Balaji Lakshminarayanan

research

∙ 07/02/2023

Morse Neural Networks for Uncertainty Quantification

We introduce a new deep generative model useful for uncertainty quantifi...

0 Benoit Dherin, et al. ∙

research

∙ 05/26/2023

Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection Using Text-image Models

We focus on the challenge of out-of-distribution (OOD) detection in deep...

0 Yunhao Ge, et al. ∙

research

∙ 02/13/2023

A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models

Contrastively trained text-image models have the remarkable ability to p...

0 James Urquhart Allingham, et al. ∙

research

∙ 02/11/2023

Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play

Standard empirical risk minimization (ERM) training can produce deep neu...

0 Jeremiah Zhe Liu, et al. ∙

research

∙ 12/20/2022

Improving the Robustness of Summarization Models by Detecting and Removing Input Noise

The evaluation of abstractive summarization models typically uses test d...

0 Kundan Krishna, et al. ∙

research

∙ 09/30/2022

Out-of-Distribution Detection and Selective Generation for Conditional Language Models

Machine learning algorithms typically assume independent and identically...

0 Jie Ren, et al. ∙

research

∙ 05/01/2022

A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awareness

Accurate uncertainty quantification is a major challenge in deep learnin...

54 Jeremiah Zhe Liu, et al. ∙

research

∙ 11/25/2021

Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift

The concern of overconfident mis-predictions under distributional shift ...

0 Kehang Han, et al. ∙

research

∙ 10/15/2021

Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation

We investigate the robustness of vision transformers (ViTs) through the ...

27 Yao Qin, et al. ∙

research

∙ 10/07/2021

Sparse MoEs meet Efficient Ensembles

Machine learning models based on the aggregated outputs of submodels, ei...

3 James Urquhart Allingham, et al. ∙

research

∙ 10/06/2021

Deep Classifiers with Label Noise Modeling and Distance Awareness

Uncertainty estimation in deep learning has recently emerged as a crucia...

0 Vincent Fortuin, et al. ∙

research

∙ 07/30/2021

Soft Calibration Objectives for Neural Networks

Optimal decision making requires that classifiers produce uncertainty es...

0 Archit Karandikar, et al. ∙

research

∙ 07/23/2021

A Realistic Simulation Framework for Learning with Label Noise

We propose a simulation framework for generating realistic instance-depe...

0 Keren Gu, et al. ∙

research

∙ 07/17/2021

BEDS-Bench: Behavior of EHR-models under Distributional Shift–A Benchmark

Machine learning has recently demonstrated impressive progress in predic...

19 Anand Avati, et al. ∙

research

∙ 06/24/2021

Task-agnostic Continual Learning with Hybrid Probabilistic Models

Learning new tasks continuously without forgetting on a constantly chang...

0 Polina Kirichenko, et al. ∙

research

∙ 06/16/2021

A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection

Mahalanobis distance (MD) is a simple and popular post-processing method...

0 Jie Ren, et al. ∙

research

∙ 06/15/2021

Predicting Unreliable Predictions by Shattering a Neural Network

Piecewise linear neural networks can be split into subfunctions, each wi...

7 Xu Ji, et al. ∙

research

∙ 06/07/2021

Uncertainty Baselines: Benchmarks for Uncertainty Robustness in Deep Learning

High-quality estimates of uncertainty and robustness are crucial for num...

0 Zachary Nado, et al. ∙

research

∙ 06/06/2021

Exploring the Limits of Out-of-Distribution Detection

Near out-of-distribution detection (OOD) is a major challenge for deep n...

0 Stanislav Fort, et al. ∙

research

∙ 04/08/2021

Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditions

We develop and rigorously evaluate a deep learning based system that can...

27 Abhijit Guha Roy, et al. ∙

research

∙ 10/19/2020

Combining Ensembles and Data Augmentation can Harm your Calibration

Ensemble methods which average over multiple neural network predictions ...

0 Yeming Wen, et al. ∙

research

∙ 10/13/2020

Training independent subnetworks for robust prediction

Recent approaches to efficiently ensemble neural networks have shown tha...

0 Marton Havasi, et al. ∙

research

∙ 07/11/2020

Bayesian Deep Ensembles via the Neural Tangent Kernel

We explore the link between deep ensembles and Gaussian processes (GPs) ...

11 Bobby He, et al. ∙

research

∙ 07/10/2020

Revisiting One-vs-All Classifiers for Predictive Uncertainty and Out-of-Distribution Detection in Neural Networks

Accurate estimation of predictive uncertainty in modern neural networks ...

20 Shreyas Padhy, et al. ∙

research

∙ 06/19/2020

Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift

Covariate shift has been shown to sharply degrade both predictive accura...

10 Zachary Nado, et al. ∙

research

∙ 06/17/2020

Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awareness

Bayesian neural networks (BNN) and deep ensembles are principled approac...

20 Jeremiah Zhe Liu, et al. ∙

research

∙ 06/16/2020

Density of States Estimation for Out-of-Distribution Detection

Perhaps surprisingly, recent studies have shown probabilistic model like...

0 Warren R. Morningstar, et al. ∙

research

∙ 05/14/2020

Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors

Bayesian neural networks (BNNs) demonstrate promising success in improvi...

11 Michael W. Dusenberry, et al. ∙

research

∙ 12/05/2019

AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty

Modern deep neural networks can achieve high accuracy when the training ...

21 Dan Hendrycks, et al. ∙

research

∙ 12/05/2019

Normalizing Flows for Probabilistic Modeling and Inference

Normalizing flows provide a general mechanism for defining expressive pr...

33 George Papamakarios, et al. ∙

research

∙ 12/05/2019

Deep Ensembles: A Loss Landscape Perspective

Deep ensembles have been empirically shown to be a promising approach fo...

10 Stanislav Fort, et al. ∙

research

∙ 06/07/2019

Detecting Out-of-Distribution Inputs to Deep Generative Models Using a Test for Typicality

Recent work has shown that deep generative models can assign higher like...

5 Eric Nalisnick, et al. ∙

research

∙ 06/07/2019

Likelihood Ratios for Out-of-Distribution Detection

Discriminative neural networks offer little or no performance guarantees...

6 Jie Ren, et al. ∙

research

∙ 06/06/2019

Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift

Modern machine learning methods including deep learning have achieved gr...

9 Yaniv Ovadia, et al. ∙

research

∙ 02/07/2019

Hybrid Models with Deep and Invertible Features

We propose a neural hybrid model consisting of a linear model defined on...

12 Eric Nalisnick, et al. ∙

research

∙ 12/05/2018

Adapting Auxiliary Losses Using Gradient Similarity

One approach to deal with the statistical inefficiency of neural network...

10 Yunshu Du, et al. ∙

research

∙ 10/22/2018

Do Deep Generative Models Know What They Don't Know?

A neural network deployed in the wild may be asked to make predictions f...

6 Eric Nalisnick, et al. ∙

research

∙ 07/24/2018

Learning from Delayed Outcomes with Intermediate Observations

Optimizing for long term value is desirable in many practical applicatio...

4 Timothy A. Mann, et al. ∙

research

∙ 02/19/2018

Distribution Matching in Variational Inference

The difficulties in matching the latent posterior to the prior, balancin...

0 Mihaela Rosca, et al. ∙

research

∙ 10/23/2017

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

Generative adversarial networks (GANs) are a family of generative models...

0 William Fedus, et al. ∙

research

∙ 06/15/2017

Variational Approaches for Auto-Encoding Generative Adversarial Networks

Auto-encoding generative adversarial networks (GANs) combine the standar...

0 Mihaela Rosca, et al. ∙

research

∙ 05/30/2017

The Cramer Distance as a Solution to Biased Wasserstein Gradients

The Wasserstein probability metric has received much attention from the ...

0 Marc G. Bellemare, et al. ∙

research

∙ 10/11/2016

Learning in Implicit Generative Models

Generative adversarial networks (GANs) provide an algorithmic framework ...

0 Shakir Mohamed, et al. ∙

research

∙ 06/16/2016

The Mondrian Kernel

We introduce the Mondrian kernel, a fast random feature approximation to...

0 Matej Balog, et al. ∙

research

∙ 12/31/2015

Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server

This paper makes two contributions to Bayesian machine learning algorith...

0 Leonard Hasenclever, et al. ∙

research

∙ 06/19/2015

Approximate Inference with the Variational Holder Bound

We introduce the Variational Holder (VH) bound as an alternative to Vari...

0 Guillaume Bouchard, et al. ∙

research

∙ 06/11/2015

Mondrian Forests for Large-Scale Regression when Uncertainty Matters

Many real-world regression problems demand a measure of the uncertainty ...

0 Balaji Lakshminarayanan, et al. ∙

research

∙ 03/09/2015

Kernel-Based Just-In-Time Learning for Passing Expectation Propagation Messages

We propose an efficient nonparametric strategy for learning a message op...

0 Wittawat Jitkrittum, et al. ∙

research

∙ 02/16/2015

Particle Gibbs for Bayesian Additive Regression Trees

Additive regression trees are flexible non-parametric models and popular...

0 Balaji Lakshminarayanan, et al. ∙

research

∙ 04/30/2013

Inferring ground truth from multi-annotator ordinal data: a probabilistic approach

A popular approach for large scale data annotation tasks is crowdsourcin...

0 Balaji Lakshminarayanan, et al. ∙

Balaji Lakshminarayanan

Featured Co-authors