UAI 2021

206 papers

Variance-dependent best arm identification

Pinyan Lu, Chao Tao, Xiaojin Zhang

Principal component analysis in the stochastic differential privacy model

Fanhua Shang, Zhihui Zhang, Tao Xu, Yuanyuan Liu, Hongying Liu

PALM: Probabilistic area loss Minimization for Protein Sequence Alignment

Fan Ding, Nan Jiang, Jianzhu Ma, Jian Peng, Jinbo Xu

NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation

xiaohui zeng, Raquel Urtasun, Richard Zemel, Sanja Fidler, Renjie Liao

Unsupervised constrained community detection via self-expressive graph neural network

Sambaran Bandyopadhyay, Vishal Peter

Hierarchical infinite relational model

Feras A. Saad, Vikash K. Mansinghka

Learning proposals for probabilistic programs with inference combinators

Sam Stites, Heiko Zimmermann, Hao Wu, Eli Sennesh, Jan-Willem van de Meent

Entropic Inequality Constraints from e-separation Relations in Directed Acyclic Graphs with Hidden Variables

Noam Finkelstein, Beata Zjawin, Elie Wolfe, Ilya Shpitser, Robert W. Spekkens

Probabilistic selection of inducing points in sparse Gaussian processes

Anders Kirk Uhrenholt, Valentin Charvet, Bjørn Sand Jensen

Bayesian optimization for modular black-box systems with switching costs

Chi-Heng Lin, Joseph D. Miano, Eva L. Dyer

Compositional abstraction error and a category of causal models

Eigil F. Rischel, Sebastian Weichwald

A decentralized policy gradient approach to multi-task reinforcement learning

Sihan Zeng, Malik Aqeel Anwar, Thinh T. Doan, Arijit Raychowdhury, Justin Romberg

No-regret learning with high-probability in adversarial Markov decision processes

Mahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo, Ufuk Topcu

Estimating treatment effects with observed confounders and mediators

Shantanu Gupta, Zachary C. Lipton, David Childers

variational combinatorial sequential monte carlo methods for bayesian phylogenetic inference

Antonio Khalil Moretti, Liyi Zhang, Christian A. Naesseth, Hadiah Venner, David Blei

Subseasonal climate prediction in the western US using Bayesian spatial models

Vishwak Srinivasan, Justin Khim, Arindam Banerjee, Pradeep Ravikumar

Mixed variable Bayesian optimization with frequency modulated kernels

Changyong Oh, Efstratios Gavves, Max Welling

GP-ConvCNP: Better generalization for conditional convolutional Neural Processes on time series data

Jens Petersen, Gregor Köhler, David Zimmerer, Fabian Isensee, Paul F. Jäger

On the effects of quantisation on model uncertainty in Bayesian neural networks

Martin Ferianc, Partha Maji, Matthew Mattina, Miguel Rodrigues

Deep kernels with probabilistic embeddings for small-data learning

Ankur Mallick, Chaitanya Dwivedi, Bhavya Kailkhura, Gauri Joshi, T. Yong-Jin Han

Neural markov logic networks

Giuseppe Marra, Ondrej Kuzelka

On random kernels of residual architectures

Etai Littwin, Tomer Galanti, Lior Wolf

BayLIME: Bayesian local interpretable model-agnostic explanations

Xingyu Zhao, Wei Huang, Xiaowei Huang, Valentin Robu, David Flynn

Time-variant variational transfer for value functions

Giuseppe Canonaco, Andrea Soprani, Matteo Giuliani, Andrea Castelletti, Manuel Roveri

Combinatorial semi-bandit in the non-stationary environment

Wei Chen, Liwei Wang, Haoyu Zhao, Kai Zheng

Identifying untrustworthy predictions in neural networks by geometric gradient analysis

Leo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck

Distribution-free uncertainty quantification for classification under label shift

Aleksandr Podkopaev, Aaditya Ramdas

Path-BN: Towards effective batch normalization in the Path Space for ReLU networks

Xufang Luo, Qi Meng, Wei Chen, Yunhong Wang, Tie-yan Liu

Natural language adversarial defense through synonym encoding

Xiaosen Wang, Jin Hao, Yichen Yang, Kun He

Dependency in DAG models with hidden variables

Robin J. Evans

Tighter Generalization Bounds for Iterative Differentially Private Learning Algorithms

Fengxiang He, Bohan Wang, Dacheng Tao

Approximation algorithm for submodular maximization under submodular cover

Naoto Ohsaka, Tatsuya Matsuoka

Probabilistic task modelling for meta-learning

Cuong C. Nguyen, Thanh-Toan Do, Gustavo Carneiro

Improved generalization bounds of group invariant / equivariant deep networks via quotient feature spaces

Akiyoshi Sannai, Masaaki Imaizumi, Makoto Kawano

Measuring data leakage in machine-learning models with Fisher information

Awni Hannun, Chuan Guo, Laurens van der Maaten

Hierarchical Indian buffet neural networks for Bayesian continual learning

Samuel Kessler, Vu Nguyen, Stefan Zohren, Stephen J. Roberts

Thompson sampling for Markov games with piecewise stationary opponent policies

Anthony DiGiovanni, Ambuj Tewari

When is particle filtering efficient for planning in partially observed linear dynamical systems?

Simon S. Du, Wei Hu, Zhiyuan Li, Ruoqi Shen, Zhao Song

Possibilistic preference elicitation by minimax regret

Loïc Adam, Sébastien Destercke

Unbiased gradient estimation for variational auto-encoders using coupled Markov chains

Francisco J. R. Ruiz, Michalis K. Titsias, Taylan Cemgil, Arnaud Doucet

Decentralized multi-agent active search for sparse signals

Ramina Ghods, Arundhati Banerjee, Jeff Schneider

Robust principal component analysis for generalized multi-view models

Frank Nussbaum, Joachim Giesen

Scaling Hamiltonian Monte Carlo inference for Bayesian neural networks with symmetric splitting

Adam D. Cobb, Brian Jalaian

Finite-time theory for momentum Q-learning

Weng Bowen, Xiong Huaqing, Zhao Lin, Liang Yingbin, Zhang Wei

Exploring the loss landscape in neural architecture search

Colin White, Sam Nolen, Yash Savani

Generative Archimedean copulas

Yuting Ng, Ali Hasan, Khalil Elkhalil, Vahid Tarokh

LocalNewton: Reducing communication rounds for distributed learning

Vipul Gupta, Avishek Ghosh, Michał Dereziński, Rajiv Khanna, Kannan Ramchandran

A heuristic for statistical seriation

Komal Dhull, Jingyan Wang, Nihar B. Shah, Yuanzhi Li, R. Ravi

A unifying framework for observer-aware planning and its complexity

Shuwa Miura, Shlomo Zilberstein

Addressing fairness in classification with a model-agnostic multi-objective algorithm

Kirtan Padh, Diego Antognini, Emma Lejal-Glaude, Boi Faltings, Claudiu Musat

Global explanations with decision rules: a co-learning approach

Geraldin Nanfack, Paul Temple, Benoît Frénay

Asynchronous $ε$-Greedy Bayesian Optimisation

George De Ath, Richard M. Everson, Jonathan E. Fieldsend

A Nonmyopic Approach to Cost-Constrained Bayesian Optimization

Eric Hans Lee, David Eriksson, Valerio Perrone, Matthias Seeger

Bayesian streaming sparse Tucker decomposition

Shikai Fang, Robert M. Kirby, Shandian Zhe

Efficient greedy coordinate descent via variable partitioning

Huang Fang, Guanhua Fang, Tan Yu, Ping Li

Generalized parametric path problems

Kshitij Gajjar, Girish Varma, Prerona Chatterjee, Jaikumar Radhakrishnan

FlexAE: flexibly learning latent priors for wasserstein auto-encoders

Arnab Kumar Mondal, Himanshu Asnani, Parag Singla, AP Prathosh

Dynamic visualization for L1 fusion convex clustering in near-linear time

Bingyuan Zhang, Jie Chen, Yoshikazu Terada

Known unknowns: Learning novel concepts using reasoning-by-elimination

Harsh Agrawal, Eli A. Meirom, Yuval Atzmon, Shie Mannor, Gal Chechik

High-dimensional Bayesian optimization with sparse axis-aligned subspaces

David Eriksson, Martin Jankowiak

The complexity of nonconvex-strongly-concave minimax optimization

Siqi Zhang, Junchi Yang, Cristóbal Guzmán, Negar Kiyavash, Niao He

Regstar: efficient strategy synthesis for adversarial patrolling games

David Klaška, Antonín Kučera, Vít Musil, Vojtěch Řehák

pRSL: Interpretable multi-label stacking by learning probabilistic rules

Michael Kirchhof, Lena Schmid, Christopher Reining, Michael ten Hompel, Markus Pauly

A weaker faithfulness assumption based on triple interactions

Alexander Marx, Arthur Gretton, Joris M. Mooij

Structured sparsification with joint optimization of group convolution and channel shuffle

Xin-Yu Zhang, KAI ZHAO, Taihong Xiao, Ming-Ming Cheng, Ming-Hsuan Yang

Bandits with partially observable confounded data

Guy Tennenholtz, Uri Shalit, Shie Mannor, Yonathan Efroni

On the distributional properties of adaptive gradients

Zhiyi Zhang, Ziyin Liu

Unsupervised program synthesis for images by sampling without replacement

Chenghui Zhou, Chun-Liang Li, Barnabás Póczos

Escaping from zero gradient: Revisiting action-constrained reinforcement learning via Frank-Wolfe policy optimization

Jyun-Li Lin, Wei Hung, Shang-Hsuan Yang, Ping-Chun Hsieh, Xi Liu

Weighted model counting with conditional weights for Bayesian networks

Paulius Dilkas, Vaishak Belle

Action redundancy in reinforcement learning

Nir Baram, Guy Tennenholtz, Shie Mannor

Unsupervised anomaly detection with adversarial mirrored autoencoders

Gowthami Somepalli, Yexin Wu, Yogesh Balaji, Bhanukiran Vinzamuri, Soheil Feizi

Symmetric Wasserstein autoencoders

Sun Sun, Hongyu Guo

Learnable uncertainty under Laplace approximations

Agustinus Kristiadi, Matthias Hein, Philipp Hennig

Formal verification of neural networks for safety-critical tasks in deep reinforcement learning

Davide Corsi, Enrico Marchesini, Alessandro Farinelli

Lifted reasoning meets weighted model integration

Jonathan Feldstein, Vaishak Belle

Hierarchical probabilistic model for blind source separation via Legendre transformation

Simon Luo, Lamiae Azizi, Mahito Sugiyama

Approximate implication with d-separation

Batya Kenig

Improving approximate optimal transport distances using quantization

Gaspard Beugnot, Aude Genevay, Kristjan Greenewald, Justin Solomon

Matrix games with bandit feedback

Brendan O’Donoghue, Tor Lattimore, Ian Osband

Defending SVMs against poisoning attacks: the hardness and DBSCAN approach

Hu Ding, Fan Yang, Jiawei Huang

Robust reinforcement learning under minimax regret for green security

Lily Xu, Andrew Perrault, Fei Fang, Haipeng Chen, Milind Tambe

Communication efficient parallel reinforcement learning

Mridul Agarwal, Bhargav Ganguly, Vaneet Aggarwal

Constrained labeling for weakly supervised learning

Chidubem Arachie, Bert Huang

Most: multi-source domain adaptation via optimal transport for student-teacher learning

Tuan Nguyen, Trung Le, He Zhao, Quan Hung Tran, Truyen Nguyen

An unsupervised video game playstyle metric via state discretization

Chiu-Chou Lin, Wei-Chen Chiu, I-Chen Wu

A kernel two-sample test with selection bias

Alexis Bellot, Mihaela van der Schaar

Application of kernel hypothesis testing on set-valued data

Alexis Bellot, Mihaela van der Schaar

Variance reduction in frequency estimators via control variates method

Rameshwar Pratap, Raghav Kulkarni

Featurized density ratio estimation

Kristy Choi, Madeline Liao, Stefano Ermon

Path dependent structural equation models

Ranjani Srinivasan, Jaron J. R. Lee, Rohit Bhattacharya, Ilya Shpitser

XOR-SGD: provable convex stochastic optimization for decision-making under uncertainty

Fan Ding, Yexiang Xue

Contrastive prototype learning with augmented embeddings for few-shot learning

Yizhao Gao, Nanyi Fei, Guangzhen Liu, Zhiwu Lu, Tao Xiang

The curious case of adversarially robust models: More data can help, double descend, or hurt generalization

Yifei Min, Lin Chen, Amin Karbasi

Graph reparameterizations for enabling 1000+ Monte Carlo iterations in Bayesian deep neural networks

Jurijs Nazarovs, Ronak R. Mehta, Vishnu Suresh Lokhande, Vikas Singh

A variational approximation for analyzing the dynamics of panel data

Jurijs Nazarovs, Rudrasis Chakraborty, Songwong Tasneeyapant, Sathya Ravi, Vikas Singh

Causal additive models with unobserved variables

Takashi Nicholas Maeda, Shohei Shimizu

Incorporating causal graphical prior knowledge into predictive modeling via simple data augmentation

Takeshi Teshima, Masashi Sugiyama

Improving uncertainty calibration of deep neural networks via truth discovery and geometric optimization

Chunwei Ma, Ziyun Huang, Jiayi Xian, Mingchen Gao, Jinhui Xu

Competitive policy optimization

Manish Prajapat, Kamyar Azizzadenesheli, Alexander Liniger, Yisong Yue, Anima Anandkumar