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.

168,657 papers · 148 categories

Trend · papers per month

2595177761,034 · Jun 202019922001200920172026
48 results for convergence improvement

Improved convergence of fixed-point methods using windowed Anderson acceleration.

problem Improving convergence of fixed-point methods for symmetric operators.
method Windowed Anderson acceleration for symmetric fixed-point iterations.
result Windowed Anderson acceleration improves convergence over standard fixed-point methods.

SIBRE boosts reinforcement learning convergence by rewarding improvement over past performance.

problem Improving the rate of convergence in reinforcement learning.
method SIBRE is a reward shaping approach that rewards improvement over the agent's own past performance.
result SIBRE converges faster and more stably to the optimal policy compared to baseline RL algorithms.

TOLD++ improves convergence of diffusion models by critically damping the forward transition matrix.

problem Improving the convergence of Denoising Diffusion Probabilistic Models.
method Critically damping the Third-Order Langevin Dynamics (TOLD) forward transition matrix using eigen-analysis.
result TOLD++ converges faster than TOLD, verified on toy and real datasets.

Paper analyzes convergence rate of noisy Bayesian Optimization with Expected Improvement.

problem Theoretical convergence behaviors and rates of Expected Improvement (EI) in Bayesian optimization.
method Analyzes Expected Improvement (EI) under Gaussian process (GP) prior assumption, considering noisy observations.
result Established asymptotic error bound and rate for GP-EI with noisy observations.

SAIL-RevKL improves SAIL's convergence by regularizing the objective function.

problem Convergence of self-improving online LLM alignment algorithms.
method Proposed SAIL-RevKL, a regularized objective function to improve optimization landscape.
result Proved SAIL-RevKL satisfies the Polyak-Lojasiewicz (PL) condition with near-linear sample complexity.

Improved convergence speed of principal component analysis through modified learning rules.

problem Slow convergence for covariance matrices with close eigenvalues.
method Introduced an additional term to the objective function to mitigate convergence issues.
result Significantly improved convergence speed confirmed through simulations.

Randomized block-diagonal preconditioning improves parallel learning convergence.

problem Improving convergence of gradient-based optimization methods in parallel settings.
method Randomization of coordinates during optimization to repartition tasks.
result Randomization significantly improves convergence of block-diagonal preconditioned methods.

This paper improves convergence guarantees for SGD algorithms in non-convex smooth functions.

problem Theoretical convergence properties of SGD algorithms for non-convex smooth functions.
method Analysis of SGD algorithms with arbitrary data ordering for non-convex smooth functions.
result Enhanced convergence guarantees for incremental gradient and single shuffle SGD, improving the optimization term of convergence guarantee.

CEI achieves convergence rates for constrained Bayesian optimization.

problem Constrained Bayesian optimization with theoretical convergence rates.
method Analyzing simple regret upper bound for CEI in RKHS and Gaussian process settings.
result CEI achieves convergence rates of t12logd+12(t)t^{-\frac{1}{2}}\log^{\frac{d+1}{2}}(t) and tν2ν+dlogν2ν+d(t)t^{\frac{-ν}{2ν+d}} \log^{\fracν{2ν+d}}(t) for squared exponential and Matérn kernels, respectively.

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.

Improved KL bounds and Wasserstein guarantees for diffusion flow matching under minimal conditions.

problem Theoretical convergence properties of Brownian motion based diffusion flow matching.
method Refined analysis under Kullback-Leibler and 2-Wasserstein distances.
result State-of-the-art scaling in KL convergence bounds under minimal conditions.

The paper improves convergence rates of curvature approximations using Regge elements.

problem Improving convergence rates of curvature approximations using Regge elements.
method Investigates the interplay between polynomial degree of curvature lifting and metric tensor degree in Regge finite element space.
result Higher convergence rates are achieved by reducing the polynomial degree of curvature lifting and using linear Regge elements.

FastAdaBelief improves convergence rate of AdaBelief by exploiting strong convexity.

problem Improving convergence rate of AdaBelief without sacrificing generalization ability.
method Designing FastAdaBelief that adjusts step size considering strong convexity.
result Proves O(logT)O(\log T) regret bound for FastAdaBelief.

Improved BO algorithms reduce prediction error under Gaussian noise.

problem Reducing prediction error in Bayesian optimization with Gaussian noise.
method Established new prediction error bounds for Gaussian process under frequentist setting.
result Proved improved convergence rates of cumulative regret for GP-UCB and GP-TS.

Improved neural network convergence with causal Bayesian modeling in retail performance.

problem Improving neural network convergence in retail performance models.
method Causal Bayesian neural network implementation, removal of weakest SEM path, Flipout layers, Vadam optimizer.
result Neural network convergence improved with removal of the weakest SEM path.

Enhances deep learning by boosting generalization and convergence.

problem Improving generalization and convergence in deep learning models.
method Implicit Regularization Enhancement (IRE) framework that decouples flat and sharp directions.
result IRE consistently improves generalization performance across various deep learning tasks and models.

Improved convergence for actor-critic algorithms in MDPs.

problem Global convergence analysis for actor-critic algorithms in MDPs.
method Introduced an analytical framework to handle complex recursions, established convergence to ε-close globally optimal policy with improved sample complexity.
result Converges to ε-close globally optimal policy with sample complexity of O(ε^(-3)) compared to O(ε^(-2)) for ε-close stationary policy.

We propose the stochastic average gradient (SAG) method for optimizing the sum of a finite number of smooth convex functions. Like stochastic gradient (SG) methods, the SAG method's iteration cost is independent of the number of terms in the sum. However, by incorporating a memory of previous gradient values the SAG me…

2013-09-10abs ↗pdf ↗

Improved Frank-Wolfe algorithm for generalized self-concordant functions converges quickly.

problem Efficiently solving learning problems with generalized self-concordant objectives.
method Simple Frank-Wolfe variant with open-loop step size strategy γt=2/(t+2)γ_t = 2/(t+2).
result Achieves O(1/t)\mathcal{O}(1/t) convergence rate for primal and Frank-Wolfe gaps.

Improved SEG method converges to Nash equilibrium in bilinear games.

problem Stochastic bilinear minimax optimization problem
method Stochastic ExtraGradient (SEG) method with constant step size, iteration averaging, and scheduled restarting.
result Provable convergence to Nash equilibrium under standard settings, optimal convergence rate in interpolation setting.

In this paper, we present a probability one convergence proof, under suitable conditions, of a certain class of actor-critic algorithms for finding approximate solutions to entropy-regularized MDPs using the machinery of stochastic approximation. To obtain this overall result, we prove the convergence of policy evaluat…

2019-07-13abs ↗pdf ↗

New analysis improves convergence guarantees for diffusion-based samplers in Wasserstein distance.

problem Improving convergence guarantees for diffusion-based generative models.
method Simple framework to analyze discretization, initialization, and score estimation errors.
result First Wasserstein convergence bound for the Heun sampler and improved results for Euler sampler.

New HMC method uses asymmetrical momentum distributions and improves performance.

problem Rigorous convergence guarantees for HMC with Gaussian momentum distributions.
method New convergence analysis for HMC with general asymmetrical momentum distributions, proposing AD-HMC.
result AD-HMC exhibits geometric convergence in Wasserstein distance under certain conditions.

Semi-supervised EM improves convergence rate with labeled samples.

problem Improving convergence rate in EM algorithm with labeled and unlabeled data.
method Analysis of semi-supervised EM algorithm for Gaussian mixture models.
result Labeled samples significantly improve the convergence rate for the EM algorithm.

This paper improves inverse problem solving with weakly convex regularisers and proves convergence.

problem Improving solution methods for inverse problems.
method Generalised formulation of convergent regularisation using weakly convex regularisers, and proof of convergence for primal-dual hybrid gradient method.
result Proves convergence of primal-dual hybrid gradient method for variational problems and shows improved performance with IWCNNs.

Improved convergence rates for Stein Variational Gradient Descent in finite-particle settings.

problem Improving convergence rates for Stein Variational Gradient Descent in finite-particle settings.
method Analyzing the time derivative of relative entropy and splitting it into dominant and smaller parts.
result Finite-particle convergence rates of order 1/\sqrt{N} for Kernelized Stein Discrepancy and Wasserstein-2 metrics.

Improved shuffling gradient methods converge faster for nonsmooth convex optimization.

problem Improving convergence rates for nonsmooth convex optimization problems.
method Analysis of shuffling gradient methods, focusing on Random Reshuffle and Single Shuffle strategies.
result Shuffling gradient methods, particularly Random Reshuffle and Single Shuffle, converge faster than Proximal Gradient Descent for nonsmooth convex optimization.

Improved algorithm for optimal stopping problems reduces runtime.

problem Optimal stopping problems with infinite time horizon and random discounting.
method Flexible forward improvement iteration with a variable look-ahead distance.
result The new algorithm converges and can significantly reduce runtime.

Improved SDE-BNN model reduces NFEs and accelerates convergence.

problem High computational cost and convergence instability in SDE-BNNs.
method Nesterov's Accelerated Gradient (NAG) method integrated into SDE-BNN framework.
result Significantly reduced number of function evaluations (NFEs) and improved predictive accuracy.

A new simulation method for Volterra processes improves convergence for rough kernels.

problem Simulating Volterra processes with singular kernels.
method iVi (integrated Volterra implicit) scheme based on Inverse Gaussian distribution.
result The iVi scheme achieves weak convergence with few time steps, especially for rough kernels.

Efficient global optimization is the problem of minimizing an unknown function f, using as few evaluations f(x) as possible. It can be considered as a continuum-armed bandit problem, with noiseless data and simple regret. Expected improvement is perhaps the most popular method for solving this problem; the algorithm pe…

2011-01-18abs ↗pdf ↗