Zobrazeno 1 - 10
of 786
pro vyhledávání: '"Khodak, A. A."'
Solving a linear system $Ax=b$ is a fundamental scientific computing primitive for which numerous solvers and preconditioners have been developed. These come with parameters whose optimal values depend on the system being solved and are often impossi
Externí odkaz:
http://arxiv.org/abs/2310.02246
Autor:
Khodak, Mikhail, Osadchiy, Ilya, Harris, Keegan, Balcan, Maria-Florina, Levy, Kfir Y., Meir, Ron, Wu, Zhiwei Steven
We study online meta-learning with bandit feedback, with the goal of improving performance across multiple tasks if they are similar according to some natural similarity measure. As the first to target the adversarial online-within-online partial-inf
Externí odkaz:
http://arxiv.org/abs/2307.02295
Autor:
Lin, Jingyang, Chen, Junyu, Lyu, Hanjia, Khodak, Igor, Chhabra, Divya, Richardson, Colby L Day, Prelipcean, Irina, Dylag, Andrew M, Luo, Jiebo
Diagnosis of adverse neonatal outcomes is crucial for preterm survival since it enables doctors to provide timely treatment. Machine learning (ML) algorithms have been demonstrated to be effective in predicting adverse neonatal outcomes. However, mos
Externí odkaz:
http://arxiv.org/abs/2303.15656
Autor:
Shen, Junhong, Li, Liam, Dery, Lucio M., Staten, Corey, Khodak, Mikhail, Neubig, Graham, Talwalkar, Ameet
Fine-tuning large-scale pretrained models has led to tremendous progress in well-studied modalities such as vision and NLP. However, similar gains have not been observed in many other modalities due to a lack of relevant pretrained models. In this wo
Externí odkaz:
http://arxiv.org/abs/2302.05738
Autor:
Kuo, Kevin, Thaker, Pratiksha, Khodak, Mikhail, Nguyen, John, Jiang, Daniel, Talwalkar, Ameet, Smith, Virginia
Hyperparameter tuning is critical to the success of federated learning applications. Unfortunately, appropriately selecting hyperparameters is challenging in federated networks. Issues of scale, privacy, and heterogeneity introduce noise in the tunin
Externí odkaz:
http://arxiv.org/abs/2212.08930
When applying differential privacy to sensitive data, we can often improve performance using external information such as other sensitive data, public data, or human priors. We propose to use the learning-augmented algorithms (or algorithms with pred
Externí odkaz:
http://arxiv.org/abs/2210.11222
Autor:
Harris, Keegan, Anagnostides, Ioannis, Farina, Gabriele, Khodak, Mikhail, Wu, Zhiwei Steven, Sandholm, Tuomas
In the literature on game-theoretic equilibrium finding, focus has mainly been on solving a single game in isolation. In practice, however, strategic interactions -- ranging from routing problems to online advertising auctions -- evolve dynamically,
Externí odkaz:
http://arxiv.org/abs/2209.14110
An important unresolved challenge in the theory of regularization is to set the regularization coefficients of popular techniques like the ElasticNet with general provable guarantees. We consider the problem of tuning the regularization parameters of
Externí odkaz:
http://arxiv.org/abs/2207.10199
We study online learning with bandit feedback across multiple tasks, with the goal of improving average performance across tasks if they are similar according to some natural task-similarity measure. As the first to target the adversarial setting, we
Externí odkaz:
http://arxiv.org/abs/2205.14128
Auxiliary objectives, supplementary learning signals that are introduced to help aid learning on data-starved or highly complex end-tasks, are commonplace in machine learning. Whilst much work has been done to formulate useful auxiliary objectives, t
Externí odkaz:
http://arxiv.org/abs/2205.14082