Minimizing Quantum Renyi Divergences via Mirror Descent with Polyak Step Size
arXiv:2109.06054
Abstract
Quantum information quantities play a substantial role in characterizing operational quantities in various quantum information-theoretic problems. We consider numerical computation of four quantum information quantities: Petz-Augustin information, sandwiched Augustin information, conditional sandwiched Renyi entropy and sandwiched Renyi information. To compute these quantities requires minimizing some order- quantum Renyi divergences over the set of quantum states. Whereas the optimization problems are obviously convex, they violate standard bounded gradient/Hessian conditions in literature, so existing convex optimization methods and their convergence guarantees do not directly apply. In this paper, we propose a new class of convex optimization methods called mirror descent with the Polyak step size. We prove their convergence under a weak condition, showing that they provably converge for minimizing quantum Renyi divergences. Numerical experiment results show that entropic mirror descent with the Polyak step size converges fast in minimizing quantum Renyi divergences.
arXiv comment22 pages, proof of Theorem 5.3 improved, Section 5.3 added
References in corpus (17)
- Quantifying Entanglement
- Quantum Resource Theories
- The operational meaning of min- and max-entropy
- Strong converse for the classical capacity of entanglement-breaking and Hadamard channels via a sandwiched Renyi relative entropy
- The general structure of quantum resource theories
- Quantum Information Processing with Finite Resources -- Mathematical Foundations
- Finite blocklength converse bounds for quantum channels
- Correlation Detection and an Operational Interpretation of the Renyi Mutual Information
- Strong converse exponent for classical-quantum channel coding
- Principles of Quantum Communication Theory: A Modern Approach
- Quantum-to-classical rate distortion coding
- Non-Asymptotic Classical Data Compression with Quantum Side Information
- Convexity and Operational Interpretation of the Quantum Information Bottleneck Function
- Divergence radii and the strong converse exponent of classical-quantum channel coding with constant compositions
- Constant Compositions in the Sphere Packing Bound for Classical-Quantum Channels
- Strong converse bounds in quantum network information theory: distributed hypothesis testing and source coding
- Stochastic Gradient Descent with Polyak's Learning Rate