paper-with-me

홈 › Papers

Theoretical Guarantees of Data Augmented Last Layer Retraining Methods

2024-05-09 · Monica Welfert, Nathan Stromberg, Lalitha Sankar

Ensuring fair predictions across many distinct subpopulations in the training data can be prohibitive for large models. Recently, simple linear last layer retraining strategies, in combination with data augmentation methods such as upweighting, downsampling and mixup, have been shown to achieve state-of-the-art performance for worst-group accuracy, which quantifies accuracy for the least prevalent subpopulation. For linear last layer retraining and the abovementioned augmentations, we present the optimal worst-group accuracy when modeling the distribution of the latent representations (input to the last layer) as Gaussian for each subpopulation. We evaluate and verify our results for both synthetic and large publicly available datasets.

📄 PDF Abstract BibTeX arXiv:2405.05934

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Augmented Lagrangian Method for Last-Iterate Convergence for Constrained MDPs

2026-05-12 · Michael Lu, Max Qiushi Lin, Mo Chen, Sharan Vaswani arxiv

We study policy optimization for infinite-horizon, discounted constrained Markov decision processes (CMDPs). While existing theoretical guarantees typically hold for the mixture policy, deploying such a policy is computa…

Continuous Control

Global Guarantees for Enforcing Deep Generative Priors by Empirical Risk

2017-05-22 · Paul Hand, Vladislav Voroninski

We examine the theoretical properties of enforcing priors provided by generative deep neural networks via empirical risk minimization. In particular we consider two models, one in which the task is to invert a generative…

Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems trained with Gradient Descent

2024-03-08 · Nathan Buskulic, Jalal Fadili, Yvain Quéau

Advanced machine learning methods, and more prominently neural networks, have become standard to solve inverse problems over the last years. However, the theoretical recovery guarantees of such methods are still scarce a…

Safe Active Dynamics Learning and Control: A Sequential Exploration-Exploitation Framework

2020-08-26 · Thomas Lew, Apoorva Sharma, James Harrison, Andrew Bylard 외

Safe deployment of autonomous robots in diverse scenarios requires agents that are capable of efficiently adapting to new environments while satisfying constraints. In this work, we propose a practical and theoretically-…

Meta-LearningMeta Reinforcement Learning

ON NEURAL NETWORK GENERALIZATION VIA PROMOTING WITHIN-LAYER ACTIVATION DIVERSITY

2021-01-01 · Firas Laakom, Jenni Raitoharju, Alexandros Iosifidis, Moncef Gabbouj

During the last decade, neural networks have been intensively used to tackle various problems and they have often led to state-of-the-art results. These networks are composed of multiple jointly optimized layers arranged…

Diversity