Complexity of Classical Acceleration for $\ell_1$-Regularized PageRank

• URL: http://arxiv.org/abs/2602.21138v1
• Date: Tue, 24 Feb 2026 17:35:46 GMT
• Title: Complexity of Classical Acceleration for $\ell_1$-Regularized PageRank
• Authors: Kimon Fountoulakis, David Martínez-Rubio,
• Abstract summary: We show that FISTA can improve the dependence on $$ while preserving the $1/$ locality scaling.<n>We analyze FISTA on a slightly over-regularized objective and show that, under a checkable confinement condition, all spurious activations remain inside a boundary set.<n>This yields a bound consisting of an accelerated $(sqrt)-1log(/varepsilon)$ term plus a boundary overhead $sqrtvol(mathcalB)/(3/2)$.
• Score: 14.919427330415608
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the degree-weighted work required to compute $\ell_1$-regularized PageRank using the standard one-gradient-per-iteration accelerated proximal-gradient method (FISTA). For non-accelerated local methods, the best known worst-case work scales as $\widetilde{O} ((αρ)^{-1})$, where $α$ is the teleportation parameter and $ρ$ is the $\ell_1$-regularization parameter. A natural question is whether FISTA can improve the dependence on $α$ from $1/α$ to $1/\sqrtα$ while preserving the $1/ρ$ locality scaling. The challenge is that acceleration can break locality by transiently activating nodes that are zero at optimality, thereby increasing the cost of gradient evaluations. We analyze FISTA on a slightly over-regularized objective and show that, under a checkable confinement condition, all spurious activations remain inside a boundary set $\mathcal{B}$. This yields a bound consisting of an accelerated $(ρ\sqrtα)^{-1}\log(α/\varepsilon)$ term plus a boundary overhead $\sqrt{vol(\mathcal{B})}/(ρα^{3/2})$. We provide graph-structural conditions that imply such confinement. Experiments on synthetic and real graphs show the resulting speedup and slowdown regimes under the degree-weighted work model.

Related papers

• Faster Gradient Methods for Highly-smooth Stochastic Bilevel Optimization [27.377966916440432]
  We show the complexity of finding an $epsilon-gradient point for bilevel optimization when the upper-level problem is nonmath and the lower-level problem is convex.<n>Recent work proposed the first-order approximation, F$2$SA, achieving the $tildemathcalO(epsilon-4)$ lower bound for firstorder smooth problems.
  arXiv  Detail & Related papers  (2025-09-03T02:02:52Z)
• Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0, L_1)$-Smoothness [57.93371273485736]
  We study first-order methods for convex optimization problems with functions $f$ satisfying the recently proposed $ell$-smoothness condition $||nabla2f(x)|| le ellleft(||nabla f(x)||right),$ which generalizes the $L$-smoothness and $(L_0,L_1)$-smoothness.
  arXiv  Detail & Related papers  (2025-08-09T08:28:06Z)
• Proving the Limited Scalability of Centralized Distributed Optimization via a New Lower Bound Construction [57.93371273485736]
  We consider a centralized distributed learning setup where all workers jointly find an unbiased bound LDeltaepsilon2,$ better poly-logarithmically in $n$, even in the homogeneous (i.i.d.) case, where all workers access the same distribution.
  arXiv  Detail & Related papers  (2025-06-30T13:27:39Z)
• On the $O(\frac{\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\ell_1$ Norm [54.28350823319057]
  This paper considers the RMSProp and its momentum extension and establishes the convergence rate of $frac1Tsum_k=1T.<n>Our convergence rate matches the lower bound with respect to all the coefficients except the dimension $d$.<n>Our convergence rate can be considered to be analogous to the $frac1Tsum_k=1T.
  arXiv  Detail & Related papers  (2024-02-01T07:21:32Z)
• Beyond Uniform Smoothness: A Stopped Analysis of Adaptive SGD [38.221784575853796]
  This work considers the problem of finding first-order stationary point of a non atau function with potentially constant smoothness using a gradient. We develop a technique that allows us to prove $mathcalO(fracmathrmpolylog(T)sigmatT)$ convergence rates without assuming uniform bounds on the noise.
  arXiv  Detail & Related papers  (2023-02-13T18:13:36Z)
• Preconditioned Gradient Descent for Overparameterized Nonconvex Burer--Monteiro Factorization with Global Optimality Certification [19.32160757444549]
  We consider using gradient descent to minimize the non function $f(X)=phi(XXT)$ over an $ntimes r$ factor matrix $X$.<n>We propose an inexpensive preconditioner that restores the convergence rate of gradient descent back to linear.
  arXiv  Detail & Related papers  (2022-06-07T14:26:49Z)
• Continuous Submodular Maximization: Boosting via Non-oblivious Function [12.755674710719616]
  In this paper, we revisit the constrained and continuous submodular iterations in both offline and online settings. We use the factorrevealing optimization equation to derive an optimal auxiliary function $F$ for problem $max_boldsymbolxinmathCf(boldsymbolx)$. In the online setting, we propose boosting a gradient feedback algorithm, achieving a regret of $sqrtD$ (where $D$ is the sum of delays of gradient feedback against $(fracgamma2)$ adversarial.
  arXiv  Detail & Related papers  (2022-01-03T15:10:17Z)
• Minimal Expected Regret in Linear Quadratic Control [79.81807680370677]
  We devise an online learning algorithm and provide guarantees on its expected regret. This regret at time $T$ is upper bounded (i) by $widetildeO((d_u+d_x)sqrtd_xT)$ when $A$ and $B$ are unknown.
  arXiv  Detail & Related papers  (2021-09-29T14:07:21Z)
• Nearly Horizon-Free Offline Reinforcement Learning [97.36751930393245]
  We revisit offline reinforcement learning on episodic time-homogeneous Markov Decision Processes with $S$ states, $A$ actions and planning horizon $H$. We obtain the first set of nearly $H$-free sample complexity bounds for evaluation and planning using the empirical MDPs.
  arXiv  Detail & Related papers  (2021-03-25T18:52:17Z)
• Private Stochastic Convex Optimization: Optimal Rates in $\ell_1$ Geometry [69.24618367447101]
  Up to logarithmic factors the optimal excess population loss of any $(varepsilon,delta)$-differently private is $sqrtlog(d)/n + sqrtd/varepsilon n.$ We show that when the loss functions satisfy additional smoothness assumptions, the excess loss is upper bounded (up to logarithmic factors) by $sqrtlog(d)/n + (log(d)/varepsilon n)2/3.
  arXiv  Detail & Related papers  (2021-03-02T06:53:44Z)
• Agnostic Q-learning with Function Approximation in Deterministic Systems: Tight Bounds on Approximation Error and Sample Complexity [94.37110094442136]
  We study the problem of agnostic $Q$-learning with function approximation in deterministic systems. We show that if $delta = Oleft(rho/sqrtdim_Eright)$, then one can find the optimal policy using $Oleft(dim_Eright)$.
  arXiv  Detail & Related papers  (2020-02-17T18:41:49Z)

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.