More Like this

1. Momentum-Based Variance Reduction in Non-Convex SGD

   Cutkosky, Ashok; Orabona, Francesco (January 2019, Advances in neural information processing systems)

   Wallach, H.; Larochelle, H.; Beygelzimer, A.; d'Alché-Buc, F.; Fox, E.; Garnett, R. (Ed.)

   Variance reduction has emerged in recent years as a strong competitor to stochastic gradient descent in non-convex problems, providing the first algorithms to improve upon the converge rate of stochastic gradient descent for finding first-order critical points. However, variance reduction techniques typically require carefully tuned learning rates and willingness to use excessively large "mega-batches" in order to achieve their improved results. We present a new algorithm, STORM, that does not require any batches and makes use of adaptive learning rates, enabling simpler implementation and less hyperparameter tuning. Our technique for removing the batches uses a variant of momentum to achieve variance reduction in non-convex optimization. On smooth losses $$F$$, STORM finds a point $$\boldsymbol{x}$$ with $$E[\|\nabla F(\boldsymbol{x})\|]\le O(1/\sqrt{T}+\sigma^{1/3}/T^{1/3})$$ in $$T$$ iterations with $$\sigma^2$$ variance in the gradients, matching the optimal rate and without requiring knowledge of $$\sigma$$. 

   more » « less
2. The Complexity of Making the Gradient Small in Stochastic Convex Optimization

   Foster, Dylan Y; Sekhari, Ayush; Shamir, Ohad; Srebro, Nathan; Sridharan, Karthik; Woodworth, Blake (June 2019, Proceedings of Machine Learning Research)

   We give nearly matching upper and lower bounds on the oracle complexity of finding ϵ-stationary points (∥∇F(x)∥≤ϵ in stochastic convex optimization. We jointly analyze the oracle complexity in both the local stochastic oracle model and the global oracle (or, statistical learning) model. This allows us to decompose the complexity of finding near-stationary points into optimization complexity and sample complexity, and reveals some surprising differences between the complexity of stochastic optimization versus learning. Notably, we show that in the global oracle/statistical learning model, only logarithmic dependence on smoothness is required to find a near-stationary point, whereas polynomial dependence on smoothness is necessary in the local stochastic oracle model. In other words, the separation in complexity between the two models can be exponential, and the folklore understanding that smoothness is required to find stationary points is only weakly true for statistical learning. Our upper bounds are based on extensions of a recent “recursive regularization” technique proposed by Allen-Zhu (2018). We show how to extend the technique to achieve near-optimal rates, and in particular show how to leverage the extra information available in the global oracle model. Our algorithm for the global model can be implemented efficiently through finite sum methods, and suggests an interesting new computational-statistical tradeoff 

   more » « less
3. Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization.

   Ge, Rong; Li, Zhize; Wang, Weiyao; Wang, Xiang (June 2019, The 32’nd Annual Conference on Learning Theory (COLT 2019))

   Variance reduction techniques like SVRG provide simple and fast algorithms for optimizing a convex finite-sum objective. For nonconvex objectives, these techniques can also find a first-order stationary point (with small gradient). However, in nonconvex optimization it is often crucial to find a second-order stationary point (with small gradient and almost PSD hessian). In this paper, we show that Stabilized SVRG (a simple variant of SVRG) can find an \eps-second-order stationary point using only O(n^{2/3}/\eps^2+n/\eps^{1.5}) stochastic gradients. To our best knowledge, this is the first second-order guarantee for a simple variant of SVRG. The running time almost matches the known guarantees for finding \eps-first-order stationary points. 

   more » « less
4. Improved Complexity for Smooth Nonconvex Optimization: A Two-Level Online Learning Approach with Quasi-Newton Methods

   https://doi.org/10.1145/3717823.3718308  

   Jiang, Ruichen; Mokhtari, Aryan; Patitucci, Francisco (June 2025, ACM)

   We study the problem of finding an 𝜀-first-order stationary point (FOSP) of a smooth function, given access only to gradient information. The best-known gradient query complexity for this task, assuming both the gradient and Hessian of the objective function are Lipschitz continuous, is O(𝜀−7/4). In this work, we propose a method with a gradient complexity of O(𝑑1/4𝜀−13/8), where 𝑑 is the problem dimension, leading to an improved complexity when 𝑑 = O(𝜀−1/2). To achieve this result, we design an optimization algorithm that, underneath, involves solving two online learning problems. Specifically, we first reformulate the task of finding a stationary point for a nonconvex problem as minimizing the regret in an online convex optimization problem, where the loss is determined by the gradient of the objective function. Then, we introduce a novel optimistic quasi-Newton method to solve this online learning problem, with the Hessian approximation update itself framed as an online learning problem in the space of matrices. Beyond improving the complexity bound for achieving an 𝜀-FOSP using a gradient oracle, our result provides the first guarantee suggesting that quasi-Newton methods can potentially outperform gradient descent-type methods in nonconvex settings. 

   more » « less
5. Provable Complexity Improvement of AdaGrad over SGD: Upper and Lower Bounds in Stochastic Non-Convex Optimization

   Jiang, R; Maladkar, D; Mokhtari, A (June 2025, https://doi.org/10.48550/arXiv.2406.04592)

   Adaptive gradient methods, such as AdaGrad, are among the most successful optimization algorithms for neural network training. While these methods are known to achieve better dimensional dependence than stochastic gradient descent (SGD) for stochastic convex optimization under favorable geometry, the theoretical justification for their success in stochastic non-convex optimization remains elusive. In fact, under standard assumptions of Lipschitz gradients and bounded noise variance, it is known that SGD is worst-case optimal in terms of finding a near-stationary point with respect to the l2-norm, making further improvements impossible. Motivated by this limitation, we introduce refined assumptions on the smoothness structure of the objective and the gradient noise variance, which better suit the coordinate-wise nature of adaptive gradient methods. Moreover, we adopt the l1-norm of the gradient as the stationarity measure, as opposed to the standard l2-norm, to align with the coordinate-wise analysis and obtain tighter convergence guarantees for AdaGrad. Under these new assumptions and the l1-norm stationarity measure, we establish an upper bound on the convergence rate of AdaGrad and a corresponding lower bound for SGD. In particular, we identify non-convex settings in which the iteration complexity of AdaGrad is favorable over SGD and show that, for certain configurations of problem parameters, it outperforms SGD by a factor of d, where d is the problem dimension. To the best of our knowledge, this is the first result to demonstrate a provable gain of adaptive gradient methods over SGD in a non-convex setting. We also present supporting lower bounds, including one specific to AdaGrad and one applicable to general deterministic first-order methods, showing that our upper bound for AdaGrad is tight and unimprovable up to a logarithmic factor under certain conditions. 

   more » « less