Home /

Research

Showing 145 - 150 / 897

Diversity-Guided Multi-Objective Bayesian Optimization With Batch Evaluations


Authors:  MinaKonakovicLukovic, YunshengTian, WojciechMatusik....
Published date-12/01/2020

Abstract: Many science, engineering, and design optimization problems require balancing the trade-offs between several conflicting objectives. The objectives are often black-box functions whose evaluations are time-consuming and costly. Multi-objective Bayesian optimization …

Learning to summarize with human feedback


Authors:  NisanStiennon, LongOuyang, JeffreyWu....
Published date-12/01/2020

Abstract: As language models become more powerful, training and evaluation are increasingly bottlenecked by the data and metrics used for a particular task. For example, summarization models are often trained to …

Model Class Reliance for Random Forests


Authors:  GavinSmith, RobertoMansilla, JamesGoulding....
Published date-12/01/2020

Abstract: Variable Importance (VI) has traditionally been cast as the process of estimating each variables contribution to a predictive model's overall performance. Analysis of a single model instance, however, guarantees no …

Learning Disentangled Representations and Group Structure of Dynamical Environments


Authors:  RobinQuessard, ThomasBarrett, WilliamClements....
Published date-12/01/2020

Abstract: Learning disentangled representations is a key step towards effectively discovering and modelling the underlying structure of environments. In the natural sciences, physics has found great success by describing the universe …

Dual-Free Stochastic Decentralized Optimization with Variance Reduction


Authors:  HadrienHendrikx, FrancisBach, LaurentMassoulié....
Published date-12/01/2020

Abstract: We consider the problem of training machine learning models on distributed data in a decentralized way. For finite-sum problems, fast single-machine algorithms for large datasets rely on stochastic updates combined …

Inverting Gradients - How easy is it to break privacy in federated learning?


Authors:  JonasGeiping, HartmutBauermeister, HannahDröge....
Published date-12/01/2020
Tasks:  FederatedLearning

Abstract: The idea of federated learning is to collaboratively train a neural network on a server. Each user receives the current weights of the network and in turns sends parameter updates …

Filter by

Categories

Tags