Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tsai, Chung-En, Cheng, Hao-Chung, Li, Yen-Huan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909133184172032
author Tsai, Chung-En
Cheng, Hao-Chung
Li, Yen-Huan
author_facet Tsai, Chung-En
Cheng, Hao-Chung
Li, Yen-Huan
contents Consider the problem of minimizing an expected logarithmic loss over either the probability simplex or the set of quantum density matrices. This problem includes tasks such as solving the Poisson inverse problem, computing the maximum-likelihood estimate for quantum state tomography, and approximating positive semi-definite matrix permanents with the currently tightest approximation ratio. Although the optimization problem is convex, standard iteration complexity guarantees for first-order methods do not directly apply due to the absence of Lipschitz continuity and smoothness in the loss function. In this work, we propose a stochastic first-order algorithm named $B$-sample stochastic dual averaging with the logarithmic barrier. For the Poisson inverse problem, our algorithm attains an $\varepsilon$-optimal solution in $\smash{\tilde{O}}(d^2/\varepsilon^2)$ time, matching the state of the art, where $d$ denotes the dimension. When computing the maximum-likelihood estimate for quantum state tomography, our algorithm yields an $\varepsilon$-optimal solution in $\smash{\tilde{O}}(d^3/\varepsilon^2)$ time. This improves on the time complexities of existing stochastic first-order methods by a factor of $d^{ω-2}$ and those of batch methods by a factor of $d^2$, where $ω$ denotes the matrix multiplication exponent. Numerical experiments demonstrate that empirically, our algorithm outperforms existing methods with explicit complexity guarantees.
format Preprint
id arxiv_https___arxiv_org_abs_2311_02557
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging
Tsai, Chung-En
Cheng, Hao-Chung
Li, Yen-Huan
Optimization and Control
Machine Learning
Quantum Physics
Consider the problem of minimizing an expected logarithmic loss over either the probability simplex or the set of quantum density matrices. This problem includes tasks such as solving the Poisson inverse problem, computing the maximum-likelihood estimate for quantum state tomography, and approximating positive semi-definite matrix permanents with the currently tightest approximation ratio. Although the optimization problem is convex, standard iteration complexity guarantees for first-order methods do not directly apply due to the absence of Lipschitz continuity and smoothness in the loss function. In this work, we propose a stochastic first-order algorithm named $B$-sample stochastic dual averaging with the logarithmic barrier. For the Poisson inverse problem, our algorithm attains an $\varepsilon$-optimal solution in $\smash{\tilde{O}}(d^2/\varepsilon^2)$ time, matching the state of the art, where $d$ denotes the dimension. When computing the maximum-likelihood estimate for quantum state tomography, our algorithm yields an $\varepsilon$-optimal solution in $\smash{\tilde{O}}(d^3/\varepsilon^2)$ time. This improves on the time complexities of existing stochastic first-order methods by a factor of $d^{ω-2}$ and those of batch methods by a factor of $d^2$, where $ω$ denotes the matrix multiplication exponent. Numerical experiments demonstrate that empirically, our algorithm outperforms existing methods with explicit complexity guarantees.
title Fast Minimization of Expected Logarithmic Loss via Stochastic Dual Averaging
topic Optimization and Control
Machine Learning
Quantum Physics
url https://arxiv.org/abs/2311.02557