More Like this

1. Learning from a Learning User for Optimal Recommendations

   Yao, Fan; Li, Chuanhao; Nekipelov, Denis; Wang, Hongning; Xu, Haifeng (July 2022, Proceedings of the 39th International Conference on Machine Learning)

   Chaudhuri, Kamalika; Jegelka, Stefanie; Song, Le; Szepesvari, Csaba; Niu, Gang; Sabato, Sivan (Ed.)

   In real-world recommendation problems, especially those with a formidably large item space, users have to gradually learn to estimate the utility of any fresh recommendations from their experience about previously consumed items. This in turn affects their interaction dynamics with the system and can invalidate previous algorithms built on the omniscient user assumption. In this paper, we formalize a model to capture such ”learning users” and design an efficient system-side learning solution, coined Noise-Robust Active Ellipsoid Search (RAES), to confront the challenges brought by the non-stationary feedback from such a learning user. Interestingly, we prove that the regret of RAES deteriorates gracefully as the convergence rate of user learning becomes worse, until reaching linear regret when the user’s learning fails to converge. Experiments on synthetic datasets demonstrate the strength of RAES for such a contemporaneous system-user learning problem. Our study provides a novel perspective on modeling the feedback loop in recommendation problems. 

   more » « less
2. Learning a manifold from a teacher’s demonstrations

   Wang, P.; Givchi, A.; Shafto, P. (January 2020, NeurIPS workshop: TDA and beyond)

   null (Ed.)
3. Learning from Teaching: A New Model of Teacher Learning

   Copur-Gencturk, Yasemin; Rodrigues, Jessica. (January 2020, athematics Education Across Cultures: Proceedings of the 42nd Meeting of the North American Chapter of the International Group for the Psychology of Mathematics Education)

   Sacristán, A.I. (Ed.)

   The development of a model that explains how teachers learn from teaching is critical for informing the design of quality professional development, which in turn can support teachers’ effectiveness and student learning. This article reports the authors’ effort to develop a model that brings together critical findings from existing research to unpack when and under what conditions teachers learn from teaching. Grounded in evidence drawn from research relating to teachers’ learning and practice, the authors build a rationale for the Learning from Teaching (LFT) model, introduce each component of the model and propose two conditions that increase the likelihood of teachers’ learning from their own teaching. 

   more » « less
4. Deep learning from a statistical perspective

   https://doi.org/10.1002/sta4.294  

   Yuan, Yubai; Deng, Yujia; Zhang, Yanqing; Qu, Annie (January 2020, Stat)

   null (Ed.)
5. Learning Graphical Models from a Distributed Stream

   https://doi.org/10.1109/ICDE.2018.00071  

   Zhang, Yu; Tirthapura, Srikanta; Cormode, Graham (April 2018, Proceedings of the IEEE 34th International Conference on Data Engineering (ICDE))

   A current challenge for data management systems is to support the construction and maintenance of machine learning models over data that is large, multi-dimensional, and evolving. While systems that could support these tasks are emerging, the need to scale to distributed, streaming data requires new models and algorithms. In this setting, as well as computational scalability and model accuracy, we also need to minimize the amount of communication between distributed processors, which is the chief component of latency. We study Bayesian Networks, the workhorse of graphical models, and present a communication-efficient method for continuously learning and maintaining a Bayesian network model over data that is arriving as a distributed stream partitioned across multiple processors. We show a strategy for maintaining model parameters that leads to an exponential reduction in communication when compared with baseline approaches to maintain the exact MLE (maximum likelihood estimation). Meanwhile, our strategy provides similar prediction errors for the target distribution and for classification tasks. 

   more » « less