The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning

• URL: http://arxiv.org/abs/2110.14427v5
• Date: Thu, 07 Nov 2024 15:59:59 GMT
• Title: The ODE Method for Asymptotic Statistics in Stochastic Approximation and Reinforcement Learning
• Authors: Vivek Borkar, Shuhang Chen, Adithya Devraj, Ioannis Kontoyiannis, Sean Meyn,
• Abstract summary: The paper concerns the $d$-dimensional recursion approximation, $$theta_n+1= theta_n + alpha_n + 1 f(theta_n, Phi_n+1) $$ where $ Phi_n $ is a process on a general state space. The main results are established under additional conditions on the mean flow and a version of the Donsker-Varadhan Lyapunov drift condition known as (DV3): (i) An appropriate Lyapunov
• Score: 3.8098187557917464
• License:
• Abstract: The paper concerns the $d$-dimensional stochastic approximation recursion, $$ \theta_{n+1}= \theta_n + \alpha_{n + 1} f(\theta_n, \Phi_{n+1}) $$ where $ \{ \Phi_n \}$ is a stochastic process on a general state space, satisfying a conditional Markov property that allows for parameter-dependent noise. The main results are established under additional conditions on the mean flow and a version of the Donsker-Varadhan Lyapunov drift condition known as (DV3): {(i)} An appropriate Lyapunov function is constructed that implies convergence of the estimates in $L_4$. {(ii)} A functional central limit theorem (CLT) is established, as well as the usual one-dimensional CLT for the normalized error. Moment bounds combined with the CLT imply convergence of the normalized covariance $\textsf{E} [ z_n z_n^T ]$ to the asymptotic covariance in the CLT, where $z_n{=:} (\theta_n-\theta^*)/\sqrt{\alpha_n}$. {(iii)} The CLT holds for the normalized version $z^{\text{PR}}_n{=:} \sqrt{n} [\theta^{\text{PR}}_n -\theta^*]$, of the averaged parameters $\theta^{\text{PR}}_n {=:} n^{-1} \sum_{k=1}^n\theta_k$, subject to standard assumptions on the step-size. Moreover, the covariance in the CLT coincides with the minimal covariance of Polyak and Ruppert. {(iv)} An example is given where $f$ and $\bar{f}$ are linear in $\theta$, and $\Phi$ is a geometrically ergodic Markov chain but does not satisfy (DV3). While the algorithm is convergent, the second moment of $\theta_n$ is unbounded and in fact diverges. {\bf This arXiv version 3 represents a major extension of the results in prior versions.} The main results now allow for parameter-dependent noise, as is often the case in applications to reinforcement learning.

Related papers

• Revisiting Step-Size Assumptions in Stochastic Approximation [1.3654846342364308]
  The paper revisits step-size selection in a general Markovian setting. A major conclusion is that the choice of $rho =0$ or even $rho1/2$ is justified only in select settings.
  arXiv  Detail & Related papers  (2024-05-28T05:11:05Z)
• Provably learning a multi-head attention layer [55.2904547651831]
  Multi-head attention layer is one of the key components of the transformer architecture that sets it apart from traditional feed-forward models. In this work, we initiate the study of provably learning a multi-head attention layer from random examples. We prove computational lower bounds showing that in the worst case, exponential dependence on $m$ is unavoidable.
  arXiv  Detail & Related papers  (2024-02-06T15:39:09Z)
• On the $O(\frac{\sqrt{d}}{T^{1/4}})$ Convergence Rate of RMSProp and Its Momentum Extension Measured by $\ell_1$ Norm [59.65871549878937]
  This paper considers the RMSProp and its momentum extension and establishes the convergence rate of $frac1Tsum_k=1T. Our convergence rate matches the lower bound with respect to all the coefficients except the dimension $d$. Our convergence rate can be considered to be analogous to the $frac1Tsum_k=1T.
  arXiv  Detail & Related papers  (2024-02-01T07:21:32Z)
• A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing [68.80803866919123]
  Under nonlinear measurements, most prior results are non-uniform, i.e., they hold with high probability for a fixed $mathbfx*$ rather than for all $mathbfx*$ simultaneously. Our framework accommodates GCS with 1-bit/uniformly quantized observations and single index models as canonical examples. We also develop a concentration inequality that produces tighter bounds for product processes whose index sets have low metric entropy.
  arXiv  Detail & Related papers  (2023-09-25T17:54:19Z)
• Convergence of a Normal Map-based Prox-SGD Method under the KL Inequality [0.0]
  We present a novel map-based algorithm ($mathsfnorMtext-mathsfSGD$) for $symbol$k$ convergence problems.
  arXiv  Detail & Related papers  (2023-05-10T01:12:11Z)
• An Optimal Stochastic Algorithm for Decentralized Nonconvex Finite-sum Optimization [25.21457349137344]
  We show a proof to show DEAREST requires at most $mathcal O(+sqrtmnLvarepsilon-2)$ first-order oracle (IFO) calls and $mathcal O(Lvarepsilon-2/sqrt1-lambda_W)$ communication rounds.
  arXiv  Detail & Related papers  (2022-10-25T11:37:11Z)
• Random matrices in service of ML footprint: ternary random features with no performance loss [55.30329197651178]
  We show that the eigenspectrum of $bf K$ is independent of the distribution of the i.i.d. entries of $bf w$. We propose a novel random technique, called Ternary Random Feature (TRF) The computation of the proposed random features requires no multiplication and a factor of $b$ less bits for storage compared to classical random features.
  arXiv  Detail & Related papers  (2021-10-05T09:33:49Z)
• Accelerating Optimization and Reinforcement Learning with Quasi-Stochastic Approximation [2.294014185517203]
  This paper sets out to extend convergence theory to quasi-stochastic approximations. It is illustrated with applications to gradient-free optimization and policy gradient algorithms for reinforcement learning.
  arXiv  Detail & Related papers  (2020-09-30T04:44:45Z)
• Linear Time Sinkhorn Divergences using Positive Features [51.50788603386766]
  Solving optimal transport with an entropic regularization requires computing a $ntimes n$ kernel matrix that is repeatedly applied to a vector. We propose to use instead ground costs of the form $c(x,y)=-logdotpvarphi(x)varphi(y)$ where $varphi$ is a map from the ground space onto the positive orthant $RRr_+$, with $rll n$.
  arXiv  Detail & Related papers  (2020-06-12T10:21:40Z)
• A Simple Convergence Proof of Adam and Adagrad [74.24716715922759]
  We show a proof of convergence between the Adam Adagrad and $O(d(N)/st)$ algorithms. Adam converges with the same convergence $O(d(N)/st)$ when used with the default parameters.
  arXiv  Detail & Related papers  (2020-03-05T01:56:17Z)

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.