A new optimizer combines Newton and ADMM for faster classification.
problem Slower convergence of first-order methods in distributed learning.
method Integrates GPU-accelerated Newton solver with ADMM for multiclass classification.
result Significantly reduces the time to solution and generalization error.
We describe stochastic Newton and stochastic quasi-Newton approaches to efficiently solve large linear least-squares problems where the very large data sets present a significant computational burden (e.g., the size may exceed computer memory or data are collected in real-time). In our proposed framework, stochasticity…
Improved iterative methods for risk parity portfolio weights.
problem Solving for portfolio weights in risk parity allocation.
method Enhanced CCD and Newton methods, including a rescaling step and improved initial guess.
result Improved CCD method is the best, three times faster with 40% fewer iterations.
SnapBoost uses random base hypothesis classes to improve gradient boosting performance.
problem Improving gradient boosting performance.
method Heterogeneous Newton Boosting Machine (HNBM) with variable base hypothesis classes.
result SnapBoost achieves better generalization loss than competing frameworks.
Simple stochastic Newton and cubic Newton methods with fast convergence.
problem Minimizing large numbers of smooth and strongly convex functions.
method Stochastic Newton and cubic Newton methods with simple local linear-quadratic rates.
result Local linear-quadratic convergence results with fast adaptation to problem's curvature.
SNS accelerates Sinkhorn algorithm with sparse Newton iterations.
problem Slow runtime of Sinkhorn algorithm for optimal transport.
method Early stopping and Newton-type subroutine for matrix scaling steps.
result SNS converges orders of magnitude faster than Sinkhorn.
Paper proposes an online covariance estimator for sketched Newton methods.
problem Estimating the limiting covariance matrix of sketched Newton methods.
method Proposes a fully online covariance matrix estimator from Newton iterates.
result Establishes the consistency and convergence rate of the proposed estimator.
Paper develops a robust PP distributed quasi-Newton estimation for Byzantine machines.
problem Byzantine machines in distributed computing under Privacy Protection constraints.
method Robust PP distributed quasi-Newton estimation method that transmits only five vectors.
result Reduces privacy budgeting and transmission cost compared to gradient descent and Newton iteration.
New algorithm improves convergence of gradient boosting trees.
problem Global convergence of Newton boosting in tabular machine learning.
method Introduces Gradient Regularized Newton Descent for GBDTs, proving linear convergence for smooth, strongly convex losses and O(k21) rate for general convex losses. result Achieves globally convergent second-order GBDT algorithm with rate matching first-order boosting.
New method uses robust estimators for Newton's method in empirical risk minimization.
problem Improving robustness in empirical risk minimization.
method Robust Newton's method with gradient and Hessian replaced by robust estimators.
result Faster convergence rates in high-dimensional settings.
Sketching, a dimensionality reduction technique, has received much attention in the statistics community. In this paper, we study sketching in the context of Newton's method for solving finite-sum optimization problems in which the number of variables and data points are both large. We study two forms of sketching that…
Newton-LESS sparsifies Gaussian sketching for faster optimization.
problem Computing the Hessian matrix in optimization is computationally expensive.
method Uses a sparsified version of a dense Gaussian sketching matrix.
result Achieves nearly the same convergence rate as dense Gaussian embeddings without the computational cost.
The paper studies the solution of stochastic optimization problems in which approximations to the gradient and Hessian are obtained through subsampling. We first consider Newton-like methods that employ these approximations and discuss how to coordinate the accuracy in the gradient and Hessian to yield a superlinear ra…
New averaging technique speeds up Newton method convergence.
problem Superlinear convergence of stochastic Newton methods with noisy Hessians.
method Hessian averaging to reduce noise and maintain superlinear convergence.
result Hessian averaging achieves superlinear convergence with a non-asymptotic rate.
In this paper we consider the composite self-concordant (CSC) minimization problem, which minimizes the sum of a self-concordant function f and a (possibly nonsmooth) proper closed convex function g. The CSC minimization is the cornerstone of the path-following interior point methods for solving a broad class of co…
A new quasi-Newton method uses cubic regularization to avoid saddle points in deep learning.
problem Avoiding saddle points and poor local minima in deep learning models.
method Limited-memory symmetric rank-one quasi-Newton approach with adaptive regularized cubics.
result The method effectively avoids saddle points and converges to better local minima.
Paper proposes an efficient online Newton method with Nesterov's acceleration for streaming data.
problem Efficient inference of online Newton methods with robustness to noise and ill-conditioning.
method Online Newton method with Hessian averaging and Nesterov's accelerated sketch-and-project solver.
result Global almost-sure convergence and asymptotic normality of the last iterate with non-asymptotic convergence guarantees.
New algorithms solve non-convex optimization problems efficiently.
problem Non-convex stochastic compositional optimization problems.
method Developed two stochastic Gauss-Newton algorithms.
result Established global oracle complexity for stochastic Gauss-Newton methods.
Paper proposes a method to find approximate SOSP for nonconvex conic optimization problems.
problem Finding approximate second-order stationary points in nonconvex conic optimization.
method Newton-CG based barrier method with complexity guarantees.
result Achieves iteration complexity of O(ε^(-3/2)) for finding (ε,√ε)-SOSP.
A new method solves entropic optimal transport faster.
problem Efficiently solving entropic optimal transport problems.
method Logarithmic Newton iteration for optimality conditions.
result Quadratic convergence rate compared to Sinkhorn-Knopp.
New method solves constrained optimization problems efficiently.
problem Equality-constrained nonlinear, nonconvex optimization problems.
method Adaptive inexact Newton method with randomized iterative sketching.
result Global almost sure convergence and local linear/superlinear convergence.
A deep learning model speeds up computation of numerous implied volatilities.
problem Frequent computation of numerous implied volatilities using iteration methods like Newton-Raphson reaches processing speed limits.
method Emulated Newton-Raphson method using PyTorch and optimized with TensorRT.
result Up to 1,000 times faster than a benchmark implementation of Newton-Raphson.
Two new sampling methods improve machine learning optimization.
problem Efficiently solving machine learning empirical risk minimization problems.
method Randomly sampled quasi-Newton methods for optimization.
result Sampled methods outperform classical variants in machine learning tasks.
Recurrent Neural Networks (RNNs) are powerful models that achieve exceptional performance on several pattern recognition problems. However, the training of RNNs is a computationally difficult task owing to the well-known "vanishing/exploding" gradient problem. Algorithms proposed for training RNNs either exploit no (or…
Proposes a faster second-order method for MDPs.
problem Slow convergence of first-order value iteration methods in MDPs.
method Applies Newton-Raphson method to successive relaxation value iteration scheme.
result Second-order convergence and faster convergence to optimal solution.
Study AR(1) series for risk model, estimating ruin probability.
problem Estimating ruin probability in risk models with dependent claim numbers.
method Established AR(1) risk model, used Newton iteration method to find adjustment coefficient, estimated ruin probability.
result Developed new method to estimate exponential upper bound of ruin probability.
GIANT optimizes distributed computing by improving Newton method efficiency.
problem Efficiently solving empirical risk minimization problems in distributed environments.
method GIANT combines local ANT directions to form a GIANT direction, averaging communications and computations.
result GIANT achieves faster convergence compared to first-order and existing Newton-type methods.
Stein variational Newton method accelerates SVGD for faster inference.
problem Efficient nonparametric variational inference.
method Accelerates SVGD by incorporating second-order information and optimal kernel selection.
result Significant computational gains over original SVGD in multiple test cases.
A new Bayesian filtering method speeds up stochastic Newton optimization.
problem Minimizing log-convex functions using stochastic methods.
method Contextualizes the problem as Bayesian inference, applying Bayesian filtering to update estimates.
result Establishes conditions for diminishing effect of older observations, akin to momentum.
This paper extends Newton's method to distributed learning, avoiding saddle points and handling Byzantine workers.
problem Avoiding saddle points in distributed non-convex optimization, especially in the presence of Byzantine workers.
method Extends cubic-regularized Newton method to distributed framework, addressing communication bottlenecks and Byzantine attacks.
result The method achieves improved iteration complexity compared to first-order methods, with a 25% improvement in experiments.
New quasi-Newton method guarantees global superlinear convergence.
problem Global convergence and superlinear convergence of quasi-Newton methods.
method Hybrid proximal extragradient method with online learning for Hessian approximation.
result First globally convergent quasi-Newton method with explicit superlinear convergence rate.
A new distributed method for convex optimization over networks with fast convergence.
problem Large-scale convex optimization over networks with limited communication.
method Distributed cubic-regularized Newton method.
result Convergence rate of O(k−3) for convex functions with Lipschitz gradient and Hessian. SVRN accelerates Newton methods by reducing variance and improving performance.
problem Improving the efficiency of Newton methods for large-scale optimization problems.
method Stochastic Variance-Reduced Newton (SVRN) algorithm that accelerates Subsampled Newton and Iterative Hessian Sketch algorithms.
result SVRN accelerates Newton methods by reducing the number of passes over the data, achieving a significant improvement in performance.
We present a novel Newton-type method for distributed optimization, which is particularly well suited for stochastic optimization and learning problems. For quadratic objectives, the method enjoys a linear rate of convergence which provably \emph{improves} with the data size, requiring an essentially constant number of…
NS-RGS improves orthogonal group synchronization with faster convergence.
problem Orthogonal group synchronization from pairwise measurements.
method Newton-Schulz iteration for Riemannian gradient optimization.
result NS-RGS achieves linear convergence and near-optimal accuracy.
Paper proposes a new method to find approximate SOSP for nonconvex constrained optimization problems.
problem Finding a second-order stationary point of nonconvex equality constrained optimization.
method Newton-CG based augmented Lagrangian method with a new Newton-CG subproblem solver.
result Achieves better complexity guarantees for finding approximate SOSP with high probability.
New adaptive first-order methods improve on quasi-Newton variants.
problem Designing efficient gradient methods for practical applications.
method Online scaled gradient methods (OSGM) with new adaptive methods OSGM-Best.
result OSGM-Best matches quasi-Newton variants but requires less memory and cheaper iterations.
Stochastic SGN method converges faster than SGD for DNNs.
problem Training deep neural networks efficiently.
method Stochastic generalized Gauss-Newton method using conjugate gradient and automatic differentiation.
result SGN requires fewer iterations and is more robust to hyperparameters.
SNAP solves LASSO and Enet efficiently with optimal convergence rates.
problem Sparse, high-dimensional linear regression with LASSO and Enet penalties.
method Semismooth Newton algorithm based on KKT conditions, warm start, and support seeking.
result SNAP converges locally superlinearly for Enet and optimally for LASSO, achieving sharp estimation error bounds.
Paper improves a method for fast global and local convergence in optimization.
problem Slow global convergence in optimization methods with noisy Hessian estimates.
method Stochastic Newton Proximal Extragradient method using HPE framework.
result Faster global linear rate and superlinear convergence in fewer iterations.
Improved sampling for complex distributions using quasi-Newton proposals.
problem Sampling from complex, high-dimensional target distributions efficiently.
method Extended pseudo-marginal Metropolis-Hastings with quasi-Newton proposals.
result Quasi-Newton proposals outperform standard random-walk and Hessian-based proposals.
A new method for machine learning updates reduces complexity and improves robustness.
problem Stochastic gradient updates are inefficient and sensitive to feature scaling.
method Incremental Gauss-Newton Descent (IGND) reduces the need for matrix operations and improves robustness.
result IGND improves robustness to sensitivity scaling and can be competitive with common stochastic optimizers.
New Q-Newton's method avoids saddle points and converges quadratically.
problem Optimizing functions with saddle points and ensuring convergence guarantees.
method Modified New Q-Newton's method with Backtracking line search.
result Theorem for Morse functions: quadratic convergence to local minima.
We propose an algorithm, semismooth Newton coordinate descent (SNCD), for the elastic-net penalized Huber loss regression and quantile regression in high dimensional settings. Unlike existing coordinate descent type algorithms, the SNCD updates each regression coefficient and its corresponding subgradient simultaneousl…
AuON is a linear-time optimizer that improves upon Muon's performance without approximate orthogonal matrices.
problem High memory and computational costs of orthogonal momentum updates.
method AuON uses normalized nonlinear scaling and a 'emergency brake' to handle exploding attention logits.
result AuON achieves strong performance without approximate orthogonal matrices, preserving structural alignment and reconditioning.
Transformers can approximate Newton's method for logistic regression.
problem Implementing higher order optimization methods in Transformers.
method Linear attention Transformers with ReLU layers approximating second order optimization algorithms.
result Transformers can implement a single step of Newton's iteration for matrix inversion.
A scalable distributed S-LSR1 algorithm reduces communication costs.
problem Efficiently scaling S-LSR1 for large-scale distributed optimization.
method Proposes DS-LSR1, a communication-efficient variant of S-LSR1.
result DS-LSR1 scales well in problem dimension and data points.
New method solves constrained stochastic optimization problems efficiently.
problem Online statistical inference of constrained stochastic nonlinear optimization problems.
method Stochastic Sequential Quadratic Programming (StoSQP) with iterative sketching solver.
result The rescaled primal-dual sequence converges to a mean-zero Gaussian distribution.