A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization
Authors:
Preprint
Abstract
This paper studies optimization for a family of problems termed $\textbf{compositional entropic risk minimization}$, in which each data's loss is formulated as a Log-Expectation-Exponential (Log-E-Exp) function. The Log-E-Exp formulation serves as an abstraction of the Log-Sum-Exponential (LogSumExp) function when the explicit summation inside the logarithm is taken over a gigantic number of items and is therefore expensive to evaluate. While entropic risk objectives of this form arise in many machine learning problems, existing optimization algorithms suffer from several fundamental limitations including non-convergence, numerical instability, and slow convergence rates. To address these limitations, we propose a geometry-aware stochastic algorithm, termed $\textbf{SCENT}$, for the dual formulation of entropic risk minimization cast as a min--min optimization problem. The key to our design is a $\textbf{stochastic proximal mirror descent (SPMD)}$ update for the dual variable, equipped with a Bregman divergence induced by a negative exponential function that faithfully captures the geometry of the objective. Our main contributions are threefold: (i) we establish an $O(1/\sqrt{T})$ convergence rate of the proposed SCENT algorithm for convex problems; (ii) we theoretically characterize the advantages of SPMD over standard SGD update for optimizing the dual variable; and (iii) we demonstrate the empirical effectiveness of SCENT on extreme classification, partial AUC maximization, contrastive learning and distributionally robust optimization, where it consistently outperforms existing baselines.
Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- Optimal methods for convex nested stochastic composite optimizationMathematical Programming, 2024
- From image descriptions to visual denotations: New similarity metrics for semantic inference over event descriptionsTransactions of the Association for Computational Linguistics, 2014
- Listwise approach to learning to rank2008
- Sparse spatial autoregressionsStatistics & Probability Letters, 1997
- Expected Utility, Penalty Functions, and Duality in Stochastic Nonlinear ProgrammingManagement Science, 1986