Country
Poisson-Randomized Gamma Dynamical Systems
Aaron Schein, Scott Linderman, Mingyuan Zhou, David Blei, Hanna Wallach
Neural Information Processing Systems http://nips.cc/
NoRL,NoSimulation: LearningtoNavigatewithout Navigating
NRNS outperforms RL-based formulations by a significant margin.
WhenDoesDifferentiallyPrivateLearning NotSufferinHighDimensions?
Large pretrained models can be fine-tuned with differential privacy to achieve performance approaching thatofnon-privatemodels. Acommon themeinthese results is the surprising observation that high-dimensional models can achieve favorable privacy-utility trade-offs.
Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses Seungwoo Y oo Juil Koo Kyeongmin Y eo Minhyuk Sung KAIST {dreamy1534,63days,aaaaa,mhsung }@kaist.ac.kr
To better distill pose information from the object's geometry, we propose the implicit pose applier to output an intrinsic mesh property, the face Jacobian. Once the extracted pose information is transferred to the target object, the pose applier is fine-tuned in a self-supervised manner to better describe the target object's shapes with pose
CodedResidualTransformforGeneralizableDeep MetricLearning
Afundamental challenge indeep metric learning isthegeneralization capability of the feature embedding network model since the embedding network learned ontraining classes needtobeevaluated onnewtestclasses.
A Bayesian Theory of Conformity in Collective Decision Making
Koosha Khalvati, Saghar Mirbagheri, Seongmin A. Park, Jean-Claude Dreher, Rajesh PN Rao
Neural Information Processing Systems http://nips.cc/
Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs
Experimental results have shown that curriculum learning, i.e., presenting simpler