Adaptively preconditions SGLD for faster convergence and better generalization.
problem Pathological curvature in deep network loss landscapes.
method Adaptive estimation of noise parameters to precondition isotropic gradient noise.
result Adaptively preconditioned SGLD achieves faster convergence and generalization equivalent of SGD.
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.
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.
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…
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…
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.
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
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.…
Effective training of deep neural networks suffers from two main issues. The first is that the parameter spaces of these models exhibit pathological curvature. Recent methods address this problem by using adaptive preconditioning for Stochastic Gradient Descent (SGD). These methods improve convergence by adapting to th…
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.
A new method reduces complexity of normalizing flows for MCMC preconditioning.
problem Improving sampling efficiency in MCMC algorithms for complex target distributions.
method Factorized preconditioning architecture combining a linear component and a conditional NF.
result Significantly better tail samples and higher effective sample sizes on various distributions.
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…
New MCMC method learns sparse preconditioner for high-dimensional problems.
problem High-dimensional sampling with complex correlation structures.
method Adaptive MCMC with sparse preconditioner using online PCA.
result Significant reduction in computational complexity and improved performance.
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.
SKT improves EKI for Bayesian inverse problems with non-Gaussian targets.
problem Efficiently solving Bayesian inverse problems with expensive forward models and non-Gaussian posterior distributions.
method Embedding EKI and FAKI within a Bayesian annealing scheme to adapt tpCN sampler.
result Significant improvements in convergence rate compared to standard SMC and pCN.
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.
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.
SLMC improves sampling efficiency for high-dimensional distributions.
problem Sampling from high-dimensional distributions is computationally challenging.
method SLMC projects Langevin updates onto subsampled eigenblocks of a time-varying preconditioner.
result SLMC offers superior adaptability and computational efficiency compared to traditional methods.
pHMC converges on infinite-dimensional spaces with bounds.
problem Convergence of pHMC on Hilbert spaces.
method Coupling of two pHMC copies, adapted from arXiv:1805.00452.
result Proven convergence bounds in 1-Wasserstein distance.
This paper studies the performance of a recently proposed preconditioned stochastic gradient descent (PSGD) algorithm on recurrent neural network (RNN) training. PSGD adaptively estimates a preconditioner to accelerate gradient descent, and is designed to be simple, general and easy to use, as stochastic gradient desce…
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.
Improved online learning algorithm with better regret bounds.
problem Online convex optimization with improved regret bounds.
method Matrix-free preconditioning approach.
result Our algorithm outperforms diagonal preconditioning in certain settings.
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.
The paper analyzes Adam and SGD in nonstationary optimization, revealing tradeoffs between noise and drift.
problem Analyzing Adam and SGD in nonstationary optimization problems.
method Theoretical analysis of Adam and SGD under non-stationary stochastic objectives, separating two regimes.
result Characterizes the tradeoff between noise and drift in Adam and SGD, revealing when adaptive step-sizing is beneficial or harmful.
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.
WarpGrad efficiently learns preconditioning matrices for gradient descent across task distributions.
problem Learning efficient update rules for rapid new task learning.
method Interleaves warp-layers between task-learner layers to meta-learn preconditioning matrices.
result WarpGrad scales to large meta-learning problems and improves across various learning settings.
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.…
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…
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.
New algorithm speeds up large-scale statistical inference.
problem Efficiently solving large-scale mean-field variational inference problems.
method Developed a novel primal-dual algorithm (PD-VI) and a block-preconditioned extension (P2D-VI) for mean-field variational inference. result PD-VI and P2D-VI achieve faster convergence and better solution quality compared to existing methods. 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.
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.
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.
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.
Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their behavior in nonconvex settings. To this end, we first provide a novel view of adaptive methods as preconditioned SGD, where the precondition…
Higher-order ODE solvers improve deep learning performance.
problem Improving deep learning performance using higher-order ODE solvers.
method Evaluation and improvement of Runge-Kutta (RK) methods for deep learning.
result Higher-order RK solvers can improve deep learning performance by incorporating key ingredients of optimizers.
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.
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 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 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.
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.
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.
FOP improves deep learning optimizers with minimal computational overhead.
problem Training deep learning models can be hindered by high correlations and different scaling in parameter space.
method FOP uses first-order information to learn a preconditioning matrix that improves convergence without the high computational cost of second-order methods.
result FOP improves performance of standard deep learning optimizers on visual classification and reinforcement learning tasks.
Current studies about motor imagery based rehabilitation training systems for stroke subjects lack an appropriate analytic method, which can achieve a considerable classification accuracy, at the same time detects gradual changes of imagery patterns during rehabilitation process and disinters potential mechanisms about…
A new optimization method reduces memory and compute requirements for deep learning.
problem Memory and compute constraints in second-order stochastic optimizers for deep learning.
method Proposes KrAD, a novel factorization to approximate inverse Fisher matrix without inversion, leading to KrADagrad.
result Improves performance over Shampoo for 32-bit precision and comparable/generalization on real datasets.