Generalizes Newton's Second Law for field theory.
problem Applying Newton's Second Law to higher-dimensional parameterized submanifolds.
method Introducing geodesic k-vector field and deriving Hamilton's equations.
result Different forces can lead to the same Hamilton's equations.
In this paper we study a class of physical systems that combine a finite number of mechanical and thermodynamic observables. We call them finite dimensional thermo-mechanical systems. We introduce these systems by means of simple examples. The evolution equations of the involved observables are obtained in each example…
Parsimonious neural networks discover interpretable physical laws from data.
problem Discovering interpretable physical laws from data using machine learning.
method Combining neural networks with evolutionary optimization to balance accuracy and parsimony.
result Developed models for classical mechanics and materials melting temperature prediction.
Modified Newton step for online learning reduces matrix size for large datasets.
problem Handling large multi-class datasets efficiently in online learning.
method Element-wise multiplication to reduce matrix size of second order matrices.
result Proposed method achieves similar mistake rates to popular methods but with faster computations.
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.
Graph networks learn symbolic physics laws from simulations.
problem Learning interpretable physics laws from simulations.
method Inductive biases on graph networks for symbolic regression.
result Graph networks can learn symbolic laws of physics.
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.
A parallel optimization method for convex functions using Hessian sketching and debiasing.
problem Massively parallel optimization of convex functions with limited communication.
method Newton method with Hessian sketching and debiasing by workers, server averages descent directions.
result Approximation of Newton step with low-complexity adaptive sketching scheme.
A new optimization method improves deep learning accuracy without hyper-parameter tuning.
problem Computational demands and convergence behavior in deep learning training.
method Stochastic quasi-Gauss-Newton (SQGN) optimization method combining stochastic quasi-Newton, Gauss-Newton, and variance reduction.
result SQGN provides excellent accuracy without hyper-parameter experimentation, improving convergence and computational performance.
In this paper we propose a look at the capital risk problem inspired by deterministic, known from classical mechanics, problem of juggling. We propose capital equivalents to the Newton's laws of motion and on this basis we determine the most secure form of credit repayment with regard to maximisation of profit. Then we…
A new method for faster optimization on statistical manifolds.
problem Slow convergence of first-order methods in manifold optimization.
method Dual Riemannian Newton method on manifolds with dual connections.
result Local quadratic convergence of the dual Riemannian Newton method.
ISAAC Newton uses input-based curvature for efficient training.
problem Efficient training in small-batch stochastic regimes.
method ISAAC Newton conditions gradients using selected second-order information based on input.
result Effective training even in small-batch stochastic regimes, competitive to first-order and second-order methods.
A new method for faster optimization in high dimensions.
problem Slow convergence in high-dimensional optimization problems.
method Subspace cubic regularized Newton method within Krylov subspace.
result Achieves a dimension-independent convergence rate of O(1/mk + 1/k^2).
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.
Adaptive norms improve neural network optimization with second-order methods.
problem Optimizing neural networks with second-order methods.
method Regularized Newton methods with adaptive norms, interpreting adaptive gradient methods as trust region methods.
result Ellipsoidal constraints outperform spherical constraints in terms of backpropagations and asymptotic loss value.
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 ( 1 k 2 ) \mathcal{O}(\frac{1}{k^2}) O ( k 2 1 ) rate for general convex losses. result Achieves globally convergent second-order GBDT algorithm with rate matching first-order boosting.
Unified framework for gradient descent variants in machine learning.
problem Understanding and comparing various gradient descent methods.
method A unified framework interpreting 6 gradient descent variants.
result Some variants coincide under specific conditions.
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.
A new method for optimization in probability space using Newton's flows.
problem Optimization in probability space with information metrics.
method Information Newton's flows, including Fisher-Rao and Wasserstein-2 metrics, with Newton's Langevin dynamics and variational methods.
result Effective numerical implementation and convergence results for the proposed method.
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.
Proposes a new stochastic quasi-Newton method with Nesterov's acceleration.
problem Improving convergence in large-scale non-convex optimization problems.
method Stochastic quasi-Newton method with Nesterov's accelerated gradient.
result Improved performance compared to classical and popular methods.
A new hybrid Newton algorithm improves convergence in logistic regression.
problem Solving large-scale binary classification problems efficiently.
method Proposes a hybrid stochastic Newton algorithm with two weighted components in the Hessian matrix estimation.
result Proves almost sure convergence to the true parameter of logistic regression.
Second-order methods improve differential privacy in convex optimization.
problem Improving differential privacy in convex optimization.
method Developed a private variant of the regularized cubic Newton method for strongly convex loss functions.
result Achieves quadratic convergence and optimal excess loss for strongly convex loss functions.
Proposes a new method for optimizing large-scale models using Nyström approximation of the Hessian.
problem Optimizing non-convex functions like deep learning models using second-order methods.
method Nyström-approximated curvature for stochastic optimization of large-scale empirical risk minimization.
result The proposed method achieves performance competitive with state-of-the-art first-order and stochastic quasi-Newton methods.
Boosting algorithms are frequently used in applied data science and in research. To date, the distinction between boosting with either gradient descent or second-order Newton updates is often not made in both applied and methodological research, and it is thus implicitly assumed that the difference is irrelevant. The g…
Muon spectral optimizer outperforms SGD in associative memory tasks.
problem Understanding the advantage of spectral optimizers in learning associative memory.
method Linear associative memory problem, Gaussian inputs and outputs, power law frequency distribution, thresholded gradient approximation.
result Muon significantly outperforms SGD in storage capacity and recovery rates.
Stochastic quasi-Newton tackles noisy gradients in optimization.
problem Optimizing with noisy data in stochastic settings.
method Extends quasi-Newton methods to handle stochastic gradients through flexible Hessian modeling and line-search regularization.
result Demonstrates superior performance in maximum likelihood estimation for complex models.
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.
New analysis improves accuracy of Newton step and influence function data attributions.
problem Improving accuracy of data attribution methods for logistic regressions.
method Introducing a new analysis of Newton Step and Influence Function data attribution methods for convex learning problems.
result Proved asymptotically tight error bounds for Newton Step and Influence Function data attribution methods.
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.
Improved training of large-scale neural networks with reduced variance noise.
problem Training large-scale neural networks with high variance noise.
method Stochastic variance reduced Nesterov's Accelerated Quasi-Newton method (SVR-NAQ).
result Improved performance compared to conventional methods on benchmark problems.
This paper improves NAQ method for faster convergence on Tensorflow.
problem Non-convex optimization problems.
method Modified Nesterov's Accelerated Quasi-Newton (NAQ) method on Tensorflow.
result mNAQ converges better and faster than first and second order optimizers.
New method solves optimization problems faster than existing methods.
problem Large-scale nonconvex optimization problems.
method ARC method using LQN matrices with exact CR subproblem solution.
result Exact solutions to CR subproblem found in matrix-free manner.
This paper improves an online learning algorithm using second-order information.
problem Online learning with limited feedback.
method Develops Online Newton Step with Expected Gradient (ONSEG) algorithm.
result Reduces expected regret from O(T^(5/6)) to O(T^(2/3)).
Quasi-Newton methods improve deep learning optimization.
problem Solving non-convex optimization problems in deep learning.
method Constructing approximate Hessian matrices using quasi-Newton methods.
result Quasi-Newton methods achieve superlinear convergence.
Stein variational gradient descent (SVGD) was recently proposed as a general purpose nonparametric variational inference algorithm [Liu & Wang, NIPS 2016]: it minimizes the Kullback-Leibler divergence between the target distribution and its approximation by implementing a form of functional gradient descent on a reprod…
A new optimisation method efficiently scales Hessian-vector products for neural networks.
problem Challenges in applying second-order quasi-Newton methods due to large Hessian and non-convexity.
method Proposes an optimisation algorithm that asymptotically uses the exact inverse Hessian with modified eigenvalues.
result Demonstrates scalability and comparable performance to other optimisation methods in neural networks.
Approximate Newton methods are a standard optimization tool which aim to maintain the benefits of Newton's method, such as a fast rate of convergence, whilst alleviating its drawbacks, such as computationally expensive calculation or estimation of the inverse Hessian. In this work we investigate approximate Newton meth…
Improved neural network ensembles using Stein Variational Newton updates.
problem Lack of efficient second-order information in current ensemble methods.
method Proposes a novel approximate Bayesian inference method integrating Stein Variational Newton updates with scalable Hessian approximations.
result Significantly faster convergence and more accurate posterior distribution approximations.
In this work, we present a globalized stochastic semismooth Newton method for solving stochastic optimization problems involving smooth nonconvex and nonsmooth convex terms in the objective function. We assume that only noisy gradient and Hessian information of the smooth part of the objective function is available via…
A new method solves large-scale sparse group square-root Lasso problems efficiently.
problem Large-scale linearly constrained sparse group square-root Lasso problems.
method Dual semismooth Newton based augmented Lagrangian method (ALM).
result The proposed method efficiently solves the problem with numerical experiments demonstrating its effectiveness.
Paper proposes a new method to efficiently incorporate curvature information in stochastic optimization.
problem Minimizing nonconvex functions with limited curvature information.
method Structured stochastic quasi-Newton method using partial Hessian information.
result Global convergence to stationary point and local superlinear convergence rate established.
Paper develops efficient methods for estimating Hessian inverses in stochastic optimization.
problem Estimating the inverse Hessian for convex function minimization.
method Robbins-Monro procedure for recursive estimation of the inverse Hessian.
result Develops universal stochastic Newton methods with improved efficiency.
I consider the existence and structure of conservation laws for the general class of evolutionary scalar second-order differential equations with parabolic symbol. First I calculate the linearized characteristic cohomology for such equations. This provides an auxiliary differential equation satisfied by the conservatio…
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.
This thesis disentangles Gauss-Newton and variational approximations in Bayesian deep learning.
problem Understanding the interplay between the Gauss-Newton method and variational approximations in Bayesian deep learning.
method Analysis of the Gauss-Newton method and Laplace/Gaussian variational approximations for neural networks.
result The combination of the Gauss-Newton method with approximate inference can be cast as inference in a linear or Gaussian process model.
We propose a randomized second-order method for optimization known as the Newton Sketch: it is based on performing an approximate Newton step using a randomly projected or sub-sampled Hessian. For self-concordant functions, we prove that the algorithm has super-linear convergence with exponentially high probability, wi…
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-augmented Lagrangian method.
result Method achieves complexity bounds of O ~ ( ε − 11 / 2 ) \widetilde{\cal O}(ε^{-11/2}) O ( ε − 11/2 ) and O ~ ( ε − 11 / 2 min { n , ε − 5 / 4 } ) \widetilde{\cal O}(ε^{-11/2}\min\{n,ε^{-5/4}\}) O ( ε − 11/2 min { n , ε − 5/4 }) for finding an ( ε , ε ) (ε,\sqrtε) ( ε , ε ) -SOSP.