Blog

Machine Learning Department at CMU | ICML 2019

CMU accepted papers to the International Conference on Machine Learning (ICML) 2019

Roberto Iriondo

May 8

We will present the following papers at the 36th International Conference on Machine Learning (ICML) in Long Beach, California. This achievement is a demonstration of the cutting-edge machine learning research being done at Carnegie Mellon University.

If you are attending ICML 2019, please stop by to say hello and hear more about what we are doing!

Full List of Accepted Papers

Statistical Foundations of Virtual Democracy

Anson Kahng (Carnegie Mellon University) · Min Kyung Lee (CMU) · Ritesh Noothigattu (Carnegie Mellon University) · Ariel Procaccia (Carnegie Mellon University) · Christos-Alexandros Psomas (Carnegie Mellon University)

TarMAC: Targeted Multi-Agent Communication

Abhishek Das (Georgia Tech) · Theophile Gervet (Carnegie Mellon University) · Joshua Romoff (McGill University) · Dhruv Batra (Georgia Institute of Technology / Facebook AI Research) · Devi Parikh (Georgia Tech & Facebook AI Research) · Michael Rabbat (Facebook) · Joelle Pineau (Facebook)

A Kernel Theory of Modern Data Augmentation

Tri Dao (Stanford University) · Albert Gu (Stanford University) · Alexander J Ratner (Stanford University) · Virginia Smith (Carnegie Mellon University) · Chris De Sa (Cornell) · Christopher Re (Stanford)

Myopic Posterior Sampling for Adaptive Goal Oriented Design of Experiments

Kirthevasan Kandasamy (Carnegie Mellon University) · Willie Neiswanger (CMU) · Reed Zhang (Carnegie Mellon University) · Akshay Krishnamurthy (Microsoft Research) · Jeff Schneider (Uber/CMU) · Barnabás Póczos (CMU)

Nearest neighbor and kernel survival analysis: Nonasymptotic error bounds and strong consistency rates

George Chen (Carnegie Mellon University)

Policy Certificates: Towards Accountable Reinforcement Learning

Christoph Dann (Carnegie Mellon University) · Lihong Li (Google Inc.) · Wei Wei (Google) · Emma Brunskill (Stanford University)

Deep Counterfactual Regret Minimization

Noam Brown (Facebook AI Research) · Adam Lerer (Facebook AI Research) · Sam Gross (Facebook AI Research) · Tuomas Sandholm (Carnegie Mellon University)

Domain Adaptation with Asymmetrically-Relaxed Distribution Alignment

Yifan Wu (Carnegie Mellon University) · Ezra Winston (CMU MLD) · Divyansh Kaushik (Carnegie Mellon University) · Zachary Lipton (Carnegie Mellon University)

Provably efficient RL with Rich Observations via Latent State Decoding

Simon Du (Carnegie Mellon University) · Akshay Krishnamurthy (Microsoft Research) · Nan Jiang (University of Illinois at Urbana-Champaign) · Alekh Agarwal (Microsoft Research) · Miroslav Dudik (Microsoft Research) · John Langford (Microsoft Research)

A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs

Jingkai Mao (Man AHL) · Jakob Foerster (Facebook AI Research) · Tim Rocktäschel (University of Oxford) · Maruan Al-Shedivat (Carnegie Mellon University) · Gregory Farquhar (University of Oxford) · Shimon Whiteson (University of Oxford)

Gradient Descent Finds Global Minima of Deep Neural Networks

Simon Du (Carnegie Mellon University) · Jason Lee (University of Southern California) · Haochuan Li (Peking University) · Liwei Wang (Peking University) · Xiyu Zhai (Massachusetts Institute of Technology)

Stable-Predictive Optimistic Counterfactual Regret Minimization

Gabriele Farina (Carnegie Mellon University) · Christian Kroer (Columbia University) · Noam Brown (CMU) · Tuomas Sandholm (Carnegie Mellon University)

Regret Circuits: Composability of Regret Minimizers

Gabriele Farina (Carnegie Mellon University) · Christian Kroer (Columbia University) · Tuomas Sandholm (Carnegie Mellon University)

Provable Guarantees for Gradient-Based Meta-Learning

Nina Balcan (Carnegie Mellon University) · Mikhail Khodak (CMU) · Ameet Talwalkar (Carnegie Mellon University)

Dimensionality Reduction for Tukey Regression

Kenneth Clarkson (IBM Research) · Ruosong Wang (Carnegie Mellon University) · David Woodruff (Carnegie Mellon University)

Certified Adversarial Robustness via Randomized Smoothing

Jeremy Cohen (Carnegie Mellon University) · Elan Rosenfeld (Carnegie Mellon University) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

Provably Efficient Imitation Learning from Observation Alone

Wen Sun (Carnegie Mellon University) · Anirudh Vemula (CMU) · Byron Boots (Georgia Tech) · Drew Bagnell (Carnegie Mellon University)

SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver

Po-Wei Wang (CMU) · Priya Donti (Carnegie Mellon University) · Bryan Wilder (University of Southern California) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

Collective Model Fusion for Multiple Black-Box Experts

Minh Hoang (Carnegie Mellon University) · Nghia Hoang (MIT-IBM Watson AI Lab, IBM Research) · Bryan Kian Hsiang Low (National University of Singapore) · Carleton Kingsford (Carnegie Mellon University

Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

Sanjeev Arora ( Princeton University and Institute for Advanced Study) · Simon Du (Carnegie Mellon University) · Wei Hu (Princeton University) · Zhiyuan Li (Princeton University) · Ruosong Wang (Carnegie Mellon University)

Width Provably Matters in Optimization for Deep Linear Neural Networks

Simon Du (Carnegie Mellon University) · Wei Hu (Princeton University)

Causal Discovery and Forecasting in Nonstationary Environments with State-Space Models

Biwei Huang (Carnegie Mellon University) · Kun Zhang (Carnegie Mellon University) · Mingming Gong (University of Pittsburgh & CMU) · Clark Glymour (Carnegie Mellon University)

Uniform Convergence Rate of the Kernel Density Estimator Adaptive to Intrinsic Volume Dimension

Jisu Kim (Inria Saclay) · Jaehyeok Shin (Carnegie Mellon University) · Alessandro Rinaldo (Carnegie Mellon University) · Larry Wasserman (Carnegie Mellon University)

Faster Algorithms for Boolean Matrix Factorization

Ravi Kumar (Google) · Rina Panigrahy (Google) · Ali Rahimi (Google) · David Woodruff (Carnegie Mellon University)

Contextual Memory Trees

Wen Sun (Carnegie Mellon University) · Alina Beygelzimer (Yahoo Research) · Hal Daume (Microsoft Research) · John Langford (Microsoft Research) · Paul Mineiro (Microsoft)

Fault Tolerance in Iterative-Convergent Machine Learning

Aurick Qiao (Petuum, Inc. and Carnegie Mellon University) · Bryon Aragam (Carnegie Mellon University) · Bingjing Zhang (Petuum, Inc.) · Eric Xing (Petuum Inc.)

Wasserstein Adversarial Examples via Projected Sinkhorn Iterations

Eric Wong (Carnegie Mellon University) · Frank Schmidt (Robert Bosch GmbH) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

Learning to Explore via Disagreement

Deepak Pathak (UC Berkeley) · Dhiraj Gandhi (Carnegie Mellon University Robotics Institute) · Abhinav Gupta (Carnegie Mellon University)

What is the Effect of Importance Weighting in Deep Learning?

Jonathon Byrd (Carnegie Mellon University) · Zachary Lipton (Carnegie Mellon University)

Adversarial camera stickers: A physical camera-based attack on deep learning systems

Juncheng Li (Carnegie Mellon University) · Frank Schmidt (Robert Bosch GmbH) · Zico Kolter (Carnegie Mellon University / Bosch Center for AI)

On Learning Invariant Representation for Domain Adaptation

Han Zhao (Carnegie Mellon University) · Remi Tachet des Combes (Microsoft Research Montreal) · Kun Zhang (Carnegie Mellon University) · Geoff Gordon (Carnegie Mellon University)

Finding Options that Minimize Planning Time

Yuu Jinnai (Brown University) · David Abel (Brown University) · David Hershkowitz (Carnegie Mellon University) · Michael L. Littman (Brown University) · George Konidaris (Brown)

Tight Kernel Query Complexity of Kernel Ridge Regression and Kernel kk-means Clustering

Taisuke Yasuda (Carnegie Mellon University) · David Woodruff (Carnegie Mellon University) · Manuel Fernandez (Carnegie Mellon University)

Full list of accepted papers at ICML 2019