paper-with-me

Papers

Distributionally Robust Optimization via Ball Oracle Acceleration

2022-03-24 · Yair Carmon, Danielle Hausler

We develop and analyze algorithms for distributionally robust optimization (DRO) of convex losses. In particular, we consider group-structured and bounded $f$-divergence uncertainty sets. Our approach relies on an accelerated method that queries a ball optimization oracle, i.e., a subroutine that minimizes the objective within a small ball around the query point. Our main contribution is efficient implementations of this oracle for DRO objectives. For DRO with $N$ non-smooth loss functions, the resulting algorithms find an $\epsilon$-accurate solution with $\widetilde{O}\left(N\epsilon^{-2/3} + \epsilon^{-2}\right)$ first-order oracle queries to individual loss functions. Compared to existing algorithms for this problem, we improve complexity by a factor of up to $\epsilon^{-4/3}$.

📄 PDF Abstract BibTeX arXiv:2203.13225

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Thinking Inside the Ball: Near-Optimal Minimization of the Maximal Loss

2021-05-04 · Yair Carmon, Arun Jambulapati, Yujia Jin, Aaron Sidford

We characterize the complexity of minimizing $\max_{i\in[N]} f_i(x)$ for convex, Lipschitz functions $f_1,\ldots, f_N$. For non-smooth functions, existing methods require $O(N\epsilon^{-2})$ queries to a first-order orac…

Distributionally Robust Logistic Regression

2015-09-30 · NeurIPS 2015 12 · Soroosh Shafieezadeh-Abadeh, Peyman Mohajerin Esfahani, Daniel Kuhn

This paper proposes a distributionally robust approach to logistic regression. We use the Wasserstein distance to construct a ball in the space of probability distributions centered at the uniform distribution on the tra…

regression

Quantitative Convergences of Lie Group Momentum Optimizers

2024-05-30 · Lingkai Kong, Molei Tao

Explicit, momentum-based dynamics that optimize functions defined on Lie groups can be constructed via variational optimization and momentum trivialization. Structure preserving time discretizations can then turn this dy…

Multi-level Monte-Carlo Gradient Methods for Stochastic Optimization with Biased Oracles

2024-08-20 · Yifan Hu, Jie Wang, Xin Chen, Niao He

We consider stochastic optimization when one only has access to biased stochastic oracles of the objective and the gradient, and obtaining stochastic gradients with low biases comes at high costs. This setting captures v…

Contrastive LearningSchedulingStochastic Optimization

ReSQueing Parallel and Private Stochastic Convex Optimization

2023-01-01 · Yair Carmon, Arun Jambulapati, Yujia Jin, Yin Tat Lee 외

We introduce a new tool for stochastic convex optimization (SCO): a Reweighted Stochastic Query (ReSQue) estimator for the gradient of a function convolved with a (Gaussian) probability density. Combining ReSQue with rec…