Zobrazeno 1 - 10
of 73
pro vyhledávání: '"Bastani, Hamsa"'
Conformal prediction has emerged as an effective strategy for uncertainty quantification by modifying a model to output sets of labels instead of a single label. These prediction sets come with the guarantee that they contain the true label with high
Externí odkaz:
http://arxiv.org/abs/2405.13268
We study the stochastic bandit problem with ReLU neural network structure. We show that a $\tilde{O}(\sqrt{T})$ regret guarantee is achievable by considering bandits with one-layer ReLU neural networks; to the best of our knowledge, our work is the f
Externí odkaz:
http://arxiv.org/abs/2405.07331
Autor:
Yao, Michael S., Zeng, Yimeng, Bastani, Hamsa, Gardner, Jacob, Gee, James C., Bastani, Osbert
Offline model-based optimization seeks to optimize against a learned surrogate model without querying the true oracle objective function during optimization. Such tasks are commonly encountered in protein design, robotics, and clinical medicine where
Externí odkaz:
http://arxiv.org/abs/2402.06532
Existing approaches to algorithmic fairness aim to ensure equitable outcomes if human decision-makers comply perfectly with algorithmic decisions. However, perfect compliance with the algorithm is rarely a reality or even a desirable outcome in human
Externí odkaz:
http://arxiv.org/abs/2310.03647
Large and complex datasets are often collected from several, possibly heterogeneous sources. Multitask learning methods improve efficiency by leveraging commonalities across datasets while accounting for possible differences among them. Here, we stud
Externí odkaz:
http://arxiv.org/abs/2306.06291
We study the problem of allocating limited supply of medical resources in developing countries, in particular, Sierra Leone. We address this problem by combining machine learning (to predict demand) with optimization (to optimize allocations). A key
Externí odkaz:
http://arxiv.org/abs/2211.08507
Autor:
Avadhanula, Vashist, Baki, Omar Abdul, Bastani, Hamsa, Bastani, Osbert, Gocmen, Caner, Haimovich, Daniel, Hwang, Darren, Karamshuk, Dima, Leeper, Thomas, Ma, Jiayuan, Macnamara, Gregory, Mullett, Jake, Palow, Christopher, Park, Sung, Rajagopal, Varun S, Schaeffer, Kevin, Shah, Parikshit, Sinha, Deeksha, Stier-Moses, Nicolas, Xu, Peng
We describe the current content moderation strategy employed by Meta to remove policy-violating content from its platforms. Meta relies on both handcrafted and learned risk models to flag potentially violating content for human review. Our approach a
Externí odkaz:
http://arxiv.org/abs/2211.06516
Autor:
Xu, Kan, Bastani, Hamsa
Decision-makers often simultaneously face many related but heterogeneous learning problems. For instance, a large retailer may wish to learn product demand at different stores to solve pricing or inventory problems, making it desirable to learn joint
Externí odkaz:
http://arxiv.org/abs/2112.14233
A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes. We propose a natural constraint on exploration -- \textit{uniformly} outperforming a conservative policy (adaptively e
Externí odkaz:
http://arxiv.org/abs/2110.13060
A key challenge facing deep learning is that neural networks are often not robust to shifts in the underlying data distribution. We study this problem from the perspective of the statistical concept of parameter identification. Generalization bounds
Externí odkaz:
http://arxiv.org/abs/2109.10935