constant stepsize and Q-learning.

problem Understanding convergence and bias in nonsmooth contractive SA with different noise types.
method Proposed prelimit coupling technique for steady-state convergence and derived asymptotic bias.
result Asymptotic bias of nonsmooth SA is proportional to the square root of the stepsize.

We propose a general yet simple theorem describing the convergence of SGD under the arbitrary sampling paradigm. Our theorem describes the convergence of an infinite array of variants of SGD, each of which is associated with a specific probability law governing the data selection rule used to form mini-batches. This is…

2019-01-27abs ↗pdf ↗

Adaptive stepsizing improves sampling in Bayesian neural networks.

problem Scalable sampling of posterior distributions in Bayesian neural networks.
method SA-SGLD, employing time rescaling to adapt stepsize dynamically.
result SA-SGLD achieves more accurate posterior sampling than SGLD.

Proposes a Quasi-Newton trust region method for policy optimization in reinforcement learning.

problem Lack of stepsize selection criterion and slow convergence in gradient descent for policy optimization.
method Uses a trust region method with Quasi-Newton approximation for the Hessian.
result Demonstrates improved performance and efficiency in continuous control tasks.

Study Whittle index learning algorithms for restless bandits with constant stepsizes.

problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.

Adaptive gradient methods such as AdaGrad and its variants update the stepsize in stochastic gradient descent on the fly according to the gradients received along the way; such methods have gained widespread use in large-scale optimization for their ability to converge robustly, without the need to fine-tune the stepsi…

2018-06-05abs ↗pdf ↗

Study on bias and extrapolation in LSA with Markovian data, showing bias reduction with Richardson-Romberg extrapolation.

problem Bias in LSA with constant stepsizes and Markovian data.
method Viewing LSA as a Markov chain, proving convergence and bias expansion, and applying Richardson-Romberg extrapolation.
result Bias is proportional to the stepsize up to higher order terms, and Richardson-Romberg extrapolation reduces the bias.