no code implementations • NAACL (ACL) 2022 • Shiau Hong Lim, Laura Wynter
We present a system for document retrieval that combines direct classification with standard content-based retrieval approaches to significantly improve the relevance of the retrieved documents.
no code implementations • 1 Apr 2024 • Achintya Kundu, Fabian Lim, Aaron Chew, Laura Wynter, Penny Chong, Rhui Dih Lee
Supernet training of LLMs is of great interest in industrial applications as it confers the ability to produce a palette of smaller models at constant cost, regardless of the number of models (of different size / latency) produced.
no code implementations • 27 Mar 2023 • Achintya Kundu, Laura Wynter, Rhui Dih Lee, Luis Angel Bathen
Hence, we propose Transfer-Once-For-All (TOFA) for supernet-style training on small data sets with constant computational training cost over any number of edge deployment scenarios.
no code implementations • 27 Feb 2022 • Supriyo Ghosh, Laura Wynter, Shiau Hong Lim, Duc Thien Nguyen
We propose a framework, called neural-progressive hedging (NP), that leverages stochastic programming during the online phase of executing a reinforcement learning (RL) policy.
1 code implementation • 14 Oct 2021 • Fabian Lim, Laura Wynter, Shiau Hong Lim
Optimal transport is a framework for comparing measures whereby a cost is incurred for transporting one measure to another.
no code implementations • 19 Feb 2021 • Antoine Grosnit, Desmond Cai, Laura Wynter
We extend those results to offer a provably-convergent decentralized actor-critic algorithm for learning deterministic policies on continuous action spaces.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 18 Feb 2021 • Desmond Cai, Shiau Hong Lim, Laura Wynter
One of the main challenges in real-world reinforcement learning is to learn successfully from limited training samples.
no code implementations • 15 Jan 2021 • Duc Thien Nguyen, Shiau Hoong Lim, Laura Wynter, Desmond Cai
Federated learning brings potential benefits of faster learning, better solutions, and a greater propensity to transfer when heterogeneous data from different parties increases diversity.
no code implementations • 14 Sep 2020 • Achintya Kundu, Pengqian Yu, Laura Wynter, Shiau Hong Lim
We present a class of methods for robust, personalized federated learning, called Fed+, that unifies many federated learning algorithms.
1 code implementation • 22 Jul 2020 • Heiko Ludwig, Nathalie Baracaldo, Gegi Thomas, Yi Zhou, Ali Anwar, Shashank Rajamoni, Yuya Ong, Jayaram Radhakrishnan, Ashish Verma, Mathieu Sinn, Mark Purcell, Ambrish Rawat, Tran Minh, Naoise Holohan, Supriyo Chakraborty, Shalisha Whitherspoon, Dean Steuer, Laura Wynter, Hifaz Hassan, Sean Laguna, Mikhail Yurochkin, Mayank Agarwal, Ebube Chuba, Annie Abay
Federated Learning (FL) is an approach to conduct machine learning without centralizing training data in a single place, for reasons of privacy, confidentiality or data volume.
no code implementations • 1 Jun 2020 • Desmond Cai, Duc Thien Nguyen, Shiau Hong Lim, Laura Wynter
Crowdsourcing has emerged as an effective means for performing a number of machine learning tasks such as annotation and labelling of images and other data sets.
no code implementations • 3 Apr 2020 • Supriyo Ghosh, Sean Laguna, Shiau Hong Lim, Laura Wynter, Hasan Poonawala
Air traffic control is an example of a highly challenging operational problem that is readily amenable to human expertise augmentation via decision support technologies.
no code implementations • 14 May 2019 • Sebastien Blandin, Laura Wynter, Hasan Poonawala, Sean Laguna, Basile Dura
Increasing urban concentration raises operational challenges that can benefit from integrated monitoring and decision support.
no code implementations • 23 Apr 2019 • Karthik Nandakumar, Sebastien Blandin, Laura Wynter
We present results from several projects aimed at enabling the real-time understanding of crowds and their behaviour in the built environment.
no code implementations • 4 Mar 2019 • Baoyang Song, Hasan Poonawala, Laura Wynter, Sebastien Blandin
The preponderance of connected devices provides unprecedented opportunities for fine-grained monitoring of the public infrastructure.
no code implementations • 28 Feb 2019 • Jingfeng Zhang, Bo Han, Laura Wynter, Kian Hsiang Low, Mohan Kankanhalli
Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization.
1 code implementation • 7 Nov 2018 • Marc Jourdan, Sebastien Blandin, Laura Wynter, Pralhad Deshpande
The Bitcoin transaction graph is a public data structure organized as transactions between addresses, each associated with a logical entity.
1 code implementation • 29 Oct 2018 • Marc Jourdan, Sebastien Blandin, Laura Wynter, Pralhad Deshpande
Bitcoin has created a new exchange paradigm within which financial transactions can be trusted without an intermediary.
no code implementations • 27 Sep 2018 • Jingfeng Zhang, Laura Wynter
Recent work has studied the reasons for the remarkable performance of deep neural networks in image classification.