paper-with-me

홈 › Papers

Aligning Distributionally Robust Optimization with Practical Deep Learning Needs

2025-08-22 · Dmitrii Feoktistov, Igor Ignashin, Andrey Veprikov, Nikita Borovko, Alexander Bogdanov, Savelii Chezhegov, Aleksandr Beznosikov arxiv

While traditional Deep Learning (DL) optimization methods treat all training samples equally, Distributionally Robust Optimization (DRO) adaptively assigns importance weights to different samples. However, a significant gap exists between DRO and current DL practices. Modern DL optimizers require adaptivity and the ability to handle stochastic gradients, as these methods demonstrate superior performance. Additionally, for practical applications, a method should allow weight assignment not only to individual samples, but also to groups of objects (for example, all samples of the same class). This paper aims to bridge this gap by introducing ALSO $\unicode{x2013}$ Adaptive Loss Scaling Optimizer $\unicode{x2013}$ an adaptive algorithm for a modified DRO objective that can handle weight assignment to sample groups. We prove the convergence of our proposed algorithm for non-convex objectives, which is the typical case for DL models. Empirical evaluation across diverse Deep Learning tasks, from Tabular DL to Split Learning tasks, demonstrates that ALSO outperforms both traditional optimizers and existing DRO methods.

📄 PDF Abstract BibTeX arXiv:2508.16734

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Wasserstein Distributionally Robust Regret Optimization for Reinforcement Learning from Human Feedback

2026-04-30 · Yikai Wang, Shang Liu, Jose Blanchet arxiv

Reinforcement learning from human feedback (RLHF) is a central post-training tool for aligning large language models, but its training reward is only a learned proxy for true human utility. This creates a decision proble…

Reinforcement Learning

Distributionally Robust Direct Preference Optimization

2025-02-04 · Zaiyan Xu, Sushil Vemuri, Kishan Panaganti, Dileep Kalathil 외

A major challenge in aligning large language models (LLMs) with human preferences is the issue of distribution shift. LLM alignment algorithms rely on static preference datasets, assuming that they accurately represent r…

Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization

2024-07-10 · Junkang Wu, Yuexiang Xie, Zhengyi Yang, Jiancan Wu 외

This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noi…

Safe Distributionally Robust Feature Selection under Covariate Shift

2026-03-17 · Hiroyuki Hanada, Satoshi Akahane, Noriaki Hashimoto, Shion Takeno 외 arxiv

In practical machine learning, the environments encountered during the model development and deployment phases often differ, especially when a model is used by many users in diverse settings. Learning models that maintai…

Distributionally-Robust Machine Learning Using Locally Differentially-Private Data

2020-06-24 · Farhad Farokhi

We consider machine learning, particularly regression, using locally-differentially private datasets. The Wasserstein distance is used to define an ambiguity set centered at the empirical distribution of the dataset corr…

BIG-bench Machine Learningregression