AI

Advances in Machine Learning at ICML 2018

Share this post:

The Thirty-fifth International Conference on Machine Learning (ICML 2018) takes place July 10-15 in Stockholm, Sweden. ICML is the leading international machine learning conference, and IBM Research AI is a Gold sponsor at ICML 2018 and will present the following papers at the conference. We invite you to stop by these sessions and our booth B06:21 and look forward to seeing you in Stockholm.

Asynchronous Decentralized Parallel Stochastic Gradient Descent
X. Lian, W. Zhang, J. Liu and C. Zhang
Oral – Wed Jul 11 01:30 – 01:50 PM @ A9
Poster – Wed Jul 11 06:15 – 09:00 PM @ Hall B #86

SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
L. Nguyen, P. H. Nguyen, M. van Dijk, P. Richtarik, K. Scheinberg and M. Takac
Oral – Jul 11 5:30 – 5:40 PM @ A9
Poster – Jul 11 6:15 – 9:00 PM @ Hall B #116

A Distributed Second-Order Algorithm You Can Trust
C. Dünner, M. Gargiani, A. Lucchi, A. Bian, T. Hofmann and M. Jaggi
Oral – Jul 12 2:00 – 2:10 PM @ A9
Poster – Jul 12 6:15 – 9:00 PM @ Hall B #219

Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
S. Ghosh, J. Yao and F. Doshi-Velez
Oral – Jul 12 5:50 – 6:00 PM @ A4
Poster – Jul 12 6:15 – 9:00 PM @ Hall B #193

Using Inherent Structures to Design Lean 2-Layer RBMs
A. Bansal, A. Anand and C. Bhattacharyya
Oral – Jul 12 4:00 – 4:20 PM @ Victoria
Poster – Jul 12 6:15 – 9:00 PM @ Hall B #107

A Boo(n) for Evaluating Architecture Performance
O. Bajgar, R. Kadlec and J. Kleindienst
Oral – Jul 13 4:30 – 4:40 PM @ K1
Poster – Jul 13 6:15 – 9:00 PM @ Hall B #20

Parallel Bayesian Network Structure Learning
T. Gao and D. Wei
Oral – Jul 13 10:00 – 10:10 AM @ A4
Poster – Jul 13 6:15 – 9:00 PM @ Hall B #139

Why Interpretability in Machine Learning? An Answer Using Distributed Detection and Data Fusion Theory
K. Varshney, P. Khanduri, S. Zhang, P. Sharma and P. Varshney
Jul 14 Workshop on Human Interpretability in Machine Learning

Therapeutic Dialogue Modeling via Locality Sensitive Hashing
S. Garg, G. Cecchi, I. Rish, S. Gao, B. Bhaskar, G. Ver Steeg, P. Goyal and A. Galstyan
Jul 14 Workshop on AI and Computational Psychology: Theories, Algorithms and Applications (CompPsy)

Theory Learning and Logical Rule Induction with Neural Theorem Proving
A. Campero, A. Pareja, T. Klinger, J. Tenenbaum and S. Riedel
Jul 15 Workshop on Neural Abstract Machines and Program Induction (NAMPI)

Internal Model from Observations for Reward Shaping
D. Kimura, S. Chaudhury, R. Tachibana and S. Dasgupta
Workshop on Adaptive Learning Agents (ALA)

Dialogue Modeling Via Hash Functions
S. Garg, G. Cecchi, I. Rish, S. Gao, B. Bhaskar, G. Ver Steeg, P. Goyal and A. Galstyan
Fourth Linguistic and Cognitive Approaches to Dialog Agents (LACATODA) Workshop

More AI stories

Characterizing the Evolution of Tasks Within Occupations

The team at the IBM-MIT Watson AI Lab presented a new study at the AAAI Conference on AI, Ethics, and Society on “Learning Occupational Task-Shares Dynamics for the Future of Work” that shows how to predict changes in the economy’s demand for different tasks.

Continue reading

Deriving Complex Insights from Event-driven Continuous Time Bayesian Networks

Real-world decision making often involves situations and systems whose uncertain and inter-dependent variables interact in a complex and dynamic way. Additionally, many scenarios are influenced by external events that affect how system variables evolve. To address these complex scenarios for decision making, together with colleagues at the IBM T. J. Watson Research Center, we have developed a new dynamic, probabilistic graphical model called - Event-driven Continuous Time Bayesian Networks.

Continue reading

Progressing IBM Project Debater at AAAI-20 — and Beyond

At the thirty-fourth AAAI conference on Artificial Intelligence (AAAI-20), we will present two papers on recent advancements in Project Debater on two core tasks, both utilizing BERT.

Continue reading