Accepted Papers

Poster and Spotlight Instructions

  • Accepted papers will receive a talk or a poster at the workshop and the abstracts will appear on the ICML website. Authors can elect to link this abstract to a version of their paper hosted elsewhere (e.g. arXiv, or a personal server).

  • Accepted papers will not have a synchronous virtual presentation option --- however, all authors of accepted papers can send in a 3-5 minute video which we will link to on this website.

  • Dates:

    • We will make final notifications of spotlights by June 15.

    • The camera-ready for spotlight video submission deadline for spotlight talk recordings is July 1, AOE.

    • If you have a poster, print it and bring it to the conference! Here are the guidelines (size etc.): https://wiki.eventhosts.cc/en/reference/physical-poster-presenter-instructions

    • Are you unable to attend the conference but would like your hard work to be visible in a physical setting? Do you dislike carrying your poster on the plane? T3 Expo will print and deliver to the workshop. DEADLINE FOR T3 POSTER PRINTING: Friday, June 24. See https://icml.cc/FAQ/PrintPostersOnsite

Accepted Paper Videos

  • Training Uncertainty-Aware Classifiers with Conformalized Deep Learning by Bat-Sheva Einbinder, Yaniv Romano, Matteo Sesia, and Yanfei Zhou

  • Approximate Conditional Coverage via Neural Model Approximations by Allen Schmalz and Danielle Rasooly

  • Conformal Training: Learning Optimal Conformal Classifiers by David Stutz, Ali Taylan Cemgil, Krishnamurthy (Dj) Dvijotham, and Arnaud Doucet

  • Conformal Off-Policy Prediction in Contextual Bandits by Muhammad Faaiz Taufiq, Jean-Francois Ton, Rob Cornish, Yee Whye Teh, and Arnaud Doucet

  • Conformalized Survival Analysis with Adaptive Cutoffs by Rina F. Barber, Zhimei Ren, Yu Gui, and Rohan Hore

  • Simple Regularisation for Uncertainty-Aware Knowledge Distillation by Martin Ferianc and Miguel Rodrigues

  • Calibrating probabilistic hierarchical forecasts with conformal predictions by Daan Ferdinandusse

  • Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection by Xiongjie Chen, Yunpeng Li, and Yongxin Yang

  • Rashomon Capacity - Quantifying Predictive Multiplicity in Probabilistic Classification by Hsiang Hsu and Flavio P. Calmon

  • Instance-Based Uncertainty Estimation for Gradient-Boosted Regression Trees by Jonathan Brophy and Daniel Lowd

  • Conformal Credal Self-Supervised Learning by Julian Lienen, Caglar Demir, and Eyke Hüllermeier

ICML22_Poster.mp4

  • Mitigating Neural Network Overconfidence with Logit Normalization by Hongxin Wei, Renchunzi Xie, Hao Cheng, Lei Feng, Bo An, and Yixuan Li

  • Trascending TRANSCEND: Revisiting Malware Classification in the Presence of Concept Drift by Federico Barbero, Feargus Pendlebury, Fabio Pierazzi, and Lorenzo Cavallero

  • Valid inferential models for prediction in supervised learning problems, by Leonardo Cella and Ryan Martin

  • Dropout Prediction Uncertainty Estimation, by Haichao Yu, Zhe Chen, Dong Lin, Gil E. Shamir, and Jie Han

  • Applying Regression Conformal Prediction with Nearest Neighbors to time series data, by Samya Tajmouati, Bouazza El Wahbi and Dakkon Mohamed

  • Calibrating probabilistic predictions of quantile regression forests with conformal predictive systems, by Di Wang, Ping Wang, Cong Wang, and Pingping Wang

  • Adaptive Conformal Predictions for Time Series by Margaux Zaffran, Olivier Féron, Yannig Goude, Julie Josse and Aymeric Dieuleveut

  • VaR-Control: Bounding the Probability of High-Loss Predictions by Jake Snell, Thomas Zollo and Richard Zemel

  • Tracking the risk of a deployed model and detecting harmful distribution shifts by Aleksandr Podkopaev and Aaditya Ramdas

  • T-Cal: An optimal test for the calibration of predictive models by Donghwan Lee, Xinmeng Huang, Hamed Hassani and Edgar Dobriban

  • Calibration Generalization by Annabelle Carrell, Neil Mallinar, James Lucas and Preetum Nakkiran

  • Modular Conformal Calibration by Charles Marx, Shengjia Zhou, Willie Neiswanger and Stefano Ermon

  • Sample-dependent Temperature Scaling for Improved Calibration by Tom Joy, Francesco Pinto, Ser-Nam Lim, Philip Torr and Puneet Dokania

  • Provably Improving Expert Predictions with Prediction Sets by Eleni Straitouri, Lequn Wang, Nastaran Okati and Manuel Gomez Rodriguez

  • Conformalized Online Learning: Online Calibration Without a Holdout Set by Shai Feldman, Stephen Bates and Yaniv Romano

  • Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imaging by Amit Kohli, Anastasios Angelopoulos, Stephen Bates, Jitendra Malik, Michael Jordan, Thayer Alshaabi, Srigokul Upadhyayula and Yaniv Romano

  • Calibration Divergences: Trainable Objectives for Uncertainty-Aware Prediction by Charles Marx and Stefano Ermon

  • JAW: Predictive Inference under Covariate Shift by Andrew Prinster, Anqi Liu and Suchi Saria

  • An empirical Bayes approach to class-conditional conformal inference by Tiffany Ding, Anastasios Angelopoulos and Stephen Bates

  • Confident Sinkhorn Allocation for Pseudo-Labeling by Vu Nguyen, Sachin Farfade and Anton van den Hengel

  • Predictive Multiplicity in Probabilistic Classification by Jamelle Watson-Daniels, David Parkes and Berk Ustun

  • Inference for Interpretable Machine Learning: Fast, Model-Agnostic Confidence Intervals for Feature Importance by Luqin Gan, Lili Zheng and Genevera I. Allen

  • DAUX: a Density-based Approach for Uncertainty eXplanations by Hao Sun, Boris van Breugel, Jonathan Crabbé, Nabeel Seedat and Mihaela van der Schaar

  • Fairness in the First Stage of Two-Stage Recommender Systems by Lequn Wang and Thorsten Joachims

  • Revisiting Recalibration by Jonathan Pearce

  • crepes: a Python Package for Generating Conformal Regressors and Predictive Systems by Henrik Boström

  • Split Conformal Prediction for Dependent Data by Roberto I. Oliveira, Paulo Orenstein, Thiago Ramos and João Vitor Romano

  • Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectly by Spencer Whitehead, Suzanne Petryk, Vedaad Shakib, Joseph Gonzalez, Trevor Darrell, Anna Rohrbach and Marcus Rohrbach

  • Calibrated Multiple-Output Quantile Regression with Representation Learning by Shai Feldman, Stephen Bates and Yaniv Romano

  • Robust Flow-based Conformal Inference (FCI) with Statistical Guarantee by Youhui Ye, Meimei Liu and Xin Xing

  • Conformal prediction set for time-series by Chen Xu and Yao Xie

  • Calibration of Natural Language Understanding Models with Venn--ABERS Predictors by Patrizio Giovannotti

  • Probabilistic Conformal Prediction Using Conditional Random Samples by Zhendong Wang, Ruijiang Gao, Mingzhang Yin, Mingyuan Zhou and David Blei

  • Fast Nonlinear Vector Quantile Regression by Aviv A. Rosenberg, Sanketh Vedula, Yaniv Romano and Alex M. Bronstein

  • Confident Adaptive Language Modeling by Tal Schuster and Adam Fisch

  • Conformal Prediction Sets with Limited False Positives by Adam Fisch, Tal Schuster, Tommi Jaakkola and Regina Barzilay

  • Distribution Free Active Learning via Minimal Stochastic Complexity by Shachar Shayovitz and Meir Feder

  • Conformal prediction with repeated measurements by Yonghoon Lee and Rina Barber

  • Stable Conformal Prediction Sets by Eugene Ndiaye

  • Three Applications of Conformal Prediction for Rating Breast Density in Mammography by Charles Lu, Ken Chang, Praveer Singh and Jayashree Kalpathy-Cramer

  • Dropout Prediction Uncertainty Estimation Using Neuron Activation Strength by Haichao Yu, Zhe Chen, Dong Lin, Gil I. Shamir and Jie Han

  • Prediction Intervals for Simulation Metamodeling by Henry Lam and Haofeng Zhang

  • MAPIE: an open-source library for distribution-free uncertainty quantification by Vianney Taquet, Vincent Blot, Thomas Morzadec, Louis Lacombe and Nicolas Brunel

  • Factor Model of Mixtures and Conformalized Regression by Cheng Peng and Stan Uryasev

  • Assessment of Prediction Intervals Using Uncertainty Characteristics Curves by Jiri Navratil, Benjamin Elder, Matthew Arnold, Soumya Ghosh and Prasanna Sattigeri

  • Calibrated and Sharp Uncertainties in Deep Learning via Density Estimation by Volodymyr Kuleshov and Shachi Deshpande

  • Towards PAC Multi-Object Detection and Tracking by Shuo Li, Sangdon Park, Xiayan Ji, Insup Lee and Osbert Bastani

  • Practical Adversarial Multivalid Conformal Prediction by Osbert Bastani, Varun Gupta, Christopher Jung, Georgy Noarov, Ramya Ramalingam and Aaron Roth

  • Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning by Bertrand Charpentier, Ransalu Senanayake, Mykel Kochenderfer and Stephan Günnemann

  • Bounded Implicit Variational Inference by Anshuk Uppal, Wouter Boomsma and Jes Frellsen

  • Faster online calibration without randomization: interval forecasts and the power of two choices by Chirag Gupta and Aaditya Ramdas

  • PAC Prediction Sets for Meta-Learning by Sangdon Park, Edgar Dobriban, Insup Lee and Osbert Bastani

  • Stock Market Prediction Using Machine Learning by Surya Prakash, Rahul Kumar Gupta and Vikas Srivasatva

  • Nonparametric Estimation and Conformal Inference of the Sufficient Forecasting With a Diverging Number of Factors by Xiufan Yu, Jiawei Yao and Lingzhou Xue

  • Clustering of Trajectories using Non-Parametric Conformal DBSCAN Algorithm by Haotian Wang, Jie Gao and Minge Xie

  • Semantic uncertainty intervals for disentangled latent spaces by Swami Sankaranarayanan, Anastasios Angelopoulos, Stephen Bates, Yaniv Romano and Phillip Isola

  • Multiple testing framework for Out-of-Distribution detection by Akshayaa Magesh, Venugopal V. Veeravalli, Anirban Roy, and Susmit Jha