Zobrazeno 1 - 10
of 225
pro vyhledávání: '"Razaviyayn, Meisam"'
Ensuring the privacy of Large Language Models (LLMs) is becoming increasingly important. The most widely adopted technique to accomplish this is DP-SGD, which trains a model to guarantee Differential Privacy (DP). However, DP-SGD overestimates an adv
Externí odkaz:
http://arxiv.org/abs/2403.15638
Diffusion models have emerged as a powerful tool rivaling GANs in generating high-quality samples with improved fidelity, flexibility, and robustness. A key component of these models is to learn the score function through score matching. Despite empi
Externí odkaz:
http://arxiv.org/abs/2401.15604
Publikováno v:
ICLR 2024
Training and deploying machine learning models that meet fairness criteria for protected groups are fundamental in modern artificial intelligence. While numerous constraints and regularization terms have been proposed in the literature to promote fai
Externí odkaz:
http://arxiv.org/abs/2312.03259
Traffic congestion has become an inevitable challenge in large cities due to population increases and expansion of urban areas. Various approaches are introduced to mitigate traffic issues, encompassing from expanding the road infrastructure to emplo
Externí odkaz:
http://arxiv.org/abs/2312.02341
Autor:
Baharlouei, Sina, Razaviyayn, Meisam
While training fair machine learning models has been studied extensively in recent years, most developed methods rely on the assumption that the training and test data have similar distributions. In the presence of distribution shifts, fair models ma
Externí odkaz:
http://arxiv.org/abs/2309.11682
Differential privacy (DP) ensures that training a machine learning model does not leak private data. In practice, we may have access to auxiliary public data that is free of privacy concerns. In this work, we assume access to a given amount of public
Externí odkaz:
http://arxiv.org/abs/2306.15056
Autor:
Lundstrom, Daniel, Razaviyayn, Meisam
Deep neural networks have produced significant progress among machine learning models in terms of accuracy and functionality, but their inner workings are still largely unknown. Attribution methods seek to shine a light on these "black box" models by
Externí odkaz:
http://arxiv.org/abs/2306.13753
Autor:
Lundstrom, Daniel, Razaviyayn, Meisam
Deep learning has revolutionized many areas of machine learning, from computer vision to natural language processing, but these high-performance models are generally "black box." Explaining such models would improve transparency and trust in AI-power
Externí odkaz:
http://arxiv.org/abs/2305.03100
Nonlinear control systems with partial information to the decision maker are prevalent in a variety of applications. As a step toward studying such nonlinear systems, this work explores reinforcement learning methods for finding the optimal policy in
Externí odkaz:
http://arxiv.org/abs/2303.08431
Publikováno v:
International Conference on Artificial Intelligence and Statistics, PMLR 2023
This work concerns the development of deep networks that are certifiably robust to adversarial attacks. Joint robust classification-detection was recently introduced as a certified defense mechanism, where adversarial examples are either correctly cl
Externí odkaz:
http://arxiv.org/abs/2210.14410