5 papers
TAME: Task Agnostic Continual Learning using Multiple Experts
Haoran Zhu, Maryam Majzoubi, Arihant Jain +1
The goal of lifelong learning is to continuously learn from non-stationary distributions, where the non-stationarity is typically imposed by a sequence of distinct tasks. Prior wor…
Efficient Contextual Bandits with Continuous Actions
Maryam Majzoubi, Chicheng Zhang, Rajan Chari +3
We create a computationally tractable algorithm for contextual bandits with continuous actions having unknown structure. Our reduction-style algorithm composes with most supervised…
Analytical Modeling of k33 Mode Partial Electrode Configuration for Loss Characterization
Yoonsang Park, Maryam Majzoubi, Yuxuan Zhang +3
Accurate determination of three types of losses (dielectric, elastic and piezoelectric) in piezoelectric materials is critical, since they are closely related to the performance of…
Improvement of the Standard Characterization Method on k33 Mode Piezoelectric Specimens
Yoonsang Park, Yuxuan Zhang, Maryam Majzoubi +3
Even though standard method to determine physical parameters of piezoelectric materials has been set up for several decades, bare attention has been made on loss determination meth…
LdSM: Logarithm-depth Streaming Multi-label Decision Trees
Maryam Majzoubi, Anna Choromanska
We consider multi-label classification where the goal is to annotate each data point with the most relevant of labels from an extremely large label set. Efficient…