A Theory of Learning with Competing Objectives and User Feedback
Dec 2, 2022
Speakers
Pranjal Awasthi
Speaker · 0 followers
Corinna Cortes
Speaker · 1 follower
Yishay Mansour
Speaker · 1 follower
Mehryar Mohri
Speaker · 4 followers
About
Large-scale deployed learning systems are often evaluated alongmultiple objectives or criteria. But, how can we learn or optimizesuch complex systems, with potentially conflicting or evenincompatible objectives? How can we improve the system when user feedback becomes available, feedback possibly alerting to issues not previously optimized for by the system?We present a new theoretical model for learning and optimizing suchcomplex systems. Rather than committing to a static or pre-definedtradeoff for the multiple objectives, our model is guided by thefeedback received, which is used to update its internal state.Our model supports multiple objectives that can be of very generalform and takes into account their potential incompatibilities.We consider both a stochastic and an adversarial setting. In thestochastic setting, we show that our framework can be naturally castas a Markov Decision Process with stochastic losses, for which we giveefficient vanishing regret algorithmic solutions. In the adversarialsetting, we design efficient algorithms with competitive ratioguarantees.We also report the results of experiments with our stochasticalgorithms validating their effectiveness.Large-scale deployed learning systems are often evaluated alongmultiple objectives or criteria. But, how can we learn or optimizesuch complex systems, with potentially conflicting or evenincompatible objectives? How can we improve the system when user feedback becomes available, feedback possibly alerting to issues not previously optimized for by the system?We present a new theoretical model for learning and optimizing suchcomplex systems. Rather than committing to a static or pre-definedtradeof…
Organizer
NeurIPS 2022
Account · 954 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Masked Autoencoders As Spatiotemporal Learners
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction
Watch later
Qiao Feng, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Robustness to Unbounded Smoothness of Generalized SignSGD
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Factuality Enhanced LMs for Open-Ended Text Generation
Watch later
Nayeon Lee, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Unsupervised Learning of Equivariant Structure from Sequences
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Lottery Tickets on a Data Diet: Finding Initializations with Sparse Trainable Networks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%