activity
20142024
most citedExponentiated Subgradient Algorithm for Online Optimization under the Random Permutation Model

6 citations · 18 across the 7 of their papers we have counts for

collaborators

6 papers

cs.LG2024

Offline Multi-task Transfer RL with Representational Penalization

Avinandan Bose, Simon Shaolei Du, Maryam Fazel

We study the problem of representation transfer in offline Reinforcement Learning (RL), where a learner has access to episodic data from a number of source tasks collected a priori…

cs.LG20231 cited

No-Regret Online Prediction with Strategic Experts

Omid Sadeghi, Maryam Fazel

We study a generalization of the online binary prediction with expert advice framework where at each round, the learner is allowed to pick experts from a pool of expe…

cs.LG20231 cited

Stochastic Contextual Bandits with Long Horizon Rewards

Yuzhen Qin, Yingcong Li, Fabio Pasqualetti +2

The growing interest in complex decision-making and language modeling problems highlights the importance of sample-efficient learning over very long horizons. This work takes a ste…

cs.GT20226 cited

Multiplayer Performative Prediction: Learning in Decision-Dependent Games

Adhyyan Narang, Evan Faulkner, Dmitriy Drusvyatskiy +2

Learning problems commonly exhibit an interesting feedback mechanism wherein the population data reacts to competing decision makers' actions. This paper formulates a new game theo…

cs.DS20164 cited

Worst Case Competitive Analysis of Online Algorithms for Conic Optimization

Reza Eghbali, Maryam Fazel

Online optimization covers problems such as online resource allocation, online bipartite matching, adwords (a central problem in e-commerce and advertising), and adwords with separ…

math.OC20146 cited

Exponentiated Subgradient Algorithm for Online Optimization under the Random Permutation Model

Reza Eghbali, Jon Swenson, Maryam Fazel

Online optimization problems arise in many resource allocation tasks, where the future demands for each resource and the associated utility functions change over time and are not k…