paper-with-me

Papers

Geometry-Calibrated DRO: Combating Over-Pessimism with Free Energy Implications

2023-11-08 · Jiashuo Liu, Jiayun Wu, Tianyu Wang, Hao Zou, Bo Li, Peng Cui

Machine learning algorithms minimizing average risk are susceptible to distributional shifts. Distributionally Robust Optimization (DRO) addresses this issue by optimizing the worst-case risk within an uncertainty set. However, DRO suffers from over-pessimism, leading to low-confidence predictions, poor parameter estimations as well as poor generalization. In this work, we conduct a theoretical analysis of a probable root cause of over-pessimism: excessive focus on noisy samples. To alleviate the impact of noise, we incorporate data geometry into calibration terms in DRO, resulting in our novel Geometry-Calibrated DRO (GCDRO) for regression. We establish the connection between our risk objective and the Helmholtz free energy in statistical physics, and this free-energy-based risk can extend to standard DRO methods. Leveraging gradient flow in Wasserstein space, we develop an approximate minimax optimization algorithm with a bounded error ratio and elucidate how our approach mitigates noisy sample effects. Comprehensive experiments confirm GCDRO's superiority over conventional DRO methods.

📄 PDF Abstract BibTeX arXiv:2311.05054

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Beyond Pessimism: Offline Learning in KL-regularized Games

2026-04-08 · Yuheng Zhang, Claire Chen, Nan Jiang arxiv

We study offline learning in KL-regularized two-player zero-sum games, where policies are optimized with respect to a fixed reference policy through KL regularization. Prior work relies on pessimistic value estimation to…

CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs

2025-01-29 · Amey Hengle, Aswini Kumar, Anil Bandhakavi, Tanmoy Chakraborty

Counterspeech has emerged as a popular and effective strategy for combating online hate speech, sparking growing research interest in automating its generation using language models. However, the field still lacks standa…

Pessimism-Free Offline Learning in General-Sum Games via KL Regularization

2026-04-30 · Claire Chen, Yuheng Zhang arxiv

Offline multi-agent reinforcement learning in general-sum settings is challenged by the distribution shift between logged datasets and target equilibrium policies. While standard methods rely on manual pessimistic penalt…

Multi-agent Reinforcement Learning

Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach

2022-10-26 · Yunzhe Zhou, Zhengling Qi, Chengchun Shi, Lexin Li

In this article, we propose a novel pessimism-based Bayesian learning method for optimal dynamic treatment regimes in the offline setting. When the coverage condition does not hold, which is common for offline data, the …

Thompson SamplingVariational Inference

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

2025-05-18 · Dominic Maggio, Hyungtae Lim, Luca Carlone

We present VGGT-SLAM, a dense RGB SLAM system constructed by incrementally and globally aligning submaps created from the feed-forward scene reconstruction approach VGGT using only uncalibrated monocular cameras. While r…

GPU