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
Opening remarks: Memory in Artificial and Real Intelligence (MemARI)
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Trustworthy Monte Carlo
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Parallel tempering with a variational reference
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Real World Offline Reinforcement Learning with Realistic Data Source
Watch later
Gaoyue Zhou, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Taming Fat-Tailed (“Heavier-Tailed” with Potentially Infinite Variance) Noise in Federated Learning
Watch later
Haibo Yang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs
Watch later
Zenan Li, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%