An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence (English)
- New search for: Kristiadi, Agustinus
- New search for: Hein, Matthias
- New search for: Hennig, Philipp
- New search for: Kristiadi, Agustinus
- New search for: Hein, Matthias
- New search for: Hennig, Philipp
In:
35th Conference on Neural Information Processing Systems (NeurIPS 2021) ; Volume 23 of 36
; 18789-18800
;
2022
- Conference paper / Print
-
Title:An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic Overconfidence
-
Contributors:
-
Conference:NeurIPS ; 35. ; 2021 ; Online
-
Published in:
-
Publisher:
- New search for: Curran Associates, Inc.
-
Place of publication:Red Hook, NY
-
Publication date:2022
-
Type of media:Conference paper
-
Type of material:Print
-
Language:English
-
Source:
The tables of contents are generated automatically and are based on the data records of the individual contributions available in the index of the TIB portal. The display of the Tables of Contents may therefore be incomplete.
- 18646
-
Heavy Ball Neural Ordinary Differential EquationsXia, Hedi / Suliafu, Vai / Ji, Hangjie / Nguyen, Tan / Bertozzi, Andrea / Osher, Stanley / Wang, Bao et al. | 2022
- 18660
-
Structure learning in polynomial time: Greedy algorithms, Bregman information, and exponential familiesRajendran, Goutham / Kivva, Bohdan / Gao, Ming / Aragam, Bryon et al. | 2022
- 18673
-
On the Sample Complexity of Learning under Geometric StabilityBietti, Alberto / Venturi, Luca / Bruna, Joan et al. | 2022
- 18685
-
SIMILAR: Submodular Information Measures Based Active Learning In Realistic ScenariosKothawade, Suraj / Beck, Nathan / Killamsetty, Krishnateja / Iyer, Rishabh et al. | 2022
- 18698
-
Monte Carlo Tree Search With Iteratively Refining State AbstractionsSokota, Samuel / Ho, Caleb Y / Ahmad, Zaheen / Kolter, J. Zico et al. | 2022
- 18710
-
Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual LearningDENG, Danruo / Chen, Guangyong / Hao, Jianye / Wang, Qiong / Heng, Pheng-Ann et al. | 2022
- 18722
-
Taxonomizing local versus global structure in neural network loss landscapesYang, Yaoqing / Hodgkinson, Liam / Theisen, Ryan / Zou, Joe / Gonzalez, Joseph E / Ramchandran, Kannan / Mahoney, Michael W et al. | 2022
- 18734
-
Learning Models for Actionable RecourseRoss, Alexis / Lakkaraju, Himabindu / Bastani, Osbert et al. | 2022
- 18747
-
Efficient and Accurate Gradients for Neural SDEsKidger, Patrick / Foster, James / Li, Xuechen (Chen) / Lyons, Terry et al. | 2022
- 18762
-
EIGNN: Efficient Infinite-Depth Graph Neural NetworksLiu, Juncheng / Kawaguchi, Kenji / Hooi, Bryan / Wang, Yiwei / Xiao, Xiaokui et al. | 2022
- 18774
-
Fractal Structure and Generalization Properties of Stochastic Optimization AlgorithmsCamuto, Alexander / Deligiannidis, George / Erdogdu, Murat A / Gurbuzbalaban, Mert / Simsekli, Umut / Zhu, Lingjiong et al. | 2022
- 18789
-
An Infinite-Feature Extension for Bayesian ReLU Nets That Fixes Their Asymptotic OverconfidenceKristiadi, Agustinus / Hein, Matthias / Hennig, Philipp et al. | 2022
- 18801
-
Bandit Phase RetrievalLattimore, Tor / Hao, Botao et al. | 2022
- 18812
-
Lower Bounds on Metropolized Sampling Methods for Well-Conditioned DistributionsLee, Yin Tat / Shen, Ruoqi / Tian, Kevin et al. | 2022
- 18825
-
Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement LearningZhang, Xin / Liu, Zhuqing / Liu, Jia / Zhu, Zhengyuan / Lu, Songtao et al. | 2022
- 18839
-
Federated Graph Classification over Non-IID GraphsXie, Han / Ma, Jing / Xiong, Li / Yang, Carl et al. | 2022
- 18853
-
SubTab: Subsetting Features of Tabular Data for Self-Supervised Representation LearningUcar, Talip / Hajiramezanali, Ehsan / Edwards, Lindsay et al. | 2022
- 18866
-
Convergence Rates of Stochastic Gradient Descent under Infinite Noise VarianceWang, Hongjian / Gurbuzbalaban, Mert / Zhu, Lingjiong / Simsekli, Umut / Erdogdu, Murat A et al. | 2022
- 18878
-
Conflict-Averse Gradient Descent for Multi-task learningLiu, Bo / Liu, Xingchao / Jin, Xiaojie / Stone, Peter / Liu, Qiang et al. | 2022
- 18891
-
Amortized Synthesis of Constrained Configurations Using a Differentiable SurrogateSun, Xingyuan / Xue, Tianju / Rusinkiewicz, Szymon / Adams, Ryan P et al. | 2022
- 18907
-
Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular DiscriminationFoster, Dylan J / Krishnamurthy, Akshay et al. | 2022
- 18920
-
Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase TransitionAcharya, Jayadev / Canonne, Clement / Liu, Yuhan / Sun, Ziteng / Tyagi, Himanshu et al. | 2022
- 18932
-
Revisiting Deep Learning Models for Tabular DataGorishniy, Yury / Rubachev, Ivan / Khrulkov, Valentin / Babenko, Artem et al. | 2022
- 18944
-
Backdoor Attack with Imperceptible Input and Latent ModificationDoan, Khoa / Lao, Yingjie / Li, Ping et al. | 2022
- 18958
-
SOPE: Spectrum of Off-Policy EstimatorsYuan, Christina / Chandak, Yash / Giguere, Stephen / Thomas, Philip S. / Niekum, Scott et al. | 2022
- 18970
-
Label-Imbalanced and Group-Sensitive Classification under OverparameterizationKini, Ganesh Ramachandra / Paraskevas, Orestis / Oymak, Samet / Thrampoulidis, Christos et al. | 2022
- 18984
-
Neural Program Generation Modulo Static AnalysisMukherjee, Rohan / Wen, Yeming / Chaudhari, Dipak / Reps, Thomas / Chaudhuri, Swarat / Jermaine, Christopher et al. | 2022
- 18997
-
Unfolding Taylor' s Approximations for Image Restorationzhou, man / Fu, Xueyang / Xiao, Zeyu / Yang, Gang / Liu, Aiping / Xiong, Zhiwei et al. | 2022
- 19010
-
Metropolis-Hastings Data Augmentation for Graph Neural NetworksPark, Hyeonjin / Lee, Seunghun / Kim, Sihyeon / Park, Jinyoung / Jeong, Jisu / Kim, Kyung-Min / Ha, Jung-Woo / Kim, Hyunwoo J et al. | 2022
- 19021
-
Strategic Behavior is Bliss: Iterative Voting Improves Social WelfareKavner, Joshua / Xia, Lirong et al. | 2022
- 19033
-
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich ObservationsSekhari, Ayush / Dann, Christoph / Mohri, Mehryar / Mansour, Yishay / Sridharan, Karthik et al. | 2022
- 19046
-
Functional Regularization for Reinforcement Learning via Learned Fourier FeaturesLi, Alexander / Pathak, Deepak et al. | 2022
- 19056
-
Adaptive First-Order Methods Revisited: Convex Minimization without Lipschitz RequirementsAntonakopoulos, Kimon / Mertikopoulos, Panayotis et al. | 2022
- 19069
-
Adapting to function difficulty and growth conditions in private optimizationAsi, Hilal / Levy, Daniel / Duchi, John C et al. | 2022
- 19082
-
Support Recovery of Sparse Signals from a Mixture of Linear MeasurementsPal, Soumyabrata / Mazumdar, Arya / Gandikota, Venkata et al. | 2022
- 19095
-
Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivityLoizou, Nicolas / Berard, Hugo / Gidel, Gauthier / Mitliagkas, Ioannis / Lacoste-Julien, Simon et al. | 2022
- 19109
-
Tighter Expected Generalization Error Bounds via Wasserstein DistanceRodríguez Gálvez, Borja / Bassi, German / Thobaben, Ragnar / Skoglund, Mikael et al. | 2022
- 19122
-
Unifying Width-Reduced Methods for Quasi-Self-Concordant OptimizationAdil, Deeksha / Bullins, Brian / Sachdeva, Sushant et al. | 2022
- 19134
-
Bridging the Imitation Gap by Adaptive InsubordinationWeihs, Luca / Jain, Unnat / Liu, Iou-Jen / Salvador, Jordi / Lazebnik, Svetlana / Kembhavi, Aniruddha / Schwing, Alex et al. | 2022
- 19147
-
Adversarial Robustness with Non-uniform PerturbationsErdemir, Ecenaz / Bickford, Jeffrey / Melis, Luca / Aydore, Sergul et al. | 2022
- 19160
-
Container: Context Aggregation Networksgao, peng / Lu, Jiasen / Li, hongsheng / Mottaghi, Roozbeh / Kembhavi, Aniruddha et al. | 2022
- 19172
-
ConE: Cone Embeddings for Multi-Hop Reasoning over Knowledge GraphsZhang, Zhanqiu / Wang, Jie / Chen, Jiajun / Ji, Shuiwang / Wu, Feng et al. | 2022
- 19184
-
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-SharingKhodak, Mikhail / Tu, Renbo / Li, Tian / Li, Liam / Balcan, Maria-Florina F / Smith, Virginia / Talwalkar, Ameet et al. | 2022
- 19198
-
Training for the Future: A Simple Gradient Interpolation Loss to Generalize Along TimeNasery, Anshul / Thakur, Soumyadeep / Piratla, Vihari / De, Abir / Sarawagi, Sunita et al. | 2022
- 19210
-
Agent Modelling under Partial Observability for Deep Reinforcement LearningPapoudakis, Georgios / Christianos, Filippos / Albrecht, Stefano et al. | 2022
- 19223
-
Leveraging Distribution Alignment via Stein Path for Cross-Domain Cold-Start RecommendationLiu, Weiming / Su, Jiajie / Chen, Chaochao / Zheng, Xiaolin et al. | 2022
- 19235
-
Conservative Offline Distributional Reinforcement LearningMa, Yecheng / Jayaraman, Dinesh / Bastani, Osbert et al. | 2022
- 19248
-
Separation Results between Fixed-Kernel and Feature-Learning Probability MetricsDomingo i Enrich, Carles / Mroueh, Youssef et al. | 2022
- 19261
-
Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy LearningBibaut, Aurelien / Kallus, Nathan / Dimakopoulou, Maria / Chambaz, Antoine / van der Laan, Mark et al. | 2022
- 19274
-
Bayesian Optimization with High-Dimensional OutputsMaddox, Wesley J / Balandat, Maximilian / Wilson, Andrew G / Bakshy, Eytan et al. | 2022
- 19288
-
Finding Optimal Tangent Points for Reducing Distortions of Hard-label AttacksMa, Chen / Guo, Xiangyu / Chen, Li / Yong, Jun-Hai / Wang, Yisen et al. | 2022
- 19301
-
Scalable Diverse Model Selection for Accessible Transfer LearningBolya, Daniel / Mittapalli, Rohit / Hoffman, Judy et al. | 2022
- 19313
-
Light Field Networks: Neural Scene Representations with Single-Evaluation RenderingSitzmann, Vincent / Rezchikov, Semon / Freeman, Bill / Tenenbaum, Josh / Durand, Fredo et al. | 2022
- 19326
-
ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape ReconstructionYang, Gengshan / Sun, Deqing / Jampani, Varun / Vlasic, Daniel / Cole, Forrester / Liu, Ce / Ramanan, Deva et al. | 2022
- 19339
-
Understanding the Effect of Stochasticity in Policy OptimizationMei, Jincheng / Dai, Bo / Xiao, Chenjun / Szepesvari, Csaba / Schuurmans, Dale et al. | 2022
- 19352
-
Fine-Grained Zero-Shot Learning with DNA as Side InformationBadirli, Sarkhan / Akata, Zeynep / Mohler, George / Picard, Christine / Dundar, Mehmet M et al. | 2022
- 19363
-
Optimal Underdamped Langevin MCMC MethodHu, Zhengmian / Huang, Feihu / Huang, Heng et al. | 2022
- 19375
-
Scheduling jobs with stochastic holding costsLee, Dabeen / Vojnovic, Milan et al. | 2022
- 19385
-
REMIPS: Physically Consistent 3D Reconstruction of Multiple Interacting People under Weak SupervisionFieraru, Mihai / Zanfir, Mihai / Szente, Teodor / Bazavan, Eduard / Olaru, Vlad / Sminchisescu, Cristian et al. | 2022
- 19398
-
Differentiable Annealed Importance Sampling and the Perils of Gradient NoiseZhang, Guodong / Hsu, Kyle / Li, Jianing / Finn, Chelsea / Grosse, Roger B et al. | 2022
- 19411
-
PSD Representations for Effective Probability ModelsRudi, Alessandro / Ciliberto, Carlo et al. | 2022
- 19423
-
Exploiting a Zoo of Checkpoints for Unseen TasksHuang, Jiaji / Qiu, Qiang / Church, Kenneth et al. | 2022
- 19435
-
Towards Open-World Feature Extrapolation: An Inductive Graph Learning ApproachWu, Qitian / Yang, Chenxiao / Yan, Junchi et al. | 2022
- 19448
-
Adversarial Teacher-Student Representation Learning for Domain GeneralizationYang, Fu-En / Cheng, Yuan-Chia / Shiau, Zu-Yun / Wang, Yu-Chiang Frank et al. | 2022
- 19461
-
Stochastic bandits with groups of similar arms.Pesquerel, Fabien / SABER, Hassan / Maillard, Odalric-Ambrym et al. | 2022
- 19473
-
Tracking Without Re-recognition in Humans and MachinesLinsley, Drew / Malik, Girik / Kim, Junkyung / Govindarajan, Lakshmi Narasimhan / Mingolla, Ennio / Serre, Thomas et al. | 2022
- 19487
-
Rethinking conditional GAN training: An approach using geometrically structured latent manifoldsRamasinghe, Sameera / Farazi, Moshiur / Khan, Salman H / Barnes, Nick / Gould, Stephen et al. | 2022