Alternating minimization for computing doubly minimized Petz Renyi mutual information

• URL: http://arxiv.org/abs/2507.05205v1
• Date: Mon, 07 Jul 2025 17:11:58 GMT
• Title: Alternating minimization for computing doubly minimized Petz Renyi mutual information
• Authors: Laura Burri,
• Abstract summary: The doubly minimized Petz Renyi mutual information (PRMI) of order $alpha$ is defined as the minimization of the Petz divergence of order $alpha$ of a fixed bipartite quantum state $rho_AB$.<n>To date, no closed-form expression for this measure has been found, necessitating the development of numerical methods for its computation.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The doubly minimized Petz Renyi mutual information (PRMI) of order $\alpha$ is defined as the minimization of the Petz divergence of order $\alpha$ of a fixed bipartite quantum state $\rho_{AB}$ relative to any product state $\sigma_A\otimes \tau_B$. To date, no closed-form expression for this measure has been found, necessitating the development of numerical methods for its computation. In this work, we show that alternating minimization over $\sigma_A$ and $\tau_B$ asymptotically converges to the doubly minimized PRMI for any $\alpha\in (\frac{1}{2},1)\cup (1,2]$, by proving linear convergence of the objective function values with respect to the number of iterations for $\alpha\in (1,2]$ and sublinear convergence for $\alpha\in (\frac{1}{2},1)$. Previous studies have only addressed the specific case where $\rho_{AB}$ is a classical-classical state, while our results hold for any quantum state $\rho_{AB}$.

Related papers

• A Proximal Modified Quasi-Newton Method for Nonsmooth Regularized Optimization [0.7373617024876725]
  Lipschitz-of-$nabla f$. $mathcalS_k|p$. $mathcalS_k|p$. $nabla f$. $mathcalS_k|p$.
  arXiv  Detail & Related papers  (2024-09-28T18:16:32Z)
• Efficient Continual Finite-Sum Minimization [52.5238287567572]
  We propose a key twist into the finite-sum minimization, dubbed as continual finite-sum minimization. Our approach significantly improves upon the $mathcalO(n/epsilon)$ FOs that $mathrmStochasticGradientDescent$ requires. We also prove that there is no natural first-order method with $mathcalOleft(n/epsilonalpharight)$ complexity gradient for $alpha 1/4$, establishing that the first-order complexity of our method is nearly tight.
  arXiv  Detail & Related papers  (2024-06-07T08:26:31Z)
• A note on $L^1$-Convergence of the Empiric Minimizer for unbounded functions with fast growth [0.0]
  For $V : mathbbRd to mathbbR$ coercive, we study the convergence rate for the $L1$-distance of the empiric minimizer. We show that in general, for unbounded functions with fast growth, the convergence rate is bounded above by $a_n n-1/q$, where $q$ is the dimension of the latent random variable.
  arXiv  Detail & Related papers  (2023-03-08T08:46:13Z)
• Average R\'{e}nyi Entropy of a Subsystem in Random Pure State [0.0]
  We plot the $ln m$-dependence of the quantum information derived from $widetildeS_alpha (m,n)$. It is remarkable to note that the nearly vanishing region of the information becomes shorten with increasing $alpha$, and eventually disappears in the limit of $alpha rightarrow infty$.
  arXiv  Detail & Related papers  (2023-01-22T08:08:51Z)
• Ridgeless Interpolation with Shallow ReLU Networks in $1D$ is Nearest Neighbor Curvature Extrapolation and Provably Generalizes on Lipschitz Functions [16.75218291152252]
  We prove a precise geometric description of all one layer ReLU networks $z(x;theta)$ with a single linear unit. We refer to them as ridgeless ReLU interpolants. Our results show that ridgeless ReLU interpolants achieve the best possible generalization for learning $1d$ Lipschitz functions.
  arXiv  Detail & Related papers  (2021-09-27T11:32:24Z)
• 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)
• Infinite-Horizon Offline Reinforcement Learning with Linear Function Approximation: Curse of Dimensionality and Algorithm [46.36534144138337]
  In this paper, we investigate the sample complexity of policy evaluation in offline reinforcement learning. Under the low distribution shift assumption, we show that there is an algorithm that needs at most $Oleft(maxleft fracleftVert thetapirightVert _24varepsilon4logfracddelta,frac1varepsilon2left(d+logfrac1deltaright)right right)$ samples to approximate the
  arXiv  Detail & Related papers  (2021-03-17T18:18:57Z)
• Convergence Rate of the (1+1)-Evolution Strategy with Success-Based Step-Size Adaptation on Convex Quadratic Functions [20.666734673282498]
  The (1+1)-evolution strategy (ES) with success-based step-size adaptation is analyzed on a general convex quadratic function. The convergence rate of the (1+1)-ES is derived explicitly and rigorously on a general convex quadratic function.
  arXiv  Detail & Related papers  (2021-03-02T09:03:44Z)
• 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)
• Improved Sample Complexity for Incremental Autonomous Exploration in MDPs [132.88757893161699]
  We learn the set of $epsilon$-optimal goal-conditioned policies attaining all states that are incrementally reachable within $L$ steps. DisCo is the first algorithm that can return an $epsilon/c_min$-optimal policy for any cost-sensitive shortest-path problem.
  arXiv  Detail & Related papers  (2020-12-29T14:06:09Z)
• $Q$-learning with Logarithmic Regret [60.24952657636464]
  We prove that an optimistic $Q$-learning enjoys a $mathcalOleft(fracSAcdot mathrmpolyleft(Hright)Delta_minlogleft(SATright)right)$ cumulative regret bound, where $S$ is the number of states, $A$ is the number of actions, $H$ is the planning horizon, $T$ is the total number of steps, and $Delta_min$ is the minimum sub-optimality gap.
  arXiv  Detail & Related papers  (2020-06-16T13:01:33Z)
• Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity [59.34067736545355]
  Given an MDP with $S$ states, $A$ actions, the discount factor $gamma in (0,1)$, and an approximation threshold $epsilon > 0$, we provide a model-free algorithm to learn an $epsilon$-optimal policy. For small enough $epsilon$, we show an improved algorithm with sample complexity.
  arXiv  Detail & Related papers  (2020-06-06T13:34:41Z)
• On the Complexity of Minimizing Convex Finite Sums Without Using the Indices of the Individual Functions [62.01594253618911]
  We exploit the finite noise structure of finite sums to derive a matching $O(n2)$-upper bound under the global oracle model. Following a similar approach, we propose a novel adaptation of SVRG which is both emphcompatible with oracles, and achieves complexity bounds of $tildeO(n2+nsqrtL/mu)log (1/epsilon)$ and $O(nsqrtL/epsilon)$, for $mu>0$ and $mu=0$
  arXiv  Detail & Related papers  (2020-02-09T03:39:46Z)

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.