ΑΙhub.org
 

Tweets from #ICLR2019


by
16 May 2019



share this:

ICRL, the International Conference on Learning Representations, was held May 6th to 9th 2019 in New Orleans.

Relive the conference through some of the top tweets (#ICLR2019).

Invited talks

Best Papers

Congratulations to the two ICLR 2019 Best Paper winners!

The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks (arXiV)
Jonathan Frankle · Michael Carbin

Abstract - Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary experience is that the sparse architectures produced by pruning are difficult to train from the start, which would similarly improve training performance.

We find that a standard pruning technique naturally uncovers subnetworks whose initializations made them capable of training effectively. Based on these results, we articulate the "lottery ticket hypothesis:" dense, randomly-initialized, feed-forward networks contain subnetworks ("winning tickets") that - when trained in isolation - reach test accuracy comparable to the original network in a similar number of iterations. The winning tickets we find have won the initialization lottery: their connections have initial weights that make training particularly effective.
We present an algorithm to identify winning tickets and a series of experiments that support the lottery ticket hypothesis and the importance of these fortuitous initializations. We consistently find winning tickets that are less than 10-20% of the size of several fully-connected and convolutional feed-forward architectures for MNIST and CIFAR10. Above this size, the winning tickets that we find learn faster than the original network and reach higher test accuracy.

Summary in MIT Tech Review.

Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks (arXiv)
Yikang Shen · Shawn Tan · Alessandro Sordoni · Aaron Courville

Abstract - Natural language is hierarchically structured: smaller units (e.g., phrases) are nested within larger units (e.g., clauses). When a larger constituent ends, all of the smaller constituents that are nested within it must also be closed. While the standard LSTM architecture allows different neurons to track information at different time scales, it does not have an explicit bias towards modeling a hierarchy of constituents. This paper proposes to add such an inductive bias by ordering the neurons; a vector of master input and forget gates ensures that when a given neuron is updated, all the neurons that follow it in the ordering are also updated. Our novel recurrent architecture, ordered neurons LSTM (ON-LSTM), achieves good performance on four different tasks: language modeling, unsupervised parsing, targeted syntactic evaluation, and logical inference.

And a summary tweet from Microsoft with an accessible blog post.

Increasing diversity

Online presentations

38 presentations can be watched here.

As well as debates.

And here are a couple researchers putting their slides online.

Other summaries and highlights from the conference

AI for social good

Also, what is going on here?

Looks like a good PR move for their paper on the wizard of Wikipedia.

That's a wrap! See you all next year!




Sabine Hauert is Associate Professor at the University of Bristol, and Executive Trustee of AIhub.org
Sabine Hauert is Associate Professor at the University of Bristol, and Executive Trustee of AIhub.org




            AIhub is supported by:



Related posts :



Machine learning for atomic-scale simulations: balancing speed and physical laws

How much underlying physics can we safely “shortcut” without breaking a simulation?

Policy design for two-sided platforms with participation dynamics: Interview with Haruka Kiyohara

  09 Oct 2025
Studying the long-term impacts of decision-making algorithms on two-sided platforms such as e-commerce or music streaming apps.

The Machine Ethics podcast: What excites you about AI? Vol.2

This is a bonus episode looking back over answers to our question: What excites you about AI?

Interview with Janice Anta Zebaze: using AI to address energy supply challenges

  07 Oct 2025
Find out more about research combining renewable energy systems, tribology, and artificial intelligence.

How does AI affect how we learn? A cognitive psychologist explains why you learn when the work is hard

  06 Oct 2025
Early research is only beginning to scratch the surface of how AI technology will truly affect learning and cognition in the long run.

Interview with Zahra Ghorrati: developing frameworks for human activity recognition using wearable sensors

  03 Oct 2025
Find out more about research developing scalable and adaptive deep learning frameworks.

Diffusion beats autoregressive in data-constrained settings

  03 Oct 2025
How can we trade off more compute for less data?

Forthcoming machine learning and AI seminars: October 2025 edition

  02 Oct 2025
A list of free-to-attend AI-related seminars that are scheduled to take place between 3 October and 30 November 2025.



 

AIhub is supported by:






 












©2025.05 - Association for the Understanding of Artificial Intelligence