More Like this

1. Understanding the acceleration phenomenon via high-resolution differential equations

   https://doi.org/10.1007/s10107-021-01681-8  

   Shi, Bin ; Du, Simon S. ; Jordan, Michael I. ; Su, Weijie J. ( July 2021 , Mathematical Programming)

   Gradient-based optimization algorithms can be studied from the perspective of limiting ordinary differential equations (ODEs). Motivated by the fact that existing ODEs do not distinguish between two fundamentally different algorithms—Nesterov’s accelerated gradient method for strongly convex functions (NAG-) and Polyak’s heavy-ball method—we study an alternative limiting process that yieldshigh-resolution ODEs. We show that these ODEs permit a general Lyapunov function framework for the analysis of convergence in both continuous and discrete time. We also show that these ODEs are more accurate surrogates for the underlying algorithms; in particular, they not only distinguish between NAG- and Polyak’s heavy-ball method, but they allow the identification of a term that we refer to as “gradient correction” that is present in NAG- but not in the heavy-ball method and is responsible for the qualitative difference in convergence of the two methods. We also use the high-resolution ODE framework to study Nesterov’s accelerated gradient method for (non-strongly) convex functions, uncovering a hitherto unknown result—that NAG- minimizes the squared gradient norm at an inverse cubic rate. Finally, by modifying the high-resolution ODE of NAG-, we obtain a family of new optimization methods that are shown to maintain the accelerated convergence rates of NAG- for smoothmore »convex functions.

   « less
2. Continuous Time Analysis of Momentum Methods

   Kovachki, Nikola ; Stuart, Andrew M. ( January 2021 , Journal of machine learning research)

   Gradient descent-based optimization methods underpin the parameter training of neural networks, and hence comprise a significant component in the impressive test results found in a number of applications. Introducing stochasticity is key to their success in practical problems, and there is some understanding of the role of stochastic gradient descent in this context. Momentum modifications of gradient descent such as Polyak’s Heavy Ball method (HB) and Nesterov’s method of accelerated gradients (NAG), are also widely adopted. In this work our focus is on understanding the role of momentum in the training of neural networks, concentrating on the common situation in which the momentum contribution is fixed at each step of the algorithm. To expose the ideas simply we work in the deterministic setting. Our approach is to derive continuous time approximations of the discrete algorithms; these continuous time approximations provide insights into the mechanisms at play within the discrete algorithms. We prove three such approximations. Firstly we show that standard implementations of fixed momentum methods approximate a time-rescaled gradient descent flow, asymptotically as the learning rate shrinks to zero; this result does not distinguish momentum methods from pure gradient descent, in the limit of vanishing learning rate. We then proceedmore »to prove two results aimed at understanding the observed practical advantages of fixed momentum methods over gradient descent, when implemented in the non-asymptotic regime with fixed small, but non-zero, learning rate. We achieve this by proving approximations to continuous time limits in which the small but fixed learning rate appears as a parameter; this is known as the method of modified equations in the numerical analysis literature, recently rediscovered as the high resolution ODE approximation in the machine learning context. In our second result we show that the momentum method is approximated by a continuous time gradient flow, with an additional momentum-dependent second order time-derivative correction, proportional to the learning rate; this may be used to explain the stabilizing effect of momentum algorithms in their transient phase. Furthermore in a third result we show that the momentum methods admit an exponentially attractive invariant manifold on which the dynamics reduces, approximately, to a gradient flow with respect to a modified loss function, equal to the original loss function plus a small perturbation proportional to the learning rate; this small correction provides convexification of the loss function and encodes additional robustness present in momentum methods, beyond the transient phase.« less
3. High-Resolution Modeling of the Fastest First-Order Optimization Method for Strongly Convex Functions

   https://doi.org/10.1109/CDC42340.2020.9304444  

   Sun, Boya ; George, Jemin ; Kia, Solmaz ( December 2020 , 2020 59th IEEE Conference on Decision and Control (CDC))

   Motivated by the fact that the gradient-based optimization algorithms can be studied from the perspective of limiting ordinary differential equations (ODEs), here we derive an ODE representation of the accelerated triple momentum (TM) algorithm. For unconstrained optimization problems with strongly convex cost, the TM algorithm has a proven faster convergence rate than the Nesterov's accelerated gradient (NAG) method but with the same computational complexity. We show that similar to the NAG method, in order to accurately capture the characteristics of the TM method, we need to use a high-resolution modeling to obtain the ODE representation of the TM algorithm. We propose a Lyapunov analysis to investigate the stability and convergence behavior of the proposed high-resolution ODE representation of the TM algorithm. We compare the rate of the ODE representation of the TM method with that of the NAG method to confirm its faster convergence. Our study also leads to a tighter bound on the worst rate of convergence for the ODE model of the NAG method. In this paper, we also discuss the use of the integral quadratic constraint (IQC) method to establish an estimate on the rate of convergence of the TM algorithm. A numerical example verifies our results.
4. From differential equation solvers to accelerated first-order methods for convex optimization

   https://doi.org/10.1007/s10107-021-01713-3  

   Luo, Hao ; Chen, Long ( October 2021 , Mathematical Programming)

   Convergence analysis of accelerated first-order methods for convex optimization problems are developed from the point of view of ordinary differential equation solvers. A new dynamical system, called Nesterov accelerated gradient (NAG) flow, is derived from the connection between acceleration mechanism andA-stability of ODE solvers, and the exponential decay of a tailored Lyapunov function along with the solution trajectory is proved. Numerical discretizations of NAG flow are then considered and convergence rates are established via a discrete Lyapunov function. The proposed differential equation solver approach can not only cover existing accelerated methods, such as FISTA, Güler’s proximal algorithm and Nesterov’s accelerated gradient method, but also produce new algorithms for composite convex optimization that possess accelerated convergence rates. Both the convex and the strongly convex cases are handled in a unified way in our approach.
5. Supervised Learning via Ensemble Tensor Completion

   https://doi.org/10.1109/IEEECONF51394.2020.9443399  

   Kargas, Nikos ; Sidiropoulos, Nicholas D. ( November 2020 , 2020 Asilomar Conference on on Signals, Systems, and Computers)

   Learning nonlinear functions from input-output data pairs is one of the most fundamental problems in machine learning. Recent work has formulated the problem of learning a general nonlinear multivariate function of discrete inputs, as a tensor completion problem with smooth latent factors. We build upon this idea and utilize two ensemble learning techniques to enhance its prediction accuracy. Ensemble methods can be divided into two main groups, parallel and sequential. Bagging also known as bootstrap aggregation is a parallel ensemble method where multiple base models are trained in parallel on different subsets of the data that have been chosen randomly with replacement from the original training data. The output of these models is usually combined and a single prediction is computed using averaging. One of the most popular bagging techniques is random forests. Boosting is a sequential ensemble method where a sequence of base models are fit sequentially to modified versions of the data. Popular boosting algorithms include AdaBoost and Gradient Boosting. We develop two approaches based on these ensemble learning techniques for learning multivariate functions using the Canonical Polyadic Decomposition. We showcase the effectiveness of the proposed ensemble models on several regression tasks and report significant improvements compared tomore »the single model.« less