More Like this

1. An Explicit Convergence Rate for Nesterov’s Method from SDP

   Safavi, Sam; Joshi, Bikash; França, Guilherme; Bento, José (June 2018, 2018 IEEE International Symposium on In Information Theory)

   The framework of Integral Quadratic Constraints (IQC) introduced by Lessard et al. (2014) reduces the com- putation of upper bounds on the convergence rate of several optimization algorithms to semi-definite programming (SDP). In particular, this technique was applied to Nesterov’s accelerated method (NAM). For quadratic functions, this SDP was explicitly solved leading to a new bound on the convergence rate of NAM, and for arbitrary strongly convex functions it was shown numerically that IQC can improve bounds from Nesterov (2004). Unfortunately, an explicit analytic solution to the SDP was not provided. In this paper, we provide such an analytical solution, obtaining a new general and explicit upper bound on the convergence rate of NAM, which we further optimize over its parameters. To the best of our knowledge, this is the best, and explicit, upper bound on the convergence rate of NAM for strongly convex functions. 

   more » « less
2. A Unified Analysis of First-Order Methods for Smooth Games via Integral Quadratic Constraints

   Zhang, Guodong; Bao, Xuchan; Lessard, Laurent; Grosse, Roger (January 2021, Journal of machine learning research)

   The theory of integral quadratic constraints (IQCs) allows the certification of exponential convergence of interconnected systems containing nonlinear or uncertain elements. In this work, we adapt the IQC theory to study first-order methods for smooth and strongly-monotone games and show how to design tailored quadratic constraints to get tight upper bounds of convergence rates. Using this framework, we recover the existing bound for the gradient method~(GD), derive sharper bounds for the proximal point method~(PPM) and optimistic gradient method~(OG), and provide for the first time a global convergence rate for the negative momentum method~(NM) with an iteration complexity O(κ1.5), which matches its known lower bound. In addition, for time-varying systems, we prove that the gradient method with optimal step size achieves the fastest provable worst-case convergence rate with quadratic Lyapunov functions. Finally, we further extend our analysis to stochastic games and study the impact of multiplicative noise on different algorithms. We show that it is impossible for an algorithm with one step of memory to achieve acceleration if it only queries the gradient once per batch (in contrast with the stochastic strongly-convex optimization setting, where such acceleration has been demonstrated). However, we exhibit an algorithm which achieves acceleration with two gradient queries per batch. 

   more » « less
3. Performance of noisy Nesterov's accelerated method for strongly convex optimization problems

   https://doi.org/10.23919/ACC.2019.8814680  

   Mohammadi, Hesameddin; Razaviyayn, Meisam; Jovanovic, Mihailo R. (July 2019, 2019 American Control Conference (ACC))

   We study the performance of noisy gradient descent and Nesterov's accelerated methods for strongly convex objective functions with Lipschitz continuous gradients. The steady-state second-order moment of the error in the iterates is analyzed when the gradient is perturbed by an additive white noise with zero mean and identity covariance. For any given condition number κ, we derive explicit upper bounds on noise amplification that only depend on κ and the problem size. We use quadratic objective functions to derive lower bounds and to demonstrate that the upper bounds are tight up to a constant factor. The established upper bound for Nesterov's accelerated method is larger than the upper bound for gradient descent by a factor of √κ. This gap identifies a fundamental tradeoff that comes with acceleration in the presence of stochastic uncertainties in the gradient evaluation. 

   more » « less
4. High Probability Convergence of Stochastic Gradient Methods

   Liu, Zijian; Nguyen, Ta Duy; Nguyen, Thien Hang; Ene, Alina; Nguyen, Huy (July 2023, International Conference on Machine Learning)

   In this work, we describe a generic approach to show convergence with high probability for both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous works for convex optimization, either the convergence is only in expectation or the bound depends on the diameter of the domain. Instead, we show high probability convergence with bounds depending on the initial distance to the optimal solution. The algorithms use step sizes analogous to the standard settings and are universal to Lipschitz functions, smooth functions, and their linear combinations. The method can be applied to the non-convex case. We demonstrate an $$O((1+\sigma^{2}\log(1/\delta))/T+\sigma/\sqrt{T})$$ convergence rate when the number of iterations $$T$$ is known and an $$O((1+\sigma^{2}\log(T/\delta))/\sqrt{T})$$ convergence rate when $$T$$ is unknown for SGD, where $$1-\delta$$ is the desired success probability. These bounds improve over existing bounds in the literature. We also revisit AdaGrad-Norm (Ward et al., 2019) and show a new analysis to obtain a high probability bound that does not require the bounded gradient assumption made in previous works. The full version of our paper contains results for the standard per-coordinate AdaGrad. 

   more » « less
5. High Probability Convergence of Stochastic Gradient Methods

   Liu, Zijian; Nguyen, Ta Duy; Nguyen, Thien Hang; Nguyen, Huy (July 2023, Proceedings of Machine Learning Research)

   In this work, we describe a generic approach to show convergence with high probability for both stochastic convex and non-convex optimization with sub-Gaussian noise. In previous works for convex optimization, either the convergence is only in expectation or the bound depends on the diameter of the domain. Instead, we show high probability convergence with bounds depending on the initial distance to the optimal solution. The algorithms use step sizes analogous to the standard settings and are universal to Lipschitz functions, smooth functions, and their linear combinations. The method can be applied to the non-convex case. We demonstrate an $$O((1+\sigma^{2}\log(1/\delta))/T+\sigma/\sqrt{T})$$ convergence rate when the number of iterations $$T$$ is known and an $$O((1+\sigma^{2}\log(T/\delta))/\sqrt{T})$$ convergence rate when $$T$$ is unknown for SGD, where $$1-\delta$$ is the desired success probability. These bounds improve over existing bounds in the literature. We also revisit AdaGrad-Norm \cite{ward2019adagrad} and show a new analysis to obtain a high probability bound that does not require the bounded gradient assumption made in previous works. The full version of our paper contains results for the standard per-coordinate AdaGrad. 

   more » « less