Online Covariance Matrix Estimation in Sketched Newton Methods

Given the ubiquity of streaming data, online algorithms have been widely used for parameter estimation, with second-order methods particularly standing out for their efficiency and robustness. In this paper, we study an online sketched Newton method that leverages a randomized sketching technique to perform an approximate Newton step in each iteration, thereby eliminating the computational bottleneck of second-order methods. While existing studies have established the asymptotic normality of sketched Newton methods, a consistent estimator of the limiting covariance matrix remains an open problem. We propose a fully online covariance matrix estimator that is constructed entirely from the Newton iterates and requires no matrix factorization. Compared to covariance estimators for first-order online methods, our estimator for second-order methods is batch-free. We establish the consistency and convergence rate of our estimator, and coupled with asymptotic normality results, we can then perform online statistical inference for the model parameters based on sketched Newton methods. We also discuss the extension of our estimator to constrained problems, and demonstrate its superior performance on regression problems as well as benchmark problems in the CUTEst set.

Online Covariance Estimation in Nonsmooth Stochastic Approximation

We consider applying stochastic approximation (SA) methods to solve nonsmooth variational inclusion problems. Existing studies have shown that the averaged iterates of SA methods exhibit asymptotic normality, with an optimal limiting covariance matrix in the local minimax sense of H\'ajek and Le Cam. However, no methods have been proposed to estimate this covariance matrix in a nonsmooth and potentially non-monotone (nonconvex) setting. In this paper, we study an online batch-means covariance matrix estimator introduced in Zhu et al.(2023). The estimator groups the SA iterates appropriately and computes the sample covariance among batches as an estimate of the limiting covariance. Its construction does not require prior knowledge of the total sample size, and updates can be performed recursively as new data arrives. We establish that, as long as the batch size sequence is properly specified (depending on the stepsize sequence), the estimator achieves a convergence rate of order $O(\sqrt{d}n^{-1/8+\varepsilon})$ for any $\varepsilon>0$, where $d$ and $n$ denote the problem dimensionality and the number of iterations (or samples) used. Although the problem is nonsmooth and potentially non-monotone (nonconvex), our convergence rate matches the best-known rate for covariance estimation methods using only first-order information in smooth and strongly-convex settings. The consistency of this covariance estimator enables asymptotically valid statistical inference, including constructing confidence intervals and performing hypothesis testing.

Physics-Informed Neural Networks with Trust-Region Sequential Quadratic Programming

Physics-Informed Neural Networks (PINNs) represent a significant advancement in Scientific Machine Learning (SciML), which integrate physical domain knowledge into an empirical loss function as soft constraints and apply existing machine learning methods to train the model. However, recent research has noted that PINNs may fail to learn relatively complex Partial Differential Equations (PDEs). This paper addresses the failure modes of PINNs by introducing a novel, hard-constrained deep learning method -- trust-region Sequential Quadratic Programming (trSQP-PINN). In contrast to directly training the penalized soft-constrained loss as in PINNs, our method performs a linear-quadratic approximation of the hard-constrained loss, while leveraging the soft-constrained loss to adaptively adjust the trust-region radius. We only trust our model approximations and make updates within the trust region, and such an updating manner can overcome the ill-conditioning issue of PINNs. We also address the computational bottleneck of second-order SQP methods by employing quasi-Newton updates for second-order information, and importantly, we introduce a simple pretraining step to further enhance training efficiency of our method. We demonstrate the effectiveness of trSQP-PINN through extensive experiments. Compared to existing hard-constrained methods for PINNs, such as penalty methods and augmented Lagrangian methods, trSQP-PINN significantly improves the accuracy of the learned PDE solutions, achieving up to 1-3 orders of magnitude lower errors. Additionally, our pretraining step is generally effective for other hard-constrained methods, and experiments have shown the robustness of our method against both problem-specific parameters and algorithm tuning parameters.

Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching

We consider solving equality-constrained nonlinear, nonconvex optimization problems. This class of problems appears widely in a variety of applications in machine learning and engineering, ranging from constrained deep neural networks, to optimal control, to PDE-constrained optimization. We develop an adaptive inexact Newton method for this problem class. In each iteration, we solve the Lagrangian Newton system inexactly via a randomized iterative sketching solver, and select a suitable stepsize by performing line search on an exact augmented Lagrangian merit function. The randomized solvers have advantages over deterministic linear system solvers by significantly reducing per-iteration flops complexity and storage cost, when equipped with suitable sketching matrices. Our method adaptively controls the accuracy of the randomized solver and the penalty parameters of the exact augmented Lagrangian, to ensure that the inexact Newton direction is a descent direction of the exact augmented Lagrangian. This allows us to establish a global almost sure convergence. We also show that a unit stepsize is admissible locally, so that our method exhibits a local linear convergence. Furthermore, we prove that the linear convergence can be strengthened to superlinear convergence if we gradually sharpen the adaptive accuracy condition on the randomized solver. We demonstrate the superior performance of our method on benchmark nonlinear problems in CUTEst test set, constrained logistic regression with data from LIBSVM, and a PDE-constrained problem.

Fully Stochastic Trust-Region Sequential Quadratic Programming for Equality-Constrained Optimization Problems

We propose a trust-region stochastic sequential quadratic programming algorithm (TR-StoSQP) to solve nonlinear optimization problems with stochastic objectives and deterministic equality constraints. We consider a fully stochastic setting, where in each iteration a single sample is generated to estimate the objective gradient. The algorithm adaptively selects the trust-region radius and, compared to the existing line-search StoSQP schemes, allows us to employ indefinite Hessian matrices (i.e., Hessians without modification) in SQP subproblems. As a trust-region method for constrained optimization, our algorithm needs to address an infeasibility issue -- the linearized equality constraints and trust-region constraints might lead to infeasible SQP subproblems. In this regard, we propose an \textit{adaptive relaxation technique} to compute the trial step that consists of a normal step and a tangential step. To control the lengths of the two steps, we adaptively decompose the trust-region radius into two segments based on the proportions of the feasibility and optimality residuals to the full KKT residual. The normal step has a closed form, while the tangential step is solved from a trust-region subproblem, to which a solution ensuring the Cauchy reduction is sufficient for our study. We establish the global almost sure convergence guarantee for TR-StoSQP, and illustrate its empirical performance on both a subset of problems in the CUTEst test set and constrained logistic regression problems using data from the LIBSVM collection.

Asymptotic Convergence Rate and Statistical Inference for Stochastic Sequential Quadratic Programming

We apply a stochastic sequential quadratic programming (StoSQP) algorithm to solve constrained nonlinear optimization problems, where the objective is stochastic and the constraints are deterministic. We study a fully stochastic setup, where only a single sample is available in each iteration for estimating the gradient and Hessian of the objective. We allow StoSQP to select a random stepsize $\bar{\alpha}_t$ adaptively, such that $\beta_t\leq \bar{\alpha}_t \leq \beta_t+\chi_t$, where $\beta_t$, $\chi_t=o(\beta_t)$ are prespecified deterministic sequences. We also allow StoSQP to solve Newton system inexactly via randomized iterative solvers, e.g., with the sketch-and-project method; and we do not require the approximation error of inexact Newton direction to vanish. For this general StoSQP framework, we establish the asymptotic convergence rate for its last iterate, with the worst-case iteration complexity as a byproduct; and we perform statistical inference. In particular, with proper decaying $\beta_t,\chi_t$, we show that: (i) the StoSQP scheme can take at most $O(1/\epsilon^4)$ iterations to achieve $\epsilon$-stationarity; (ii) asymptotically and almost surely, $\|(x_t -x^\star, \lambda_t - \lambda^\star)\| = O(\sqrt{\beta_t\log(1/\beta_t)})+O(\chi_t/\beta_t)$, where $(x_t,\lambda_t)$ is the primal-dual StoSQP iterate; (iii) the sequence $1/\sqrt{\beta_t}\cdot (x_t -x^\star, \lambda_t - \lambda^\star)$ converges to a mean zero Gaussian distribution with a nontrivial covariance matrix. Moreover, we establish the Berry-Esseen bound for $(x_t, \lambda_t)$ to measure quantitatively the convergence of its distribution function. We also provide a practical estimator for the covariance matrix, from which the confidence intervals of $(x^\star, \lambda^\star)$ can be constructed using iterates $\{(x_t,\lambda_t)\}_t$. Our theorems are validated using nonlinear problems in CUTEst test set.

Hessian Averaging in Stochastic Newton Methods Achieves Superlinear Convergence

We consider minimizing a smooth and strongly convex objective function using a stochastic Newton method. At each iteration, the algorithm is given an oracle access to a stochastic estimate of the Hessian matrix. The oracle model includes popular algorithms such as the Subsampled Newton and Newton Sketch, which can efficiently construct stochastic Hessian estimates for many tasks. Despite using second-order information, these existing methods do not exhibit superlinear convergence, unless the stochastic noise is gradually reduced to zero during the iteration, which would lead to a computational blow-up in the per-iteration cost. We address this limitation with Hessian averaging: instead of using the most recent Hessian estimate, our algorithm maintains an average of all past estimates. This reduces the stochastic noise while avoiding the computational blow-up. We show that this scheme enjoys local $Q$-superlinear convergence with a non-asymptotic rate of $(\Upsilon\sqrt{\log (t)/t}\,)^{t}$, where $\Upsilon$ is proportional to the level of stochastic noise in the Hessian oracle. A potential drawback of this (uniform averaging) approach is that the averaged estimates contain Hessian information from the global phase of the iteration, i.e., before the iterates converge to a local neighborhood. This leads to a distortion that may substantially delay the superlinear convergence until long after the local neighborhood is reached. To address this drawback, we study a number of weighted averaging schemes that assign larger weights to recent Hessians, so that the superlinear convergence arises sooner, albeit with a slightly slower rate. Remarkably, we show that there exists a universal weighted averaging scheme that transitions to local convergence at an optimal stage, and still enjoys a superlinear convergence~rate nearly (up to a logarithmic factor) matching that of uniform Hessian averaging.

Inequality Constrained Stochastic Nonlinear Optimization via Active-Set Sequential Quadratic Programming

We study nonlinear optimization problems with stochastic objective and deterministic equality and inequality constraints, which emerge in numerous applications including finance, manufacturing, power systems and, recently, deep neural networks. We propose an active-set stochastic sequential quadratic programming algorithm, using a differentiable exact augmented Lagrangian as the merit function. The algorithm adaptively selects the penalty parameters of augmented Lagrangian and performs stochastic line search to decide the stepsize. The global convergence is established: for any initialization, the "liminf" of the KKT residuals converges to zero almost surely. Our algorithm and analysis further develop the prior work \cite{Na2021Adaptive} by allowing nonlinear inequality constraints. We demonstrate the performance of the algorithm on a subset of nonlinear problems collected in the CUTEst test set.

An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangians

We consider the problem of solving nonlinear optimization programs with stochastic objective and deterministic equality constraints. We assume for the objective that the function evaluation, the gradient, and the Hessian are inaccessible, while one can compute their stochastic estimates by, for example, subsampling. We propose a stochastic algorithm based on sequential quadratic programming (SQP) that uses a differentiable exact augmented Lagrangian as the merit function. To motivate our algorithm, we revisit an old SQP method \citep{Lucidi1990Recursive} developed for deterministic programs. We simplify that method and derive an adaptive SQP, which serves as the skeleton of our stochastic algorithm. Based on the derived algorithm, we then propose a non-adaptive SQP for optimizing stochastic objectives, where the gradient and the Hessian are replaced by stochastic estimates but the stepsize is deterministic and prespecified. Finally, we incorporate a recent stochastic line search procedure \citep{Paquette2020Stochastic} into our non-adaptive stochastic SQP to arrive at an adaptive stochastic SQP. To our knowledge, the proposed algorithm is the first stochastic SQP that allows a line search procedure and the first stochastic line search procedure that allows the constraints. The global convergence for all proposed SQP methods is established, while numerical experiments on nonlinear problems in the CUTEst test set demonstrate the superiority of the proposed algorithm.

AEGCN: An Autoencoder-Constrained Graph Convolutional Network

We propose a novel neural network architecture, called autoencoder-constrained graph convolutional network, to solve node classification task on graph domains. As suggested by its name, the core of this model is a convolutional network operating directly on graphs, whose hidden layers are constrained by an autoencoder. Comparing with vanilla graph convolutional networks, the autoencoder step is added to reduce the information loss brought by Laplacian smoothing. We consider applying our model on both homogeneous graphs and heterogeneous graphs. For homogeneous graphs, the autoencoder approximates the adjacency matrix of the input graph by taking hidden layer representations as encoder and another one-layer graph convolutional network as decoder. For heterogeneous graphs, since there are multiple adjacency matrices corresponding to different types of edges, the autoencoder approximates the feature matrix of the input graph instead, and changes the encoder to a particularly designed multi-channel pre-processing network with two layers. In both cases, the error occurred in the autoencoder approximation goes to the penalty term in the loss function. In extensive experiments on citation networks and other heterogeneous graphs, we demonstrate that adding autoencoder constraints significantly improves the performance of graph convolutional networks. We also notice that such technique can be applied on graph attention network to improve the performance as well. This reveals the wide applicability of the proposed autoencoder technique.