Anderson mixing (or Anderson acceleration) is an efficient acceleration method for fixed point iterations (i.e., $x_{t+1}=G(x_t)$), e.g., gradient descent can be viewed as iteratively applying the operation $G(x) = x-\alpha\nabla f(x)$. It is known that Anderson mixing is quite efficient in practice and can be viewed as an extension of Krylov subspace methods for nonlinear problems. First, we show that Anderson mixing with Chebyshev polynomial parameters can achieve the optimal convergence rate $O(\sqrt{\kappa}\ln\frac{1}{\epsilon})$, which improves the previous result $O(\kappa\ln\frac{1}{\epsilon})$ provided by [Toth and Kelley, 2015] for quadratic functions. Then, we provide a convergence analysis for minimizing general nonlinear problems. Besides, if the hyperparameters (e.g., the Lipschitz smooth parameter $L$) are not available, we propose a Guessing Algorithm for guessing them dynamically and also prove a similar convergence rate. Finally, the experimental results demonstrate that the proposed Anderson-Chebyshev mixing method converges significantly faster than other algorithms, e.g., vanilla gradient descent (GD), Nesterov's Accelerated GD. Also, these algorithms combined with the proposed guessing algorithm (guessing the hyperparameters dynamically) achieve much better performance.

Many machine learning, statistical inference, and portfolio optimization problems require minimization of a composition of expected value functions (CEVF). Of particular interest is the finite-sum versions of such compositional optimization problems (FS-CEVF). Compositional stochastic variance reduced gradient (C-SVRG) methods that combine stochastic compositional gradient descent (SCGD) and stochastic variance reduced gradient descent (SVRG) methods are the state-of-the-art methods for FS-CEVF problems. We introduce compositional stochastic average gradient descent (C-SAG) a novel extension of the stochastic average gradient method (SAG) to minimize composition of finite-sum functions. C-SAG, like SAG, estimates gradient by incorporating memory of previous gradient information. We present theoretical analyses of C-SAG which show that C-SAG, like SAG, and C-SVRG, achieves a linear convergence rate when the objective function is strongly convex; However, C-CAG achieves lower oracle query complexity per iteration than C-SVRG. Finally, we present results of experiments showing that C-SAG converges substantially faster than full gradient (FG), as well as C-SVRG.

Variants of gradient descent (GD) dominate CNN loss minimization in computer vision. But, as we show, some powerful loss functions are practically useless only due to their poor optimization by GD. In the context of weakly-supervised CNN segmentation, we present a general ADM approach to regularized losses, which are inspired by well-known MRF/CRF models in "shallow" segmentation. While GD fails on the popular nearest-neighbor Potts loss, ADM splitting with $\alpha$-expansion solver significantly improves optimization of such grid CRF losses yielding state-of-the-art training quality. Denser CRF losses become amenable to basic GD, but they produce lower quality object boundaries in agreement with known noisy performance of dense CRF inference in shallow segmentation.

In this paper, we consider the convex and non-convex composition problem with the structure $\frac{1}{n}\sum\nolimits_{i = 1}^n {{F_i}( {G( x )} )}$, where $G( x )=\frac{1}{n}\sum\nolimits_{j = 1}^n {{G_j}( x )} $ is the inner function, and $F_i(\cdot)$ is the outer function. We explore the variance reduction based method to solve the composition optimization. Due to the fact that when the number of inner function and outer function are large, it is not reasonable to estimate them directly, thus we apply the stochastically controlled stochastic gradient (SCSG) method to estimate the gradient of the composition function and the value of the inner function. The query complexity of our proposed method for the convex and non-convex problem is equal to or better than the current method for the composition problem. Furthermore, we also present the mini-batch version of the proposed method, which has the improved the query complexity with related to the size of the mini-batch.

In this paper, we focus on escaping from saddle points in smooth nonconvex optimization problems subject to a convex set $\mathcal{C}$. We propose a generic framework that yields convergence to a second-order stationary point of the problem, if the convex set $\mathcal{C}$ is simple for a quadratic objective function. To be more precise, our results hold if one can find a $\rho$-approximate solution of a quadratic program subject to $\mathcal{C}$ in polynomial time, where $\rho<1$ is a positive constant that depends on the structure of the set $\mathcal{C}$. Under this condition, we show that the sequence of iterates generated by the proposed framework reaches an $(\epsilon,\gamma)$-second order stationary point (SOSP) in at most $\mathcal{O}(\max\{\epsilon^{-2},\rho^{-3}\gamma^{-3}\})$ iterations. We further characterize the overall arithmetic operations to reach an SOSP when the convex set $\mathcal{C}$ can be written as a set of quadratic constraints. Finally, we extend our results to the stochastic setting and characterize the number of stochastic gradient and Hessian evaluations to reach an $(\epsilon,\gamma)$-SOSP.

We develop new stochastic gradient methods for efficiently solving sparse linear regression in a partial attribute observation setting, where learners are only allowed to observe a fixed number of actively chosen attributes per example at training and prediction times. It is shown that the methods achieve essentially a sample complexity of $O(1/\varepsilon)$ to attain an error of $\varepsilon$ under a variant of restricted eigenvalue condition, and the rate has better dependency on the problem dimension than existing methods. Particularly, if the smallest magnitude of the non-zero components of the optimal solution is not too small, the rate of our proposed {\it Hybrid} algorithm can be boosted to near the minimax optimal sample complexity of {\it full information} algorithms. The core ideas are (i) efficient construction of an unbiased gradient estimator by the iterative usage of the hard thresholding operator for configuring an exploration algorithm; and (ii) an adaptive combination of the exploration and an exploitation algorithms for quickly identifying the support of the optimum and efficiently searching the optimal parameter in its support. Experimental results are presented to validate our theoretical findings and the superiority of our proposed methods.

We present a novel regularization approach to train neural networks that enjoys better generalization and test error than standard stochastic gradient descent. Our approach is based on the principles of cross-validation, where a validation set is used to limit the model overfitting. We formulate such principles as a bilevel optimization problem. This formulation allows us to define the optimization of a cost on the validation set subject to another optimization on the training set. The overfitting is controlled by introducing weights on each mini-batch in the training set and by choosing their values so that they minimize the error on the validation set. In practice, these weights define mini-batch learning rates in a gradient descent update equation that favor gradients with better generalization capabilities. Because of its simplicity, this approach can be integrated with other regularization methods and training schemes. We evaluate extensively our proposed algorithm on several neural network architectures and datasets, and find that it consistently improves the generalization of the model, especially when labels are noisy.

Particle-optimization sampling (POS) is a recently developed technique to generate high-quality samples from a target distribution by iteratively updating a set of interactive particles. A representative algorithm is the Stein variational gradient descent (SVGD). Though obtaining significant empirical success, the {\em non-asymptotic} convergence behavior of SVGD remains unknown. In this paper, we generalize POS to a stochasticity setting by injecting random noise in particle updates, called stochastic particle-optimization sampling (SPOS). Standard SVGD can be regarded as a special case of our framework. Notably, for the first time, we develop non-asymptotic convergence theory for the SPOS framework (which includes SVGD), characterizing the bias of a sample approximation w.r.t. the numbers of particles and iterations under both convex- and noncovex-energy-function settings. Remarkably, we provide theoretical understand of a pitfall of SVGD that can be avoided in the proposed SPOS framework, i.e., particles tent to collapse to a local mode in SVGD under some particular conditions. Our theory is based on the analysis of nonlinear stochastic differential equations, which serves as an extension and a complemented development to the asymptotic convergence theory for SVGD such as [1].

Although stochastic gradient descent (SGD) method and its variants (e.g., stochastic momentum methods, AdaGrad) are the choice of algorithms for solving non-convex problems (especially deep learning), there still remain big gaps between the theory and the practice with many questions unresolved. For example, there is still a lack of theories of convergence for SGD and its variants that use stagewise step size and return an averaged solution in practice. In addition, theoretical insights of why adaptive step size of AdaGrad could improve non-adaptive step size of {\sgd} is still missing for non-convex optimization. This paper aims to address these questions and fill the gap between theory and practice. We propose a universal stagewise optimization framework for a broad family of {\bf non-smooth non-convex} (namely weakly convex) problems with the following key features: (i) at each stage any suitable stochastic convex optimization algorithms (e.g., SGD or AdaGrad) that return an averaged solution can be employed for minimizing a regularized convex problem; (ii) the step size is decreased in a stagewise manner; (iii) an averaged solution is returned as the final solution that is selected from all stagewise averaged solutions with sampling probabilities {\it increasing} as the stage number. Our theoretical results of stagewise AdaGrad exhibit its adaptive convergence, therefore shed insights on its faster convergence for problems with sparse stochastic gradients than stagewise SGD. To the best of our knowledge, these new results are the first of their kind for addressing the unresolved issues of existing theories mentioned earlier.

Gradient boosting is a prediction method that iteratively combines weak learners to produce a complex and accurate model. From an optimization point of view, the learning procedure of gradient boosting mimics a gradient descent on a functional variable. This paper proposes to build upon the proximal point algorithm when the empirical risk to minimize is not differentiable. In addition, the novel boosting approach, called accelerated proximal boosting, benefits from Nesterov's acceleration in the same way as gradient boosting [Biau et al., 2018]. Advantages of leveraging proximal methods for boosting are illustrated by numerical experiments on simulated and real-world data. In particular, we exhibit a favorable comparison over gradient boosting regarding convergence rate and prediction accuracy.