High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
- URL: http://arxiv.org/abs/2310.18784v7
- Date: Wed, 1 May 2024 02:30:23 GMT
- Title: High-probability Convergence Bounds for Nonlinear Stochastic Gradient Descent Under Heavy-tailed Noise
- Authors: Aleksandar Armacki, Pranay Sharma, Gauri Joshi, Dragana Bajovic, Dusan Jakovetic, Soummya Kar,
- Abstract summary: We show that wetailed high-prob convergence guarantees of learning on streaming data in the presence of heavy-tailed noise.
We demonstrate analytically and that $ta$ can be used to the preferred choice of setting for a given problem.
- Score: 59.25598762373543
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We study high-probability convergence guarantees of learning on streaming data in the presence of heavy-tailed noise. In the proposed scenario, the model is updated in an online fashion, as new information is observed, without storing any additional data. To combat the heavy-tailed noise, we consider a general framework of nonlinear stochastic gradient descent (SGD), providing several strong results. First, for non-convex costs and component-wise nonlinearities, we establish a convergence rate arbitrarily close to $\mathcal{O}\left(t^{-\frac{1}{4}}\right)$, whose exponent is independent of noise and problem parameters. Second, for strongly convex costs and component-wise nonlinearities, we establish a rate arbitrarily close to $\mathcal{O}\left(t^{-\frac{1}{2}}\right)$ for the weighted average of iterates, with exponent again independent of noise and problem parameters. Finally, for strongly convex costs and a broader class of nonlinearities, we establish convergence of the last iterate, with a rate $\mathcal{O}\left(t^{-\zeta} \right)$, where $\zeta \in (0,1)$ depends on problem parameters, noise and nonlinearity. As we show analytically and numerically, $\zeta$ can be used to inform the preferred choice of nonlinearity for given problem settings. Compared to state-of-the-art, who only consider clipping, require bounded noise moments of order $\eta \in (1,2]$, and establish convergence rates whose exponents go to zero as $\eta \rightarrow 1$, we provide high-probability guarantees for a much broader class of nonlinearities and symmetric density noise, with convergence rates whose exponents are bounded away from zero, even when the noise has finite first moment only. Moreover, in the case of strongly convex functions, we demonstrate analytically and numerically that clipping is not always the optimal nonlinearity, further underlining the value of our general framework.
Related papers
- Large Deviations and Improved Mean-squared Error Rates of Nonlinear SGD: Heavy-tailed Noise and Power of Symmetry [47.653744900375855]
We study large deviations and mean-squared error (MSE) guarantees a general framework of nonlinear convex gradient methods in the online setting.
We provide strong results for broad bound step-sizes in the presence of heavy noise symmetric density function.
arXiv Detail & Related papers (2024-10-21T04:50:57Z) - Nonlinear Stochastic Gradient Descent and Heavy-tailed Noise: A Unified Framework and High-probability Guarantees [56.80920351680438]
We study high-probability convergence in online learning, in the presence of heavy-tailed noise.
Compared to state-of-the-art, who only consider clipping and require noise with bounded $p$-th moments, we provide guarantees for a broad class of nonlinearities.
arXiv Detail & Related papers (2024-10-17T18:25:28Z) - Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems [56.86067111855056]
We consider clipped optimization problems with heavy-tailed noise with structured density.
We show that it is possible to get faster rates of convergence than $mathcalO(K-(alpha - 1)/alpha)$, when the gradients have finite moments of order.
We prove that the resulting estimates have negligible bias and controllable variance.
arXiv Detail & Related papers (2023-11-07T17:39:17Z) - Optimal Extragradient-Based Bilinearly-Coupled Saddle-Point Optimization [116.89941263390769]
We consider the smooth convex-concave bilinearly-coupled saddle-point problem, $min_mathbfxmax_mathbfyF(mathbfx) + H(mathbfx,mathbfy)$, where one has access to first-order oracles for $F$, $G$ as well as the bilinear coupling function $H$.
We present a emphaccelerated gradient-extragradient (AG-EG) descent-ascent algorithm that combines extragrad
arXiv Detail & Related papers (2022-06-17T06:10:20Z) - High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad
Stepsize [55.0090961425708]
We propose a new, simplified high probability analysis of AdaGrad for smooth, non- probability problems.
We present our analysis in a modular way and obtain a complementary $mathcal O (1 / TT)$ convergence rate in the deterministic setting.
To the best of our knowledge, this is the first high probability for AdaGrad with a truly adaptive scheme, i.e., completely oblivious to the knowledge of smoothness.
arXiv Detail & Related papers (2022-04-06T13:50:33Z) - Nonlinear gradient mappings and stochastic optimization: A general
framework with applications to heavy-tail noise [11.768495184175052]
We introduce a general framework for nonlinear gradient descent scenarios when gradient noise exhibits heavy tails.
We show that for a nonlinearity with bounded outputs and for the gradient noise that may not have finite moments of order greater than one, the nonlinear SGD converges to zero at rate$O(/tzeta)$, $zeta in (0,1)$.
Experiments show that, while our framework is more general than existing studies of SGD under heavy-tail noise, several easy-to-implement nonlinearities from our framework are competitive with state of the art alternatives on real data sets
arXiv Detail & Related papers (2022-04-06T06:05:52Z) - Convergence Rates of Stochastic Gradient Descent under Infinite Noise
Variance [14.06947898164194]
Heavy tails emerge in gradient descent (SGD) in various scenarios.
We provide convergence guarantees for SGD under a state-dependent and heavy-tailed noise with a potentially infinite variance.
Our results indicate that even under heavy-tailed noise with infinite variance, SGD can converge to the global optimum.
arXiv Detail & Related papers (2021-02-20T13:45:11Z) - Last iterate convergence of SGD for Least-Squares in the Interpolation
regime [19.05750582096579]
We study the noiseless model in the fundamental least-squares setup.
We assume that an optimum predictor fits perfectly inputs and outputs $langle theta_*, phi(X) rangle = Y$, where $phi(X)$ stands for a possibly infinite dimensional non-linear feature map.
arXiv Detail & Related papers (2021-02-05T14:02:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.