Robust Stochastic Optimization via Gradient Quantile Clipping
- URL: http://arxiv.org/abs/2309.17316v2
- Date: Sat, 12 Oct 2024 11:42:27 GMT
- Title: Robust Stochastic Optimization via Gradient Quantile Clipping
- Authors: Ibrahim Merad, Stéphane Gaïffas,
- Abstract summary: We introduce a quant clipping strategy for Gradient Descent (SGD)
We use gradient new outliers as norm clipping chains.
We propose an implementation of the algorithm using Huberiles.
- Score: 6.2844649973308835
- License:
- Abstract: We introduce a clipping strategy for Stochastic Gradient Descent (SGD) which uses quantiles of the gradient norm as clipping thresholds. We prove that this new strategy provides a robust and efficient optimization algorithm for smooth objectives (convex or non-convex), that tolerates heavy-tailed samples (including infinite variance) and a fraction of outliers in the data stream akin to Huber contamination. Our mathematical analysis leverages the connection between constant step size SGD and Markov chains and handles the bias introduced by clipping in an original way. For strongly convex objectives, we prove that the iteration converges to a concentrated distribution and derive high probability bounds on the final estimation error. In the non-convex case, we prove that the limit distribution is localized on a neighborhood with low gradient. We propose an implementation of this algorithm using rolling quantiles which leads to a highly efficient optimization procedure with strong robustness properties, as confirmed by our numerical experiments.
Related papers
- Fast Unconstrained Optimization via Hessian Averaging and Adaptive Gradient Sampling Methods [0.3222802562733786]
We consider minimizing finite-sum expectation objective functions via Hessian-averaging based subsampled Newton methods.
These methods allow for inexactness and have fixed per-it Hessian approximation costs.
We present novel analysis techniques and propose challenges for their practical implementation.
arXiv Detail & Related papers (2024-08-14T03:27:48Z) - Sampling from Gaussian Process Posteriors using Stochastic Gradient
Descent [43.097493761380186]
gradient algorithms are an efficient method of approximately solving linear systems.
We show that gradient descent produces accurate predictions, even in cases where it does not converge quickly to the optimum.
Experimentally, gradient descent achieves state-of-the-art performance on sufficiently large-scale or ill-conditioned regression tasks.
arXiv Detail & Related papers (2023-06-20T15:07:37Z) - Faster One-Sample Stochastic Conditional Gradient Method for Composite
Convex Minimization [61.26619639722804]
We propose a conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms.
The proposed method, equipped with an average gradient (SAG) estimator, requires only one sample per iteration. Nevertheless, it guarantees fast convergence rates on par with more sophisticated variance reduction techniques.
arXiv Detail & Related papers (2022-02-26T19:10:48Z) - Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and
Beyond [63.59034509960994]
We study shuffling-based variants: minibatch and local Random Reshuffling, which draw gradients without replacement.
For smooth functions satisfying the Polyak-Lojasiewicz condition, we obtain convergence bounds which show that these shuffling-based variants converge faster than their with-replacement counterparts.
We propose an algorithmic modification called synchronized shuffling that leads to convergence rates faster than our lower bounds in near-homogeneous settings.
arXiv Detail & Related papers (2021-10-20T02:25:25Z) - COCO Denoiser: Using Co-Coercivity for Variance Reduction in Stochastic
Convex Optimization [4.970364068620608]
We exploit convexity and L-smoothness to improve the noisy estimates outputted by the gradient oracle.
We show that increasing the number and proximity of the queried points leads to better gradient estimates.
We also apply COCO in vanilla settings by plugging it in existing algorithms, such as SGD, Adam or STRSAGA.
arXiv Detail & Related papers (2021-09-07T17:21:09Z) - Heavy-tailed Streaming Statistical Estimation [58.70341336199497]
We consider the task of heavy-tailed statistical estimation given streaming $p$ samples.
We design a clipped gradient descent and provide an improved analysis under a more nuanced condition on the noise of gradients.
arXiv Detail & Related papers (2021-08-25T21:30:27Z) - Differentiable Annealed Importance Sampling and the Perils of Gradient
Noise [68.44523807580438]
Annealed importance sampling (AIS) and related algorithms are highly effective tools for marginal likelihood estimation.
Differentiability is a desirable property as it would admit the possibility of optimizing marginal likelihood as an objective.
We propose a differentiable algorithm by abandoning Metropolis-Hastings steps, which further unlocks mini-batch computation.
arXiv Detail & Related papers (2021-07-21T17:10:14Z) - High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise [51.31435087414348]
It is essential to theoretically guarantee that algorithms provide small objective residual with high probability.
Existing methods for non-smooth convex optimization have complexity bounds with dependence on confidence level.
We propose novel stepsize rules for two methods with gradient clipping.
arXiv Detail & Related papers (2021-06-10T17:54:21Z) - Stochastic Reweighted Gradient Descent [4.355567556995855]
We propose an importance-sampling-based algorithm we call SRG (stochastic reweighted gradient)
We pay particular attention to the time and memory overhead of our proposed method.
We present empirical results to support our findings.
arXiv Detail & Related papers (2021-03-23T04:09:43Z) - Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box
Optimization Framework [100.36569795440889]
This work is on the iteration of zero-th-order (ZO) optimization which does not require first-order information.
We show that with a graceful design in coordinate importance sampling, the proposed ZO optimization method is efficient both in terms of complexity as well as as function query cost.
arXiv Detail & Related papers (2020-12-21T17:29:58Z)
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.