Pith. sign in

REVIEW 2 cited by

Optimal and instance-dependent guarantees for Markovian linear stochastic approximation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2112.12770 v2 pith:SQJ7HXXA submitted 2021-12-23 math.OC cs.LGmath.PRmath.STstat.MLstat.TH

classification math.OCcs.LGmath.PRmath.STstat.MLstat.TH
keywords lambdaboundinstance-dependentlinearmathrmnon-asymptoticapproximationaveraged
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

We study stochastic approximation procedures for approximately solving a $d$-dimensional linear fixed point equation based on observing a trajectory of length $n$ from an ergodic Markov chain. We first exhibit a non-asymptotic bound of the order $t_{\mathrm{mix}} \tfrac{d}{n}$ on the squared error of the last iterate of a standard scheme, where $t_{\mathrm{mix}}$ is a mixing time. We then prove a non-asymptotic instance-dependent bound on a suitably averaged sequence of iterates, with a leading term that matches the local asymptotic minimax limit, including sharp dependence on the parameters $(d, t_{\mathrm{mix}})$ in the higher order terms. We complement these upper bounds with a non-asymptotic minimax lower bound that establishes the instance-optimality of the averaged SA estimator. We derive corollaries of these results for policy evaluation with Markov noise -- covering the TD($\lambda$) family of algorithms for all $\lambda \in [0, 1)$ -- and linear autoregressive models. Our instance-dependent characterizations open the door to the design of fine-grained model selection procedures for hyperparameter tuning (e.g., choosing the value of $\lambda$ when running the TD($\lambda$) algorithm).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Statistical inference for Linear Stochastic Approximation with Markovian Noise

    stat.ML 2025-05 conditional novelty 7.0 of 10

    Polyak-Ruppert averaged linear stochastic approximation with Markovian noise achieves Berry-Esseen rate O(n^{-1/4}) in Kolmogorov distance, and a multiplier subsample bootstrap achieves coverage error O(n^{-1/10}).

  2. Optimization under Persistent State-Dependent Bias: Gradient-based Method and Complexity Analysis

    math.OC 2026-07 reject novelty 6.0 of 10

    Residual Learning, a proposed bilevel gradient method, claims exact convergence under state-dependent analog-hardware bias with rate O~(kappa1*kappa2^4*sigma^2/(mu*K)).

Pith tools