UAI 2021

206 papers

Sequential core-set Monte Carlo

Boyan Beronov, Christian Weilbach, Frank Wood, Trevor Campbell

Geometric rates of convergence for kernel-based sampling algorithms

Rajiv Khanna, Liam Hodgkinson, Michael W. Mahoney

Min/max stability and box distributions

Michael Boratko, Javier Burroni, Shib Sankar Dasgupta, Andrew McCallum

Learning and certification under instance-targeted poisoning

Ji Gao, Amin Karbasi, Mohammad Mahmoody

Identifying regions of trusted predictions

Nivasini Ananthakrishnan, Shai Ben-David, Tosca Lechner, Ruth Urner

Towards a unified framework for fair and stable graph representation learning

Chirag Agarwal, Himabindu Lakkaraju, Marinka Zitnik

SDM-Net: A simple and effective model for generalized zero-shot learning

Shabnam Daghaghi, Tharun Medini, Anshumali Shrivastava

Disentangling mixtures of unknown causal interventions

Abhinav Kumar, Gaurav Sinha

No-regret approximate inference via Bayesian optimisation

Rafael Oliveira, Lionel Ott, Fabio Ramos

Efficient online inference for nonparametric mixture models

Rylan Schaeffer, Blake Bordelon, Mikail Khona, Weiwei Pan, Ila Rani Fiete

Exact and approximate hierarchical clustering using A*

Craig S. Greenberg, Sebastian Macaluso, Nicholas Monath, Avinava Dubey, Patrick Flaherty

Conditionally independent data generation

Kartik Ahuja, Prasanna Sattigeri, Karthikeyan Shanmugam, Dennis Wei, Karthikeyan Natesan Ramamurthy

Learning probabilistic sentential decision diagrams under logic constraints by sampling and averaging

Renato Lui Geh, Denis Deratani Mauá

Uncertainty in minimum cost multicuts for image and motion segmentation

Amirhossein Kardoost, Margret Keuper

PROVIDE: a probabilistic framework for unsupervised video decomposition

Polina Zablotskaia, Edoardo A. Dominici, Leonid Sigal, Andreas M. Lehrmann

Leveraging probabilistic circuits for nonparametric multi-output regression

Zhongjie Yu, Mingye Zhu, Martin Trapp, Arseny Skryagin, Kristian Kersting

Adrià Garriga-Alonso, Mark van der Wilk

Statistical mechanical analysis of neural network pruning

Rupam Acharyya, Ankani Chattoraj, Boyu Zhang, Shouman Das, Daniel Stefankovic

Explicit pairwise factorized graph neural network for semi-supervised node classification

Yu Wang, Yuesong Shen, Daniel Cremers

CORe: Capitalizing On Rewards in Bandit Exploration

Nan Wang, Branislav Kveton, Maryam Karimzadehgan

Sketching curvature for efficient out-of-distribution detection for deep neural networks

Apoorva Sharma, Navid Azizan, Marco Pavone

Condition number bounds for causal inference

Spencer L. Gordon, Vinayak M. Kumar, Leonard J. Schulman, Piyush Srivastava

q-Paths: Generalizing the geometric annealing path using power means

Vaden Masrani, Rob Brekelmans, Thang Bui, Frank Nielsen, Aram Galstyan

Learning in Multi-Player Stochastic Games

William Brown

Active multi-fidelity Bayesian online changepoint detection

Gregory W. Gundersen, Diana Cai, Chuteng Zhou, Barbara E. Engelhardt, Ryan P. Adams

SGD with low-dimensional gradients with applications to private and distributed learning

Shiva Prasad Kasiviswanathan

Doubly non-central beta matrix factorization for DNA methylation data

Aaron Schein, Anjali Nagulpally, Hanna Wallach, Patrick Flaherty

Gradient-based optimization for multi-resource spatial coverage problems

Nitin Kamra, Yan Liu

Explaining fast improvement in online imitation learning

Xinyan Yan, Byron Boots, Ching-An Cheng

Convergence behavior of belief propagation: estimating regions of attraction via Lyapunov functions

Harald Leisenberger, Christian Knoll, Richard Seeber, Franz Pernkopf

Staying in shape: learning invariant shape representations using contrastive learning

Jeffrey Gu, Serena Yeung

Non-PSD matrix sketching with applications to regression and optimization

Zhili Feng, Fred Roosta, David P. Woodruff

Diagnostics for conditional density models and Bayesian inference algorithms

David Zhao, Niccolò Dalmasso, Rafael Izbicki, Ann B. Lee

Variational refinement for importance sampling using the forward Kullback-Leibler divergence

Ghassen Jerfel, Serena Wang, Clara Wong-Fannjiang, Katherine A. Heller, Yian Ma

Bias-corrected peaks-over-threshold estimation of the CVaR

Dylan Troop, Fréderic Godin, Jia Yuan Yu

Partial Identifiability in Discrete Data with Measurement Error

Noam Finkelstein, Roy Adams, Suchi Saria, Ilya Shpitser

Contextual policy transfer in reinforcement learning domains via deep mixtures-of-experts

Michael Gimelfarb, Scott Sanner, Chi-Guhn Lee

Nearest neighbor search under uncertainty

Blake Mason, Ardhendu Tripathy, Robert Nowak

Know your limits: Uncertainty estimation with ReLU classifiers fails at reliable OOD detection

Dennis Ulmer, Giovanni Cinà

Constrained differentially private federated learning for low-bandwidth devices

Raouf Kerkouche, Gergely Ács, Claude Castelluccia, Pierre Genevès

Markov equivalence of max-linear Bayesian networks

Carlos Amendola, Benjamin Hollering, Seth Sullivant, Ngoc Tran

Statistically robust neural network classification

Benjie Wang, Stefan Webb, Tom Rainforth

Integer programming-based error-correcting output code design for robust classification

Samarth Gupta, Saurabh Amin

Certification of iterative predictions in Bayesian neural networks

Matthew Wicker, Luca Laurenti, Andrea Patane, Nicola Paoletti, Alessandro Abate

Federated stochastic gradient Langevin dynamics

Khaoula el Mekkaoui, Diego Mesquita, Paul Blomstedt, Samuel Kaski

Multi-task and meta-learning with sparse linear bandits

Leonardo Cella, Massimiliano Pontil

Random probabilistic circuits

Nicola Di Mauro, Gennaro Gala, Marco Iannotta, Teresa M.A. Basile

Modeling financial uncertainty with multivariate temporal entropy-based curriculums

Ramit Sawhney, Arnav Wadhwa, Ayush Mangal, Vivek Mittal, Shivam Agarwal

Investigating vulnerabilities of deep neural policies

Ezgi Korkmaz

An optimization and generalization analysis for max-pooling networks

Alon Brutzkus, Amir Globerson

Enabling long-range exploration in minimization of multimodal functions

Jiaxin Zhang, Hoang Tran, Dan Lu, Guannan Zhang

Hierarchical learning of Hidden Markov Models with clustering regularization

Hui Lan, Antoni B. Chan

Class balancing GAN with a classifier in the loop

Harsh Rangwani, Konda Reddy Mopuri, R. Venkatesh Babu

Combining pseudo-point and state space approximations for sum-separable Gaussian Processes

Will Tebbutt, Arno Solin, Richard E. Turner

Information theoretic meta learning with Gaussian processes

Michalis K. Titsias, Francisco J. R. Ruiz, Sotirios Nikoloutsopoulos, Alexandre Galashov

Strategically efficient exploration in competitive multi-agent reinforcement learning

Robert Loftin, Aadirupa Saha, Sam Devlin, Katja Hofmann

Graph-based semi-supervised learning through the lens of safety

Shreyas Sheshadri, Avirup Saha, Priyank Patel, Samik Datta, Niloy Ganguly

A Bayesian nonparametric conditional two-sample test with an application to Local Causal Discovery

Philip A. Boeken, Joris M. Mooij

Generating adversarial examples with graph neural networks

Florian Jaeckle, M. Pawan Kumar

Invariant representation learning for treatment effect estimation

Claudia Shi, Victor Veitch, David M. Blei

Contingency-aware influence maximization: A reinforcement learning approach

Haipeng Chen, Wei Qiu, Han-Ching Ou, Bo An, Milind Tambe

RISAN: Robust instance specific deep abstention network

Bhavya Kalra, Kulin Shah, Naresh Manwani

Generalization error bounds for deep unfolding RNNs

Boris Joukovsky, Tanmoy Mukherjee, Huynh Van Luong, Nikos Deligiannis

Multi-output Gaussian Processes for uncertainty-aware recommender systems

Yinchong Yang, Florian Buettner

Minimax sample complexity for turn-based stochastic game

Qiwen Cui, Lin F. Yang

Trusted-maximizers entropy search for efficient Bayesian optimization

Quoc Phong Nguyen, Zhaoxuan Wu, Bryan Kian Hsiang Low, Patrick Jaillet

Sum-product laws and efficient algorithms for imprecise Markov chains

Jasper De Bock, Alexander Erreygers, Thomas Krak

Learning to learn with Gaussian processes

Quoc Phong Nguyen, Bryan Kian Hsiang Low, Patrick Jaillet

CLAIM: curriculum learning policy for influence maximization in unknown social networks

Dexun Li, Meghna Lowalekar, Pradeep Varakantham

Simple combinatorial algorithms for combinatorial bandits: corruptions and approximations

Haike Xu, Jian Li

Causal and interventional Markov boundaries

Sofia Triantafillou, Fattaneh Jabbari, Gregory F. Cooper

Probabilistic DAG search

Julia Grosse, Cheng Zhang, Philipp Hennig

Towards tractable optimism in model-based reinforcement learning

Aldo Pacchiano, Philip Ball, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts

Post-hoc loss-calibration for Bayesian neural networks

Meet P. Vadera, Soumya Ghosh, Kenney Ng, Benjamin M. Marlin

Faster lifting for two-variable logic using cell graphs

Timothy van Bremen, Ondrej Kuzelka

Local explanations via necessity and sufficiency: unifying theory and practice

David S. Watson, Limor Gultchin, Ankur Taly, Luciano Floridi

PLSO: A generative framework for decomposing nonstationary time-series into piecewise stationary oscillatory components

Andrew H. Song, Demba Ba, Emery N. Brown

Subset-of-data variational inference for deep Gaussian-processes regression

Ayush Jain, P. K. Srijith, Mohammad Emtiyaz Khan

ReZero is all you need: fast convergence at large depth

Thomas Bachlechner, Bodhisattwa Prasad Majumder, Henry Mao, Gary Cottrell, Julian McAuley

Towards robust episodic meta-learning

Beyza Ermis, Giovanni Zappella, Cédric Archambeau

Zijing Liu, Mauricio Barahona

Tensor-train density estimation

Georgii S. Novikov, Maxim E. Panov, Ivan V. Oseledets

Dimension reduction for data with heterogeneous missingness

Yurong Ling, Zijing Liu, Jing-Hao Xue

Inference of causal effects when control variables are unknown

Ludvig Hult, Dave Zachariah

Optimized auxiliary particle filters: adapting mixture proposals via convex optimization

Nicola Branchini, Victor Elvira

Stochastic model for sunk cost bias

Jon Kleinberg, Sigal Oren, Manish Raghavan, Nadav Sklar

Trumpets: Injective flows for inference and inverse problems

Konik Kothari, AmirEhsan Khorashadizadeh, Maarten de Hoop, Ivan Dokmanić

Gaussian process nowcasting: application to COVID-19 mortality reporting

Iwona Hawryluk, Henrique Hoeltgebaum, Swapnil Mishra, Xenia Miscouridou, Ricardo P Schnekenberg

Extendability of causal graphical models: Algorithms and computational complexity

Marcel Wienöbst, Max Bannach, Maciej Liśkiewicz

Maximal ancestral graph structure learning via exact search

Kari Rantanen, Antti Hyttinen, Matti Järvisalo

Classification with abstention but without disparities

Nicolas Schreuder, Evgenii Chzhen

Confidence in causal discovery with linear causal models

David Strieder, Tobias Freidling, Stefan Haffner, Mathias Drton

The promises and pitfalls of deep kernel learning

Sebastian W. Ober, Carl E. Rasmussen, Mark van der Wilk

Testification of Condorcet Winners in dueling bandits

Björn Haddenhorst, Viktor Bengs, Jasmin Brandt, Eyke Hüllermeier

Uncertainty-aware sensitivity analysis using Rényi divergences

Topi Paananen, Michael Riis Andersen, Aki Vehtari

Sparse linear networks with a fixed butterfly structure: theory and practice

Nir Ailon, Omer Leibovitch, Vineet Nair

Tractable computation of expected kernels

Wenzhe Li, Zhe Zeng, Antonio Vergari, Guy Van den Broeck

Faster Convergence of Stochastic Gradient Langevin Dynamics for Non-Log-Concave Sampling

Difan Zou, Pan Xu, Quanquan Gu

On the distribution of penultimate activations of classification networks

Minkyo Seo, Yoonho Lee, Suha Kwak

Stochastic continuous normalizing flows: training SDEs as ODEs

Liam Hodgkinson, Chris van der Heide, Fred Roosta, Michael W. Mahoney