[AISTATS Logo]
AI & Statistics 2016

AISTATS 2016 Schedule

Accepted papers

All accepted papers are available here.

Information for presenters

Each presenter has 20 minutes: 16-minute presentation and 4-minute Q&A session.

Registration desk hours

  • Sunday May 8: 17:00 to 20:00
  • Monday May 9: 7:30 to 13:30
  • Tuesday May 10: 7:30 to 13:30
  • Wednesday May 11: 7:30 to 10:30

May 9 (Monday)

Time Schedule
9:00 - 10:00 Invited speaker: Richard Samworth
10:10 - 11:30 Oral Session 1.1: Gaussian processes
Session chair: Aki Vehtari
  • GLASSES: Relieving The Myopia Of Bayesian Optimisation
    Javier Gonzalez, Michael Osborne, Neil Lawrence
  • Optimization as Estimation with Gaussian Processes in Bandit Settings
    Zi Wang, Bolei Zhou, Stefanie Jegelka,
  • Scalable Gaussian Process Classification via Expectation Propagation
    Daniel Hernandez-Lobato, Jose Miguel Hernandez-Lobato
  • Control Functionals for Quasi-Monte Carlo Integration
    Chris Oates, Mark Girolami
11:30 - 14:00 Poster session 1
14:00 - 15:30 Lunch (on your own)
15:30 - 16:50 Oral Session 1.2: Deep learning and reinforcement learning
Session chair: Byron Boots
  • Dreaming More Data: Class-dependent Distributions over Diffeomorphisms for Learned Data Augmentation
    Søren Hauberg, Oren Freifeld, Anders Boesen Lindbo Larsen
  • Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimization
    Changyou Chen, David Carlson, Zhe Gan, Chunyuan Li, Lawrence Carin
  • Stochastic Neural Networks with Monotonic Activation Functions
    Siamak Ravanbakhsh, Barnabas Poczos, Jeff Schneider, Dale Schuurmans, Russell Greiner
  • Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics
    Michael Herman, Tobias Gindele, Jörg Wagner, Felix Schmitt, Wolfram Burgard
16:50 - 17:20 Coffee break
17:20 - 18:40 Oral Session 1.3: Monte Carlo methods for Bayesian inference
Session chair: Lawrence Murray
  • K2-ABC: Approximate Bayesian Computation with Kernel Embeddings
    Mijung Park, Wittawat Jitkrittum, Dino Sejdinovic
  • C3: Lightweight Incrementalized MCMC for Probabilistic Programs using Continuations and Callsite Caching
    Daniel Ritchie, Andreas Stuhlmüller, Noah Goodman
  • Parallel Markov Chain Monte Carlo via Spectral Clustering
    Guillaume Basse, Aaron Smith, Natesh Pillai
  • Provable Bayesian Inference via Particle Mirror Descent
    Bo Dai, Niao He, Hanjun Dai, Le Song
18:40 Welcome speech from the organizers
19:30 Welcome cocktail

May 10 (Tuesday)

Time Schedule
9:00 - 10:00 Invited speaker: Kamalika Chaudhuri
10:10 - 11:30 Oral Session 2.1: Graphical models
Session chair: Dino Sejdinovic
  • Survey Propagation beyond Constraint Satisfaction Problems
    Christopher Srinivasa, Siamak Ravanbakhsh, Brendan Frey
  • Tightness of LP Relaxations for Almost Balanced Models
    Adrian Weller, David Sontag
  • Active Learning Algorithms for Graphical Model Selection
    Gautamd Dasarathy, Aarti Singh, Maria-Florina Balcan, Jong Park
  • Tight Variational Bounds via Random Projections and I-Projections
    Lun-Kai Hsu, Tudor Achim, Stefano Ermon
11:30 - 14:00 Poster session 2
14:00 - 15:30 Lunch (on your own)
15:30 - 16:50 Oral Session 2.2: Theory of learning
Session chair: Ambuj Tewari
  • Probability Inequalities for Kernel Embeddings in Sampling without Replacement
    Markus Schneider
  • Nearly optimal classification for semimetrics
    Lee-Ad Gottlieb, Aryeh Kontorovich, Pinhas Nisnevitch
  • Online learning with noisy side observations
    Tomáš Kocák, Gergely Neu, Michal Valko
  • Differentially Private Causal Inference
    Matt Kusner, Yu Sun, Karthik Sridharan, Kilian Weinberger
16:50 - 17:20 Coffee break
17:20 - 18:40 Oral Session 2.3: Matrix and tensor methods
Session chair: Yiming Ying
  • Multiresolution Matrix Compression
    Nedelina Teneva, Pramod Kaushik Mudrakarta, Risi Kondor
  • Low-Rank and Sparse Structure Pursuit via Alternating Minimization
    Quanquan Gu, Zhaoran Wang, Han Liu
  • Tensor vs Matrix Methods: Robust Tensor Decomposition under Block Sparse Perturbations
    Anima Anandkumar, Prateek Jain, Yang Shi, Niranjan Uma Naresh
  • Tractable and Scalable Schatten Quasi-Norm Approximations for Rank Minimization
    Fanhua Shang, Yuanyuan Liu, James Cheng
19:30 Dinner at Bodegas Gonzalez-Byass. Buses leave at 19:30

May 11 (Wednesday)

Time Schedule
9:00 - 10:00 Invited speaker: Adam Tauman Kalai
10:10 - 11:30 Oral Session 3.1: Large-scale learning
Session chair: Anima Anandkumar
  • Large-Scale Semi-Supervised Learning Using Streaming Approximation
    Sujith Ravi, Qiming Diao
  • A Convex Surrogate Operator for General Non-Modular Loss Functions
    Jiaqian Yu, Matthew Blaschko
  • Ordered Weighted l1 Regularized Regression with Strongly Correlated Covariates: Theoretical Aspects
    Mario Figueiredo, Robert Nowak
  • Scalable geometric density estimation
    Ye Wang, Antonio Canale, David Dunson
11:30 - 14:00 Poster session 3 and MLSS posters.
14:00 - 15:30 Lunch (on your own)
15:30 - 16:50 Oral Session 3.2: Sensing and Information
Session chair: Mladen Kolar
  • DUAL-LOCO: Distributing Statistical Estimation Using Random Projections
    Christina Heinze, Brian McWilliams, Nicolai Meinshausen
  • Controlling Bias in Adaptive Data Analysis Using Information Theory
    Daniel Russo, James Zou
  • Unsupervised Ensemble Learning with Dependent Classifiers
    Ethan Fetaya, Boaz Nadler, Ariel Jaffe, Ting Ting Jiang, Yuval Kluger
  • Learning Sparse Additive Models with Interactions in High Dimensions
    Hemant Tyagi, Anastasios Kyrillidis, Bernd Gärtner, Andreas Krause
16:50 - 17:20 Coffee break
17:20 - 18:40 Oral Session 3.3: Variational methods and point processes
Session chair: Iain Murray
  • Early Stopping as Nonparametric Variational Inference
    David Duvenaud, Dougal Maclaurin, Ryan Adams
  • Efficient Sampling for k-Determinantal Point Processes
    Chengtao Li, Stefanie Jegelka, Suvrit Sra
  • Universal Models of Multivariate Temporal Point Processes
    Asela Gunawardana, Chris Meek