High Probability Guarantees for Random Reshuffling

• URL: http://arxiv.org/abs/2311.11841v2
• Date: Fri, 8 Dec 2023 02:26:17 GMT
• Title: High Probability Guarantees for Random Reshuffling
• Authors: Hengxu Yu, Xiao Li
• Abstract summary: We consider the gradient method with random reshuffling ($mathsfRR$) for tackling nonmathp optimization problems. In this work, we first investigate the neural sample complexity for $mathsfRR$s sampling procedure. Then, we design a random reshuffling method ($mathsfp$mathsfRR$) that involves an additional randomized perturbation procedure stationary points.
• Score: 5.663909018247509
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the stochastic gradient method with random reshuffling ($\mathsf{RR}$) for tackling smooth nonconvex optimization problems. $\mathsf{RR}$ finds broad applications in practice, notably in training neural networks. In this work, we first investigate the concentration property of $\mathsf{RR}$'s sampling procedure and establish a new high probability sample complexity guarantee for driving the gradient (without expectation) below $\varepsilon$, which effectively characterizes the efficiency of a single $\mathsf{RR}$ execution. Our derived complexity matches the best existing in-expectation one up to a logarithmic term while imposing no additional assumptions nor changing $\mathsf{RR}$'s updating rule. Furthermore, by leveraging our derived high probability descent property and bound on the stochastic error, we propose a simple and computable stopping criterion for $\mathsf{RR}$ (denoted as $\mathsf{RR}$-$\mathsf{sc}$). This criterion is guaranteed to be triggered after a finite number of iterations, and then $\mathsf{RR}$-$\mathsf{sc}$ returns an iterate with its gradient below $\varepsilon$ with high probability. Moreover, building on the proposed stopping criterion, we design a perturbed random reshuffling method ($\mathsf{p}$-$\mathsf{RR}$) that involves an additional randomized perturbation procedure near stationary points. We derive that $\mathsf{p}$-$\mathsf{RR}$ provably escapes strict saddle points and efficiently returns a second-order stationary point with high probability, without making any sub-Gaussian tail-type assumptions on the stochastic gradient errors. Finally, we conduct numerical experiments on neural network training to support our theoretical findings.

Related papers

• Nonconvex Stochastic Optimization under Heavy-Tailed Noises: Optimal Convergence without Gradient Clipping [21.865728815935665]
  We provide the first convergence under heavy-tailed noises but without clipping. We also establish first $mathcalO(Tfrac1-mathfrakp3mathfrakp-2)$ convergence rate in the case where the tail index $mathfrakp$ is unknown in advance.
  arXiv  Detail & Related papers  (2024-12-27T08:46:46Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Mirror Descent Algorithms with Nearly Dimension-Independent Rates for Differentially-Private Stochastic Saddle-Point Problems [6.431793114484429]
  We propose $sqrtlog(d)/sqrtn + log(d)/[nvarepsilon]2/5$ to solve the problem of differentially-private saddle-points in the polyhedral setting. We show that our algorithms attain a rate of $sqrtlog(d)/sqrtn + log(d)/[nvarepsilon]2/5$ with constant success.
  arXiv  Detail & Related papers  (2024-03-05T12:28:00Z)
• A New Random Reshuffling Method for Nonsmooth Nonconvex Finite-sum Optimization [6.314057999212246]
  Random reshuffling techniques are used in large-scale applications, such as neural networks. In this paper, we show that the random reshuffling-type iterations generated by norm-PRR converge to a linear setting. Finally, we derive last convergence rates that can be applied to the proposed approach.
  arXiv  Detail & Related papers  (2023-12-02T07:12:00Z)
• Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging [8.990961435218544]
  We propose a first-order algorithm named $B$-sample dual averaging with the logarithmic barrier. For the Poisson inverse problem, our algorithm attains an $varepsilon$ solution in $smashtildeO(d3/varepsilon2)$ time. When computing the maximum-likelihood estimate for quantum state tomography, our algorithm yields an $varepsilon$-optimal solution in $smashtildeO(d3/varepsilon2)$ time.
  arXiv  Detail & Related papers  (2023-11-05T03:33:44Z)
• Near Optimal Heteroscedastic Regression with Symbiotic Learning [29.16456701187538]
  We consider the problem of heteroscedastic linear regression. We can estimate $mathbfw*$ in squared norm up to an error of $tildeOleft(|mathbff*|2cdot left(frac1n + left(dnright)2right)$ and prove a matching lower bound.
  arXiv  Detail & Related papers  (2023-06-25T16:32:00Z)
• Convergence of Alternating Gradient Descent for Matrix Factorization [5.439020425819001]
  We consider alternating gradient descent (AGD) with fixed step size applied to the asymmetric matrix factorization objective. We show that, for a rank-$r$ matrix $mathbfA in mathbbRm times n$, smoothness $C$ in the complexity $T$ to be an absolute constant.
  arXiv  Detail & Related papers  (2023-05-11T16:07:47Z)
• Near-Optimal Cryptographic Hardness of Agnostically Learning Halfspaces and ReLU Regression under Gaussian Marginals [43.0867217287089]
  We study the task of agnostically learning halfspaces under the Gaussian distribution. We prove a near-optimal computational hardness result for this task.
  arXiv  Detail & Related papers  (2023-02-13T16:46:23Z)
• Learning a Single Neuron with Adversarial Label Noise via Gradient Descent [50.659479930171585]
  We study a function of the form $mathbfxmapstosigma(mathbfwcdotmathbfx)$ for monotone activations. The goal of the learner is to output a hypothesis vector $mathbfw$ that $F(mathbbw)=C, epsilon$ with high probability.
  arXiv  Detail & Related papers  (2022-06-17T17:55:43Z)
• 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)
• On Submodular Contextual Bandits [92.45432756301231]
  We consider the problem of contextual bandits where actions are subsets of a ground set and mean rewards are modeled by an unknown monotone submodular function. We show that our algorithm efficiently randomizes around local optima of estimated functions according to the Inverse Gap Weighting strategy.
  arXiv  Detail & Related papers  (2021-12-03T21:42:33Z)
• Randomized Exploration for Reinforcement Learning with General Value Function Approximation [122.70803181751135]
  We propose a model-free reinforcement learning algorithm inspired by the popular randomized least squares value iteration (RLSVI) algorithm. Our algorithm drives exploration by simply perturbing the training data with judiciously chosen i.i.d. scalar noises. We complement the theory with an empirical evaluation across known difficult exploration tasks.
  arXiv  Detail & Related papers  (2021-06-15T02:23:07Z)
• Optimal Robust Linear Regression in Nearly Linear Time [97.11565882347772]
  We study the problem of high-dimensional robust linear regression where a learner is given access to $n$ samples from the generative model $Y = langle X,w* rangle + epsilon$ We propose estimators for this problem under two settings: (i) $X$ is L4-L2 hypercontractive, $mathbbE [XXtop]$ has bounded condition number and $epsilon$ has bounded variance and (ii) $X$ is sub-Gaussian with identity second moment and $epsilon$ is
  arXiv  Detail & Related papers  (2020-07-16T06:44:44Z)
• Second-Order Information in Non-Convex Stochastic Optimization: Power and Limitations [54.42518331209581]
  We find an algorithm which finds. epsilon$-approximate stationary point (with $|nabla F(x)|le epsilon$) using. $(epsilon,gamma)$surimate random random points. Our lower bounds here are novel even in the noiseless case.
  arXiv  Detail & Related papers  (2020-06-24T04:41:43Z)
• Agnostic Learning of a Single Neuron with Gradient Descent [92.7662890047311]
  We consider the problem of learning the best-fitting single neuron as measured by the expected square loss. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$. For the ReLU activation, our population risk guarantee is $O(mathsfOPT1/2)+epsilon$.
  arXiv  Detail & Related papers  (2020-05-29T07:20:35Z)
• Complexity of Finding Stationary Points of Nonsmooth Nonconvex Functions [84.49087114959872]
  We provide the first non-asymptotic analysis for finding stationary points of nonsmooth, nonsmooth functions. In particular, we study Hadamard semi-differentiable functions, perhaps the largest class of nonsmooth functions.
  arXiv  Detail & Related papers  (2020-02-10T23:23:04Z)
• Stochastic Recursive Gradient Descent Ascent for Stochastic Nonconvex-Strongly-Concave Minimax Problems [36.645753881826955]
  In this paper, we propose a novel method called RecurEnti Ascent (SREDA), which estimates more efficiently using variance. This method achieves the best known for this problem.
  arXiv  Detail & Related papers  (2020-01-11T09:05:03Z)

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.