AI

IBM Research AI Moves Machine Learning Forward at ICML 2019

Share this post:

At the 36th International Conference on Machine Learning (ICML 2019), June 10–15 in Long Beach, CA, IBM Research AI will present recent technical advances in machine learning for AI and data science. We’ve led the exploration and development of machine learning technologies for decades, and now we’re progressing the AI field through our portfolio of research focused on advancing AI, trusting AI, and scaling AI.

We are proud to be a Gold sponsor of ICML 2019 and will be exhibiting at the conference at booth #117. Visit our booth to experience our tech first-hand with demos of our tools and resources, and learn about our latest research in the talks and posters listed below. We look forward to seeing you in Long Beach!

Accepted papers at ICML 2019

Topological Data Analysis of Decision Boundaries with Application to Model Selection
Karthikeyan Natesan Ramamurthy, Kush Varshney
Tue Jun 11th 11:35 — 11:40 AM @ Seaside Ballroom

Molecular Hypergraph Grammar with Its Application to Molecular Optimization
Hiroshi Kajino
Tue Jun 11th 11:40 AM — 12:00 PM @ Room 201

PROVEN: Verifying Robustness of Neural Networks with a Probabilistic Approach
Lily Weng, Pin-yu Chen, Lam Nguyen, Mark Squillante, Akhilan Boopathy, Ivan Oseledets, Luca Daniel
Tue Jun 11th 12:15 — 12:20 PM @ Grand Ballroom

Characterization of Convex Objective Functions and Optimal Expected Convergence Rates for SGD
Marten van Dijk, Lam Nguyen, Phuong-Ha Nguyen, Dzung Phan
Tue Jun 11th 02:30 — 02:35 PM @ Room 103

Dirichlet Simplex Nest and Geometric Inference
Mikhail Yurochkin, Yuekai Sun, Aritra Guha, XuanLong Nguyen
Tue Jun 11th 04:00 — 04:20 PM @ Room 101

Scalable Fair Clustering
Arturs Backurs, Piotr Indyk, Krzysztof Onak, Baruch Schieber, Ali Vakilian, Tal Wagner
Tue Jun 11th 04:30 — 04:35 PM @ Grand Ballroom

Generalized Linear Rule Models
Sanjeeb Dash, Tian Gao, Oktay Gunluk, Dennis Wei
Tue Jun 11th 04:35 — 04:40 PM @ Room 201

Fast Incremental von Neumann Graph Entropy Computation: Theory, Algorithm, and Applications
Pin-Yu Chen, Lingfei Wu, Sijia Liu, Indika Rajapakse
Tue Jun 11th 04:40 — 05:00 PM @ Room 201

Beyond Backprop: Online Alternating Minimization with Auxiliary Variables
Anna Choromanska, Benjamin Cowen, Sadhana Kumaravel, Ronny Luss, Mattia Rigotti, Irina Rish, Brian Kingsbury, Paolo Di Achille, Viatcheslav Gurev, Ravi Tejwani, Djallel Bouneffouf
Tue Jun 11th 05:00 — 05:05 PM @ Hall B
(Read blog post)

Collective Model Fusion for Multiple Black-Box Experts
Minh Hoang, Nghia Hoang, Bryan Kian Hsiang Low, Carleton Kingsford
Wed Jun 12th 11:30 — 11:35 AM @ Room 103

Estimating Information Flow in Deep Neural Networks
Ziv Goldfeld, Ewout Van Den Berg, Kristjan Greenewald, Igor Melnyk, Nam Nguyen, Brian Kingsbury, Yury Polyanksiy
Wed Jun 12th 11:40 AM — 12:00 PM @ Room 104
(Read blog post)

Trimming the l1 Regularizer: Statistical Analysis, Optimization, and Applications to Deep Learning
Jihun Yun, Peng Zheng, Eunho Yang, Aurelie Lozano, Aleksandr Aravkin
Wed Jun 12th 11:40 AM — 12:00 PM @ Room 103

Dynamic Learning with Frequent New Product Launches: A Sequential Multinomial Logit Bandit Problem
Junyu Cao, Wei Sun
Wed Jun 12th 12:15 — 12:20 PM @ Seaside Ballroom

Variational Russian Roulette for Deep Bayesian Nonparametrics
Kai Xu, Akash Srivastava, Charles Sutton
Wed Jun 12th 02:30 — 02:35 PM @ Room 101

Bayesian Nonparametric Federated Learning of Neural Networks
Mikhail Yurochkin, Mayank Agarwal, Soumya Ghosh, Kristjan Greenewald, Nghia Hoang, Yasaman Khazaeni
Wed Jun 12th 03:15 — 03:20 PM @ Hall A

Analyzing Federated Learning through an Adversarial Lens
Arjun Nitin Bhagoji, Supriyo Chakraborty, Prateek Mittal, Seraphin Calo
Wed Jun 12th 04:30 — 04:35 PM @ Seaside Ballroom

Kernel-Based Reinforcement Learning in Robust Markov Decision Processes
Shiau Hong Lim, Arnaud Autef
Wed Jun 12th 05:15 — 05:20 PM @ Room 104

Linear-Complexity Data-Parallel Earth Mover’s Distance Approximations
Kubilay Atasu, Thomas Mittelholzer
Thu Jun 13th 09:20 — 09:25 AM @ Room 201

AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
Yang Zhang, Shiyu Chang
Thu Jun 13th 10:10 — 10:15 AM @ Room 201

Dimensionality Reduction for Tukey Regression
Ken Clarkson, David P. Woodruff, Ruosong Wong
Thu Jun 13th 11:20 — 11:25 AM @ Room 101

DAG-GNN: DAG Structure Learning with Graph Neural Network
Jie Chen, Tian Gao, Mo Yu
Thu Jun 13th 12:10 — 12:15 PM @ Room 101

Accepted workshop papers at ICML 2019

Network-based Biased Tree Ensembles (NetBiTE) for Drug Sensitivity Prediction and Drug Sensitivity Biomarker Identification in Cancer
Ali Kazemi Oskooei, Matteo Manica, Roland Mathis, Maria Rodriguez Martinez
Workshop on Computational Biology
Fri Jun 14th 08:30 AM — 06:00 PM Room 101

Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity
Peng Liao, Kristjan Greenewald, Predrag Klasnja
Reinforcement Learning for Real Life Workshop
Fri Jun 14th 08:30 AM — 12:30 PM Room Seaside Ballroom

Towards Explainable Anticancer Compound Sensitivity Prediction via Multimodal Attention-based Convolutional Encoders
Matteo Manica, Ali Kazemi Oskooei, Jannis Born, Vigneshwari Subramanian, Julio Sáez-Rodríguez, Maria Rodriguez Martinez
Workshop on Computational Biology
Fri Jun 14th 08:30 AM — 06:00 PM Room 101

IPC: A Benchmark Data Set for Learning with Graph-Structured Data
Tengfei Ma, Siyu Huo, Jie Chen, Michael Katz
Learning and Reasoning with Graph-Structured Representations Workshop
Sat Jun 15th 08:30 AM — 06:00 PM @ Grand Ballroom B

Open Platforms for Artificial Intelligence for Social Good: Common Patterns as a Pathway to True Impact
Kush Varshney, Aleksandra Mojsilovic
AI for Social Good Workshop
Sat Jun 15th 08:30 AM — 06:00 PM Room 104 B

Teaching Meaningful Explanations
Noel Codella, Mike Hind, Karthikeyan Natesan Ramamurthy, Murray Campbell, Amit Dhurandhar, Kush Varshney, Dennis Wei, Aleksandra Mojsilovic
Workshop on Human in the Loop Learning
Fri Jun 14th8:30 AM – 6:00 PM Room 103

 

 

IBM Fellow, IBM Research

More AI stories

Text2Scene: Generating Compositional Scenes from Textual Descriptions

At CVPR 2019, IBM researchers introduce techniques to interpret visually descriptive language to generate compositional scene representations from textual descriptions.

Continue reading

Overcoming Challenges In Automated Image Captioning

At CVPR 2019, IBM researchers introduce an improved method to bridge the semantic gap between visual scenes and language to produce diverse, creative and human-like captions.

Continue reading

Label Set Operations (LaSO) Networks for Multi-Label Few-Shot Learning

Data augmentation is one of the leading methods to tackle the problem of few-shot learning, but current synthesis approaches only address the scenario of a single label per image, when in reality real life images may contain multiple objects. The IBM team came up with a novel technique for synthesizing samples with multiple labels.

Continue reading