BL
Balaji Lakshminarayanan
cs.LGstat.MLcs.CVcs.AIcs.CLDermatologystat.COAcousticsAdaptation, PhysiologicalClimate Change
On Valency
published · living versionsW_5vz5yxu5·v1 · currentpublished
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step
with William Fedus, Mihaela Rosca, Andrew M. Dai, Shakir Mohamed +1
1 version
Preprints & journals
68 papers in the corpus · 2012–2026Climate-induced shifts in habitat suitability of forest types and adaptation strategies in the Western Ghats of Tamil Nadu, India.41580417 · Ramachandran, Andimuthu, Manickavasagam, Mithilasri, Hariharan, S et al.2026 · 1 citationScientific reports. 2026;16(1):3481
Gemini: A Family of Highly Capable Multimodal Models2312.11805v5 · Gemini Team Google: Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac et al.2023 · 838 citationsarXiv
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context2403.05530v5 · Gemini Team Google: Petko Georgiev, Ving Ian Lei, Ryan Burnell et al.2024 · 296 citationsarXiv
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness2408.05446v1 · Stanislav Fort, Balaji Lakshminarayanan2024 · 1 citationarXiv
Self-Evaluation Improves Selective Generation in Large Language Models2312.09300v1 · Jie Ren, Yao Zhao, Tu Vu et al.2023 · 2 citationsarXiv
Improving the Robustness of Summarization Models by Detecting and Removing Input Noise2212.09928v2 · Kundan Krishna, Yao Zhao, Jie Ren et al.2022 · 2 citationsarXiv
A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models2302.06235v2 · James Urquhart Allingham, Jie Ren, Michael W Dusenberry et al.2023 · 9 citationsarXiv
Sparse MoEs meet Efficient Ensembles2110.03360v2 · James Urquhart Allingham, Florian Wenzel, Zelda E Mariet et al.2021 · 1 citationarXiv
Morse Neural Networks for Uncertainty Quantification2307.00667v1 · Benoit Dherin, Huiyi Hu, Jie Ren et al.2023 · 2 citationsarXiv
Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models2305.17207v1 · Yunhao Ge, Jie Ren, Jiaping Zhao et al.2023 · 1 citationarXiv
Improving Zero-shot Generalization and Robustness of Multi-modal Models2212.01758v2 · Yunhao Ge, Jie Ren, Andrew Gallagher et al.2022 · 27 citationsarXiv
Out-of-Distribution Detection and Selective Generation for Conditional Language Models2209.15558v2 · Jie Ren, Jiaming Luo, Yao Zhao et al.2022 · 12 citationsarXiv
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation2110.07858v2 · Yao Qin, Chiyuan Zhang, Ting Chen et al.2021 · 16 citationsarXiv
What Are Effective Labels for Augmented Data? Improving Calibration and Robustness with AutoLabel2302.11188v1 · Yao Qin, Xuezhi Wang, Balaji Lakshminarayanan et al.2023 · 4 citationsarXiv
Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play2302.05807v1 · Jeremiah Zhe Liu, Krishnamurthy Dj Dvijotham, Jihyeon Lee et al.2023 · 0 citationsarXiv
A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness2205.00403v2 · Jeremiah Zhe Liu, Shreyas Padhy, Jie Ren et al.2022 · 35 citationsarXiv
Deep Classifiers with Label Noise Modeling and Distance Awareness2110.02609v2 · Vincent Fortuin, Mark Collier, Florian Wenzel et al.2021 · 0 citationsarXiv
Test Sample Accuracy Scales with Training Sample Density in Neural Networks2106.08365v7 · Xu Ji, Razvan Pascanu, Devon Hjelm et al.2021 · 1 citationarXiv
Plex: Towards Reliability using Pretrained Large Model Extensions2207.07411v1 · Dustin Tran, Jeremiah Liu, Michael W. Dusenberry et al.2022 · 37 citationsarXiv
Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions2104.03829v1 · Abhijit Guha Roy, Jie Ren, Shekoofeh Azizi et al.2021 · 76 citationsMedical Image Analysis (2022)
Uncertainty Baselines: Benchmarks for Uncertainty & Robustness in Deep Learning2106.04015v3 · Zachary Nado, Neil Band, Mark Collier et al.2021 · 36 citationsarXiv
Soft Calibration Objectives for Neural Networks2108.00106v2 · Archit Karandikar, Nicholas Cain, Dustin Tran et al.2021 · 8 citationsarXiv
Hybrid optimization model for conjunctive use of surface and groundwater resources in water deficit irrigation system.34850712 · Sampathkumar, Karthikeyan Moothampalayam, Ramasamy, Saravanan, Ramasubbu, Balamurugan et al.2021 · 11 citationsWater science and technology : a journal of the International Association on Water Pollution Research. 2021;84(10-11):3055-3071
Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift2111.12951v1 · Kehang Han, Balaji Lakshminarayanan, Jeremiah Liu2021 · 15 citationsarXiv
An Instance-Dependent Simulation Framework for Learning with Label Noise2107.11413v4 · Keren Gu, Xander Masotto, Vandana Bachani et al.2021 · 21 citationsarXiv
Training independent subnetworks for robust prediction2010.06610v2 · Marton Havasi, Rodolphe Jenatton, Stanislav Fort et al.2020 · 28 citationsarXiv
Exploring the Limits of Out-of-Distribution Detection2106.03004v3 · Stanislav Fort, Jie Ren, Balaji Lakshminarayanan2021 · 107 citationsarXiv
BEDS-Bench: Behavior of EHR-models under Distributional Shift--A Benchmark2107.08189v1 · Anand Avati, Martin Seneviratne, Emily Xue et al.2021 · 7 citationsarXiv
Task-agnostic Continual Learning with Hybrid Probabilistic Models2106.12772v1 · Polina Kirichenko, Mehrdad Farajtabar, Dushyant Rao et al.2021 · 4 citationsarXiv
A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection2106.09022v1 · Jie Ren, Stanislav Fort, Jeremiah Liu et al.2021 · 70 citationsarXiv
Normalizing Flows for Probabilistic Modeling and Inference1912.02762v2 · George Papamakarios, Eric Nalisnick, Danilo Jimenez Rezende et al.2019 · 340 citationsJournal of Machine Learning Research, 22(57):1-64, 2021
Combining Ensembles and Data Augmentation can Harm your Calibration2010.09875v2 · Yeming Wen, Ghassen Jerfel, Rafael Muller et al.2020 · 9 citationsarXiv
Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift2006.10963v3 · Zachary Nado, Shreyas Padhy, D. Sculley et al.2020 · 91 citationsarXiv
Adapting Auxiliary Losses Using Gradient Similarity1812.02224v2 · Yunshu Du, Wojciech M. Czarnecki, Siddhant M. Jayakumar et al.2018 · 91 citationsarXiv
Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness2006.10108v2 · Jeremiah Zhe Liu, Zi Lin, Shreyas Padhy et al.2020 · 214 citationsarXiv
Bayesian Deep Ensembles via the Neural Tangent Kernel2007.05864v2 · Bobby He, Balaji Lakshminarayanan, Yee Whye Teh2020 · 31 citationsarXiv
Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors2005.07186v2 · Michael W. Dusenberry, Ghassen Jerfel, Yeming Wen et al.2020 · 29 citationsarXiv
Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks2007.05134v1 · Shreyas Padhy, Zachary Nado, Jie Ren et al.2020 · 27 citationsarXiv
Deep Ensembles: A Loss Landscape Perspective1912.02757v2 · Stanislav Fort, Huiyi Hu, Balaji Lakshminarayanan2019 · 336 citationsarXiv
Density of States Estimation for Out-of-Distribution Detection2006.09273v2 · Warren R. Morningstar, Cusuh Ham, Andrew G. Gallagher et al.2020 · 13 citationsarXiv
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty1912.02781v2 · Dan Hendrycks, Norman Mu, Ekin D. Cubuk et al.2019 · 708 citationsarXiv
Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift1906.02530v2 · Yaniv Ovadia, Emily Fertig, Jie Ren et al.2019 · 965 citationsarXiv
Likelihood Ratios for Out-of-Distribution Detection1906.02845v2 · Jie Ren, Peter J. Liu, Emily Fertig et al.2019 · 8 citationsarXiv
Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality1906.02994v2 · Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh et al.2019 · 78 citationsarXiv
Learning from Delayed Outcomes via Proxies with Applications to Recommender Systems1807.09387v2 · Timothy A. Mann, Sven Gowal, Andr'as Gyorgy et al.2018 · 6 citationsarXiv
Distribution Matching in Variational Inference1802.06847v4 · Mihaela Rosca, Balaji Lakshminarayanan, Shakir Mohamed2018 · 47 citationsarXiv
Hybrid Models with Deep and Invertible Features1902.02767v2 · Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh et al.2019 · 31 citationsarXiv
Clinically applicable deep learning for diagnosis and referral in retinal disease.30104768 · De Fauw, Jeffrey, Ledsam, Joseph R, Romera-Paredes, Bernardino et al.2019 · 2,729 citationsNature medicine. 2018;24(9):1342-1350
Do Deep Generative Models Know What They Don't Know?1810.09136v3 · Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh et al.2018 · 55 citationsarXiv
Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step1710.08446v3 · William Fedus, Mihaela Rosca, Balaji Lakshminarayanan et al.2017 · 159 citationsarXivon Valency
Career total: 93 works. 68 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.