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

92184276368 · Jun 202019922001200920172026
48 results for gradient preconditioning

Preconditioned non-convex gradient descent improves noisy matrix estimation.

problem Estimating low-rank matrices from noisy measurements.
method Preconditioned non-convex gradient descent for noisy measurements.
result Preconditioned method converges to minimax optimal estimate at a linear rate.

PolarGrad optimizes deep learning models by considering matrix structure, outperforming Adam and Muon.

problem Efficient optimization of large-scale neural networks and language models.
method A unifying framework for analyzing matrix-aware preconditioned methods, including PolarGrad.
result PolarGrad outperforms Adam and Muon in various tasks.

Preconditioned gradient methods are among the most general and powerful tools in optimization. However, preconditioning requires storing and manipulating prohibitively large matrices. We describe and analyze a new structure-aware preconditioning algorithm, called Shampoo, for stochastic optimization over tensor spaces.…

2018-02-26abs ↗pdf ↗

Gradient-based MCMC for discrete spaces improves sampling performance.

problem Sampling in discrete spaces using traditional methods is challenging.
method Introduced new discrete Metropolis-Hastings samplers inspired by MALA, with a novel preconditioning technique.
result Demonstrated strong empirical performance across various challenging sampling problems.

Improved convergence for overparameterized low-rank matrix sensing.

problem Overparameterized low-rank matrix sensing with unknown rank and ill-conditioning.
method ScaledGD(λλ) - preconditioned gradient descent method.
result ScaledGD(λλ) converges at a constant linear rate after a logarithmic number of iterations.

We provide an online convex optimization algorithm with regret that interpolates between the regret of an algorithm using an optimal preconditioning matrix and one using a diagonal preconditioning matrix. Our regret bound is never worse than that obtained by diagonal preconditioning, and in certain setting even surpass…

2019-05-29abs ↗pdf ↗

Stochastic Gradient Langevin Dynamics infuses isotropic gradient noise to SGD to help navigate pathological curvature in the loss landscape for deep networks. Isotropic nature of the noise leads to poor scaling, and adaptive methods based on higher order curvature information such as Fisher Scoring have been proposed t…

2019-06-10abs ↗pdf ↗

Dual Space Preconditioning speeds up gradient descent in overparameterized models.

problem Improving convergence of gradient descent in overparameterized linear models.
method Introducing a novel preconditioner of the form ablaK abla K for convex KK and applying it to overparameterized linear models.
result The iterates of the preconditioned gradient descent converge to a solution W{W}_{\infty} satisfying XW=Y{X}{W}_{\infty} = {Y}.

Stochastic gradient descent (SGD) still is the workhorse for many practical problems. However, it converges slow, and can be difficult to tune. It is possible to precondition SGD to accelerate its convergence remarkably. But many attempts in this direction either aim at solving specialized problems, or result in signif…

2015-12-14abs ↗pdf ↗

The computational and storage complexity of kernel machines presents the primary barrier to their scaling to large, modern, datasets. A common way to tackle the scalability issue is to use the conjugate gradient algorithm, which relieves the constraints on both storage (the kernel matrix need not be stored) and computa…

2016-02-22abs ↗pdf ↗

Stochastic Gradient Descent improved for various Hilbert scales and misspecified models.

problem Understanding and optimizing SGD in Hilbert scales for machine learning.
method Extending SGD analysis to Hilbert scales, including Sobolev and Diffusion spaces, and showing the effects of smoothness and preconditioning.
result Violation of smoothness assumption affects learning rate; preconditioning in Hilbert scales reduces the number of iterations for misspecified models.

Bayesian sparse learning method improves deep neural network efficiency.

problem Sparse learning in deep neural networks with complex geometry.
method Preconditioned stochastic gradient Langevin Dynamics (PSGLD) for sampling and adaptive optimization of hyperparameters.
result The proposed algorithm achieves asymptotic convergence with controlled bias.

TDprop uses Jacobi preconditioning to improve adaptive optimizers in Deep RL.

problem Improving performance of adaptive optimizers in Deep RL.
method TDprop computes per-parameter learning rates based on Jacobi preconditioning of the TD update rule.
result TDprop matches or exceeds Adam's performance in Deep RL experiments, suggesting Jacobi preconditioning can improve adaptive methods.

Standard gradient descent methods are susceptible to a range of issues that can impede training, such as high correlations and different scaling in parameter space.These difficulties can be addressed by second-order approaches that apply a pre-conditioning matrix to the gradient to improve convergence. Unfortunately, s…

2019-10-18abs ↗pdf ↗

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.

Gradient descent with preconditioning finds global optima in overparameterized nonconvex factorization.

problem Finding global optima in nonconvex Burer-Monteiro factorization.
method Preconditioned gradient descent for overparameterized nonconvex function minimization.
result Gradient descent with preconditioning achieves linear convergence in the overparameterized case.

Unified framework for understanding and optimizing training acceleration.

problem Challenges in optimizing training with regularization and acceleration techniques.
method Explains how AdaGrad, RMSProp, and Adam accelerate training, and derives a generalization for L1L_1-regularization.
result Derives a unified mathematical framework for understanding and optimizing training acceleration.

APGD algorithm efficiently recovers over-parameterized matrices from noisy measurements.

problem Matrix sensing problem with over-parameterization and noisy measurements.
method Alternating preconditioned gradient descent (APGD) algorithm incorporating preconditioning terms.
result APGD converges to a near-optimal error at a linear rate.

Stein variational gradient descent (SVGD) is a particle-based inference algorithm that leverages gradient information for efficient approximate inference. In this work, we enhance SVGD by leveraging preconditioning matrices, such as the Hessian and Fisher information matrix, to incorporate geometric information into SV…

2019-10-28abs ↗pdf ↗

Polyak-Ruppert CLT for SA-Adam with momentum and non-convergent adaptive preconditioning

problem Adaptive optimizers combining momentum and non-convergent preconditioning
method Proving positive drift stability and a non-autonomous Polyak-Ruppert CLT for SA-Adam
result The iterate-marginal covariance is exactly the plain stochastic gradient descent (SGD) sandwich

SignSGD analysis quantifies its effects in high dimensions.

problem Understanding signSGD's effects in high-dimensional settings.
method High-dimensional analysis of signSGD, deriving SDE and ODE for risk.
result Quantification of signSGD's effects: effective learning rate, noise compression, diagonal preconditioning, gradient noise reshaping.

State-of-the-art models are now trained with billions of parameters, reaching hardware limits in terms of memory consumption. This has created a recent demand for memory-efficient optimizers. To this end, we investigate the limits and performance tradeoffs of memory-efficient adaptively preconditioned gradient methods.…

2019-02-12abs ↗pdf ↗

This work analyzes Adam's preconditioning effect on quadratic functions and quantifies its impact on condition number.

problem Understanding and quantifying the preconditioning effect of Adam to alleviate ill-conditioning in gradient descent.
method Detailed analysis of Adam's preconditioning effect for quadratic functions, including empirical evidence.
result Adam can mitigate the condition number but at a dimension-dependent cost, with specific bounds for different types of Hessians.

Gradient descent converges geometrically to optimal self-attention parameters.

problem Training softmax self-attention layers for linear regression.
method Structure-aware gradient descent with preconditioner and regularizer.
result Gradient descent converges geometrically to global minima.

NeuralIF uses neural networks to improve preconditioning for faster CG convergence.

problem Improving convergence of conjugate gradient method for large-scale sparse systems.
method Data-driven approach using graph neural networks to generate incomplete factorization.
result Data-driven preconditioners accelerate convergence of conjugate gradient method.

PDHAMS improves sampling for discrete distributions with quadratic potential functions.

problem Sampling discrete distributions efficiently and accurately.
method Integrates a second-order approximation of the potential function and uses Gaussian integral trick.
result PDHAMS yields superior performance compared to other methods.

New theory explains why normalization is preferred in SGD under heavy-tailed noise.

problem Understanding why normalization is preferred in stochastic gradient descent (SGD) under heavy-tailed noise.
method Developed a worst-case complexity theory for stochastically preconditioned SGD and its variants.
result Normalization guarantees convergence at optimal rates, while clipping may fail in the worst case.

New particle-based VI algorithm expands function class and improves scalability.

problem Limited function class in particle-based VI algorithms restricts flexibility and scalability.
method Introduces a functional regularization term to expand the function class and proposes PFG algorithm.
result Proposed PFG algorithm has larger function class, improved scalability, better adaptation to ill-conditioned distributions, and provable convergence.

The paper explores how dynamic preconditioning affects the CLT in online averaging.

problem When does dynamic preconditioning preserve the Polyak-Ruppert CLT?
method The authors decompose the averaged error and identify a stabilization-rate threshold for the CLT to hold.
result The CLT holds if the dynamic remainder vanishes in L2L^2 and the stabilization rate exceeds a threshold.

This work analyzes how preconditioning affects generalization in machine learning models.

problem The impact of preconditioning on the generalization of machine learning models.
method An asymptotic bias-variance decomposition of the generalization error for ridgeless regression under various preconditioners.
result The optimal preconditioner depends on label noise, model specification, and signal alignment, with NGD potentially better under certain conditions.

Muon optimizer simplifies matrix optimization with spectral orthogonalization.

problem Matrix optimization challenges, especially with large condition numbers.
method Simplified Muon optimizer using spectral orthogonalization of gradients.
result Simplified Muon converges linearly with independent scalar sequences, outperforming gradient descent and Adam.