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.
Optimal preconditioning improves Langevin sampling efficiency.
problem Improving sampling efficiency in high-dimensional target distributions.
method Optimal preconditioning using Fisher information, applied to MALA.
result Adaptive MCMC scheme significantly outperforms other methods.
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.…
This paper optimizes diagonal preconditioning to improve matrix condition numbers.
problem Optimizing diagonal preconditioning to reduce matrix condition numbers.
method Reformulated as a quasi-convex problem, solved with bisection and Newton updates.
result Optimal diagonal preconditioners can significantly improve iterative methods.
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…
Layer-wise preconditioning methods improve neural network optimization and feature learning.
problem Suboptimal feature learning in standard optimization algorithms.
method Layer-wise preconditioning methods that introduce preconditioners per axis of each layer's weight tensors.
result Layer-wise preconditioning is necessary for provable feature learning in linear and single-index models.
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.
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 L1-regularization. result Derives a unified mathematical framework for understanding and optimizing training acceleration.
Bias correction improves language model training performance.
problem Stochastic update bias in preconditioned optimizers.
method Cross-fitted preconditioning and variance-corrected inversion.
result Reduces held-out pretraining loss by 0.15 nats.
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.
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.
In this paper, we analyze different preconditionings designed to enhance robustness of pure-pixel search algorithms, which are used for blind hyperspectral unmixing and which are equivalent to near-separable nonnegative matrix factorization algorithms. Our analysis focuses on the successive projection algorithm (SPA), …
New method speeds up solving orthogonality constrained problems.
problem Solving orthogonality constrained problems efficiently.
method Riemannian optimization and Riemannian preconditioning.
result Preconditioning improves computational costs and convergence.
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.…
In this work, we study data preconditioning, a well-known and long-existing technique, for boosting the convergence of first-order methods for regularized loss minimization. It is well understood that the condition number of the problem, i.e., the ratio of the Lipschitz constant to the strong convexity modulus, has a h…
APO optimizes neural network parameters by amortizing proximal point methods.
problem Optimizing neural network parameters online and adaptively.
method APO framework that meta-learns proximal point parameters.
result APO can recover and outperform existing optimizers and schedules.
We propose a novel Riemannian manifold preconditioning approach for the tensor completion problem with rank constraint. A novel Riemannian metric or inner product is proposed that exploits the least-squares structure of the cost function and takes into account the structured symmetry that exists in Tucker decomposition…
This paper improves linear system solving by optimizing matrix diagonal scaling.
problem Improving the condition number of a matrix for faster iterative methods.
method Left or right diagonal rescaling of the matrix A, with new bounds and algorithms.
result Jacobi preconditioning reduces A's condition number to within a quadratic factor of the best possible scaling.
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.
New research shows how preconditioning can solve sparse linear regression problems efficiently.
problem Efficiently solving sparse linear regression problems without restrictive conditions.
method Preconditioned Lasso approach to solve sparse linear regression problems.
result Preconditioning can solve a large class of sparse linear regression problems nearly optimally.
Adaptive learning rate algorithms such as RMSProp are widely used for training deep neural networks. RMSProp offers efficient training since it uses first order gradients to approximate Hessian-based preconditioning. However, since the first order gradients include noise caused by stochastic optimization, the approxima…
Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on properties of the optimization algorithm, including acceleration and preconditioning, thr…
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…
We present a novel preconditioning technique for proximal optimization methods that relies on graph algorithms to construct effective preconditioners. Such combinatorial preconditioners arise from partitioning the graph into forests. We prove that certain decompositions lead to a theoretically optimal condition number.…
RL accelerates portfolio optimization and option pricing by dynamically adjusting preconditioner sizes.
problem Large linear systems in portfolio optimization and option pricing lead to slow convergence.
method Reinforcement Learning (RL) dynamically adjusts block-preconditioner sizes to accelerate convergence.
result RL-driven solver significantly reduces computational cost and accelerates convergence.
New methods improve solving linear systems and preconditioning with reduced complexity.
problem Efficiently solving linear systems and preconditioning matrices.
method Developed structured semidefinite programming algorithms.
result Improved runtimes for preconditioning and solving linear systems.
Adaptive regularization methods pre-multiply a descent direction by a preconditioning matrix. Due to the large number of parameters of machine learning problems, full-matrix preconditioning methods are prohibitively expensive. We show how to modify full-matrix adaptive regularization in order to make it practical and e…
We describe a framework for deriving and analyzing online optimization algorithms that incorporate adaptive, data-dependent regularization, also termed preconditioning. Such algorithms have been proven useful in stochastic optimization by reshaping the gradients according to the geometry of the data. Our framework capt…
Boosts linear neurons for faster convergence in neural networks.
problem Optimizing neural networks' neurons in function space.
method Reparameterizing network to whiten neuron features using Boosted Backpropagation.
result Equivalent to preconditioned gradient descent, leading to faster convergence.
In this paper we introduce a parameter dependent class of Krylov-based methods, namely CD, for the solution of symmetric linear systems. We give evidence that in our proposal we generate sequences of conjugate directions, extending some properties of the standard Conjugate Gradient (CG) method, in order to preserve the…
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…
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.
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.
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 for convex K and applying it to overparameterized linear models. result The iterates of the preconditioned gradient descent converge to a solution W∞ satisfying XW∞=Y. Universal preconditioning reduces sequential prediction regret.
problem Improving sequential prediction performance.
method Convolve target sequence with orthogonal polynomial coefficients.
result First sublinear and hidden-dimension-independent regret bounds.
Preconditioned neural posterior estimation improves reliability in misspecified models.
problem Reliability issues in neural posterior estimation for misspecified models.
method Preconditioning with data-dependent weights and forest-proximity scores to stabilize and improve accuracy.
result Preconditioned robust neural posterior estimation increases stability and accuracy over standard methods.
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
Improved likelihood-free inference using preconditioned neural posterior estimation.
problem Inaccurate posterior estimation in likelihood-free inference methods.
method Preconditioned Neural Posterior Estimation (PNPE) and Sequential PNPE (PSNPE) methods.
result PNPE and PSNPE improve posterior estimation accuracy over NPE and SNPE.
Two methods solve kernel ridge regression problems efficiently.
problem Solving kernel ridge regression problems with large datasets.
method RPCholesky and KRILL preconditioning techniques.
result Efficient solutions to KRR problems with strong guarantees.
Preconditioned SGD accelerates convergence for ill-conditioned huge-scale matrix completion.
problem Recovering a low-rank matrix from incomplete data with high condition number.
method Preconditioned Stochastic Gradient Descent (SGD) for huge-scale online optimization.
result Preconditioned SGD converges to ε-accuracy in O(log(1/ε)) iterations, compared to O(κlog(1/ε)) for unpreconditioned SGD.
AdaDPS uses side information to improve private adaptive optimization.
problem Private adaptive optimization methods degrade when training with differential privacy.
method AdaDPS uses non-sensitive side information to precondition gradients.
result AdaDPS reduces the amount of noise needed for similar privacy guarantees, improving optimization performance.
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.
New sampling method using regularized Wasserstein proximal for Gibbs distributions.
problem Sampling from Gibbs distributions with numerical stability and efficiency.
method Preconditioned regularized Wasserstein proximal operator.
result Discrete-time convergence analysis and explicit bias characterization.
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.
A new method improves convergence in low-rank approximation.
problem Efficiently solving large-scale numerical linear algebra problems.
method Error-Powered Sketched Inverse Iteration (EPSI) Method.
result Convergence rate improves at least linearly with sketch size.
Preconditioned NFs speed up sampling from complex posterior distributions in inverse problems.
problem Sampling from posterior distributions of inverse problems with expensive forward operators.
method Preconditioning a conditional normalizing flow (NF) to speed up training.
result Significant speed-ups achieved compared to training NFs from scratch.
AI-driven framework optimizes MCMC-based preconditioners for faster linear system solving.
problem Slow convergence of Krylov subspace solvers for ill-conditioned matrices.
method Graph neural surrogate and Bayesian optimization for AI-tuned MCMC parameters.
result 50% reduction in iterations to convergence on unseen system.