Pairwise learning is essential in machine learning, especially for problems involving loss functions defined on pairs of training examples. Online gradient descent (OGD) algorithms have been proposed to handle online pairwise learning, where data arrives sequentially. However, the pairwise nature of the problem makes scalability challenging, as the gradient computation for a new sample involves all past samples. Recent advancements in OGD algorithms have aimed to reduce the complexity of calculating online gradients, achieving complexities less than $O(T)$ and even as low as $O(1)$. However, these approaches are primarily limited to linear models and have induced variance. In this study, we propose a limited memory OGD algorithm that extends to kernel online pairwise learning while improving the sublinear regret. Specifically, we establish a clear connection between the variance of online gradients and the regret, and construct online gradients using the most recent stratified samples with a limited buffer of size of $s$ representing all past data, which have a complexity of $O(sT)$ and employs $O(\sqrt{T}\log{T})$ random Fourier features for kernel approximation. Importantly, our theoretical results demonstrate that the variance-reduced online gradients lead to an improved sublinear regret bound. The experiments on real-world datasets demonstrate the superiority of our algorithm over both kernelized and linear online pairwise learning algorithms.

This paper proposes a new procedure called quantum shadow gradient descent (QSGD) that addresses these key challenges. Our method has the benefits of a one-shot approach, in not requiring any sample duplication while having a convergence rate comparable to the ideal update rule using exact gradient computation. We propose a new technique for generating quantum shadow samples (QSS), which generates quantum shadows as opposed to classical shadows used in existing works. With classical shadows, the computations are typically performed on classical computers and, hence, are prohibitive since the dimension grows exponentially. Our approach resolves this issue by measurements of quantum shadows. As the second main contribution, we study more general non-product ansatz of the form $\exp\{i\sum_j \theta_j A_j\}$ that model variational Hamiltonians. We prove that the gradient can be written in terms of the gradient of single-parameter ansatzes that can be easily measured. Our proof is based on the Suzuki-Trotter approximation; however, our expressions are exact, unlike prior efforts that approximate non-product operators. As a result, existing gradient measurement techniques can be applied to more general VQAs followed by correction terms without any approximation penalty. We provide theoretical proofs, convergence analysis and verify our results through numerical experiments.

Characterizing and understanding the stability of Stochastic Gradient Descent (SGD) remains an open problem in deep learning. A common method is to utilize the convergence of statistical moments, esp. the variance, of the parameters to quantify the stability. We revisit the definition of stability for SGD and propose using the $\textit{convergence in probability}$ condition to define the $\textit{probabilistic stability}$ of SGD. The probabilistic stability sheds light on a fundamental question in deep learning theory: how SGD selects a meaningful solution for a neural network from an enormous number of possible solutions that may severely overfit. We show that only through the lens of probabilistic stability does SGD exhibit rich and practically relevant phases of learning, such as the phases of the complete loss of stability, incorrect learning where the model captures incorrect data correlation, convergence to low-rank saddles, and correct learning where the model captures the correct correlation. These phase boundaries are precisely quantified by the Lyapunov exponents of the dynamics. The obtained phase diagrams imply that SGD prefers low-rank saddles in a neural network when the underlying gradient is noisy, thereby influencing the learning performance.

Data-driven approximations of the Koopman operator are promising for predicting the time evolution of systems characterized by complex dynamics. Among these methods, the approach known as extended dynamic mode decomposition with dictionary learning (EDMD-DL) has garnered significant attention. Here we present a modification of EDMD-DL that concurrently determines both the dictionary of observables and the corresponding approximation of the Koopman operator. This innovation leverages automatic differentiation to facilitate gradient descent computations through the pseudoinverse. We also address the performance of several alternative methodologies. We assess a 'pure' Koopman approach, which involves the direct time-integration of a linear, high-dimensional system governing the dynamics within the space of observables. Additionally, we explore a modified approach where the system alternates between spaces of states and observables at each time step -- this approach no longer satisfies the linearity of the true Koopman operator representation. For further comparisons, we also apply a state space approach (neural ODEs). We consider systems encompassing two and three-dimensional ordinary differential equation systems featuring steady, oscillatory, and chaotic attractors, as well as partial differential equations exhibiting increasingly complex and intricate behaviors. Our framework significantly outperforms EDMD-DL. Furthermore, the state space approach offers superior performance compared to the 'pure' Koopman approach where the entire time evolution occurs in the space of observables. When the temporal evolution of the Koopman approach alternates between states and observables at each time step, however, its predictions become comparable to those of the state space approach.

In the stochastic gradient descent (SGD) for sequential simulations such as the neural stochastic differential equations, the Multilevel Monte Carlo (MLMC) method is known to offer better theoretical computational complexity compared to the naive Monte Carlo approach. However, in practice, MLMC scales poorly on massively parallel computing platforms such as modern GPUs, because of its large parallel complexity which is equivalent to that of the naive Monte Carlo method. To cope with this issue, we propose the delayed MLMC gradient estimator that drastically reduces the parallel complexity of MLMC by recycling previously computed gradient components from earlier steps of SGD. The proposed estimator provably reduces the average parallel complexity per iteration at the cost of a slightly worse per-iteration convergence rate. In our numerical experiments, we use an example of deep hedging to demonstrate the superior parallel complexity of our method compared to the standard MLMC in SGD.

We revisit the problem of learning a single neuron with ReLU activation under Gaussian input with square loss. We particularly focus on the over-parameterization setting where the student network has $n\ge 2$ neurons. We prove the global convergence of randomly initialized gradient descent with a $O\left(T^{-3}\right)$ rate. This is the first global convergence result for this problem beyond the exact-parameterization setting ($n=1$) in which the gradient descent enjoys an $\exp(-\Omega(T))$ rate. Perhaps surprisingly, we further present an $\Omega\left(T^{-3}\right)$ lower bound for randomly initialized gradient flow in the over-parameterization setting. These two bounds jointly give an exact characterization of the convergence rate and imply, for the first time, that over-parameterization can exponentially slow down the convergence rate. To prove the global convergence, we need to tackle the interactions among student neurons in the gradient descent dynamics, which are not present in the exact-parameterization case. We use a three-phase structure to analyze GD's dynamics. Along the way, we prove gradient descent automatically balances student neurons, and use this property to deal with the non-smoothness of the objective function. To prove the convergence rate lower bound, we construct a novel potential function that characterizes the pairwise distances between the student neurons (which cannot be done in the exact-parameterization case). We show this potential function converges slowly, which implies the slow convergence rate of the loss function.

Federated reinforcement learning (FedRL) enables agents to collaboratively train a global policy without sharing their individual data. However, high communication overhead remains a critical bottleneck, particularly for natural policy gradient (NPG) methods, which are second-order. To address this issue, we propose the FedNPG-ADMM framework, which leverages the alternating direction method of multipliers (ADMM) to approximate global NPG directions efficiently. We theoretically demonstrate that using ADMM-based gradient updates reduces communication complexity from ${O}({d^{2}})$ to ${O}({d})$ at each iteration, where $d$ is the number of model parameters. Furthermore, we show that achieving an $\epsilon$-error stationary convergence requires ${O}(\frac{1}{(1-\gamma)^{2}{\epsilon}})$ iterations for discount factor $\gamma$, demonstrating that FedNPG-ADMM maintains the same convergence rate as the standard FedNPG. Through evaluation of the proposed algorithms in MuJoCo environments, we demonstrate that FedNPG-ADMM maintains the reward performance of standard FedNPG, and that its convergence rate improves when the number of federated agents increases.

Training a modern machine learning architecture on a new task requires extensive learning-rate tuning, which comes at a high computational cost. Here we develop new adaptive learning rates that can be used with any momentum method, and require less tuning to perform well. We first develop MoMo, a Momentum Model based adaptive learning rate for SGD-M (Stochastic gradient descent with momentum). MoMo uses momentum estimates of the batch losses and gradients sampled at each iteration to build a model of the loss function. Our model also makes use of any known lower bound of the loss function by using truncation, e.g. most losses are lower-bounded by zero. We then approximately minimize this model at each iteration to compute the next step. We show how MoMo can be used in combination with any momentum-based method, and showcase this by developing MoMo-Adam - which is Adam with our new model-based adaptive learning rate. Additionally, for losses with unknown lower bounds, we develop on-the-fly estimates of a lower bound, that are incorporated in our model. Through extensive numerical experiments, we demonstrate that MoMo and MoMo-Adam improve over SGD-M and Adam in terms of accuracy and robustness to hyperparameter tuning for training image classifiers on MNIST, CIFAR10, CIFAR100, Imagenet, recommender systems on the Criteo dataset, and a transformer model on the translation task IWSLT14.

Attention to data-driven optimization approaches, including the well-known stochastic gradient descent method, has grown significantly over recent decades, but data-driven constraints have rarely been studied, because of the computational challenges of projections onto the feasible set defined by these hard constraints. In this paper, we focus on the non-smooth convex-concave stochastic minimax regime and formulate the data-driven constraints as expectation constraints. The minimax expectation constrained problem subsumes a broad class of real-world applications, including two-player zero-sum game and data-driven robust optimization. We propose a class of efficient primal-dual algorithms to tackle the minimax expectation-constrained problem, and show that our algorithms converge at the optimal rate of $\mathcal{O}(\frac{1}{\sqrt{N}})$. We demonstrate the practical efficiency of our algorithms by conducting numerical experiments on large-scale real-world applications.

Many problems encountered in science and engineering can be formulated as estimating a low-rank object (e.g., matrices and tensors) from incomplete, and possibly corrupted, linear measurements. Through the lens of matrix and tensor factorization, one of the most popular approaches is to employ simple iterative algorithms such as gradient descent (GD) to recover the low-rank factors directly, which allow for small memory and computation footprints. However, the convergence rate of GD depends linearly, and sometimes even quadratically, on the condition number of the low-rank object, and therefore, GD slows down painstakingly when the problem is ill-conditioned. This chapter introduces a new algorithmic approach, dubbed scaled gradient descent (ScaledGD), that provably converges linearly at a constant rate independent of the condition number of the low-rank object, while maintaining the low per-iteration cost of gradient descent for a variety of tasks including sensing, robust principal component analysis and completion. In addition, ScaledGD continues to admit fast global convergence to the minimax-optimal solution, again almost independent of the condition number, from a small random initialization when the rank is over-specified in the presence of Gaussian noise. In total, ScaledGD highlights the power of appropriate preconditioning in accelerating nonconvex statistical estimation, where the iteration-varying preconditioners promote desirable invariance properties of the trajectory with respect to the symmetry in low-rank factorization without hurting generalization.