Europe
Provable Tempered Overfitting of Minimal Nets and Typical Nets
For both learning rules, we prove overfitting is tempered.
Stochastic Spectral and Conjugate Descent Methods
Dmitry Kovalev, Peter Richtarik, Eduard Gorbunov, Elnur Gasanov
Neural Information Processing Systems http://nips.cc/
Nonzero-sum Adversarial Hypothesis Testing Games
Sarath Yasodharan, Patrick Loiseau
Neural Information Processing Systems http://nips.cc/
Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization Haitz Sáez de Ocáriz Borde Oxford Robotics Institute University of Oxford Álvaro Arroyo
Recent research indicates that the performance of machine learning models can be improved by aligning the geometry of the latent space with the underlying data structure.
DppNet: Approximating Determinantal Point Processes with Deep Networks
Zelda E. Mariet, Yaniv Ovadia, Jasper Snoek
Neural Information Processing Systems http://nips.cc/
Data-Efficient Hierarchical Reinforcement Learning
Ofir Nachum, Shixiang (Shane) Gu, Honglak Lee, Sergey Levine
Neural Information Processing Systems http://nips.cc/
When Can We Track Significant Preference Shifts in Dueling Bandits?
We show that the answer to this question depends on the properties of underlying preference distributions.
Towards a Zero-One Law for Column Subset Selection
Zhao Song, David Woodruff, Peilin Zhong
Indeed, this is a central question of recent workstudyinggeneralized lowrankmodels.
Binarized Spectral Compressive Imaging
Consequently, these methods can hardly be deployed on resource-limited mobile devices.